diff --git a/releases/1.35.1/Examples/tensorflow/quantization/keras/quantsim_cle.ipynb b/releases/1.35.1/Examples/tensorflow/quantization/keras/quantsim_cle.ipynb
index 0a55913..6adca66 100644
--- a/releases/1.35.1/Examples/tensorflow/quantization/keras/quantsim_cle.ipynb
+++ b/releases/1.35.1/Examples/tensorflow/quantization/keras/quantsim_cle.ipynb
@@ -277,7 +277,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "e3a590a2",
+   "id": "33b66b4d",
    "metadata": {
     "collapsed": false
    },
@@ -349,7 +349,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "ad19213c",
+   "id": "8a10e833",
    "metadata": {
     "collapsed": false
    },
@@ -406,7 +406,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "a3626c09",
+   "id": "86c35ac5",
    "metadata": {
     "collapsed": false
    },
diff --git a/releases/1.35.1/api_docs/onnx.html b/releases/1.35.1/api_docs/onnx.html
index c0d4d11..450964c 100644
--- a/releases/1.35.1/api_docs/onnx.html
+++ b/releases/1.35.1/api_docs/onnx.html
@@ -243,9 +243,15 @@
 <li class="toctree-l4"><a class="reference internal" href="torch_quantization.html#aimet-torch">aimet_torch</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="torch_quantization.html#api-reference">API Reference</a><ul>
 <li class="toctree-l6"><a class="reference internal" href="torch_model_guidelines.html"> Model Guidelines</a></li>
-<li class="toctree-l6"><a class="reference internal" href="torch_architecture_checker.html"> Architecture Checker API</a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_architecture_checker.html"> Architecture Checker API</a><ul>
+<li class="toctree-l7"><a class="reference internal" href="torch_architecture_checker.html#aimet_torch.arch_checker.arch_checker.ArchChecker.check_model_arch"><code class="docutils literal notranslate"><span class="pre">check_model_arch()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l6"><a class="reference internal" href="torch_model_preparer.html"> Model Preparer API</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="torch_model_preparer.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_model_preparer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_model_preparer.html#aimet_torch.model_preparer.prepare_model"><code class="docutils literal notranslate"><span class="pre">prepare_model()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_model_preparer.html#code-examples">Code Examples</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_model_preparer.html#limitations-of-torch-fx-symbolic-trace-api">Limitations of torch.fx symbolic trace API</a></li>
 </ul>
@@ -255,10 +261,23 @@
 <li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.enable_per_layer_mse_loss"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.enable_per_layer_mse_loss()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.analyze"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.analyze()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_common.utils.CallbackFunc"><code class="docutils literal notranslate"><span class="pre">CallbackFunc</span></code></a></li>
 </ul>
 </li>
-<li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#run-specific-utility">Run specific utility</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#run-specific-utility">Run specific utility</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.check_model_sensitivity_to_quantization"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.check_model_sensitivity_to_quantization()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.perform_per_layer_analysis_by_enabling_quant_wrappers"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.perform_per_layer_analysis_by_enabling_quant_wrappers()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.perform_per_layer_analysis_by_disabling_quant_wrappers"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.perform_per_layer_analysis_by_disabling_quant_wrappers()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.export_per_layer_encoding_min_max_range"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.export_per_layer_encoding_min_max_range()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.export_per_layer_stats_histogram"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.export_per_layer_stats_histogram()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.export_per_layer_mse_loss"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.export_per_layer_mse_loss()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
@@ -266,7 +285,16 @@
 <li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#guidelines">Guidelines</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.QuantizationSimModel"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.QuantizationSimModel.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel.compute_encodings()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.QuantizationSimModel.export"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel.export()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.save_checkpoint"><code class="docutils literal notranslate"><span class="pre">quantsim.save_checkpoint()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.load_checkpoint"><code class="docutils literal notranslate"><span class="pre">quantsim.load_checkpoint()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#enum-definition">Enum Definition</a><ul>
 <li class="toctree-l8"><a class="reference internal" href="torch_quantsim.html#aimet_common.defs.QuantScheme"><code class="docutils literal notranslate"><span class="pre">QuantScheme</span></code></a><ul>
 <li class="toctree-l9"><a class="reference internal" href="torch_quantsim.html#aimet_common.defs.QuantScheme.post_training_percentile"><code class="docutils literal notranslate"><span class="pre">QuantScheme.post_training_percentile</span></code></a></li>
@@ -284,8 +312,14 @@
 <li class="toctree-l6"><a class="reference internal" href="torch_adaround.html"> Adaptive Rounding API</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#examples-notebook-link">Examples Notebook Link</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#top-level-api">Top-level API</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#adaround-parameters">Adaround Parameters</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_adaround.html#aimet_torch.v1.adaround.adaround_weight.Adaround.apply_adaround"><code class="docutils literal notranslate"><span class="pre">apply_adaround()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#adaround-parameters">Adaround Parameters</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_adaround.html#aimet_torch.v1.adaround.adaround_weight.AdaroundParameters"><code class="docutils literal notranslate"><span class="pre">AdaroundParameters</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#enum-definition">Enum Definition</a><ul>
 <li class="toctree-l8"><a class="reference internal" href="torch_adaround.html#aimet_common.defs.QuantScheme"><code class="docutils literal notranslate"><span class="pre">QuantScheme</span></code></a><ul>
 <li class="toctree-l9"><a class="reference internal" href="torch_adaround.html#aimet_common.defs.QuantScheme.post_training_percentile"><code class="docutils literal notranslate"><span class="pre">QuantScheme.post_training_percentile</span></code></a></li>
@@ -304,15 +338,31 @@
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#introduction">Introduction</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#cross-layer-equalization-api">Cross Layer Equalization API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#cross-layer-equalization-api">Cross Layer Equalization API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_cross_layer_equalization.html#aimet_torch.cross_layer_equalization.equalize_model"><code class="docutils literal notranslate"><span class="pre">equalize_model()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#code-example">Code Example</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#primitive-apis">Primitive APIs</a><ul>
 <li class="toctree-l8"><a class="reference internal" href="torch_primitive_apis_cle.html">Primitive APIs for Cross Layer Equalization</a><ul>
 <li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#introduction">Introduction</a></li>
-<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#clssetinfo-definition">ClsSetInfo Definition</a></li>
-<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#higher-level-apis-for-cross-layer-equalization">Higher Level APIs for Cross Layer Equalization</a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#clssetinfo-definition">ClsSetInfo Definition</a><ul>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.cross_layer_equalization.ClsSetInfo"><code class="docutils literal notranslate"><span class="pre">ClsSetInfo</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#higher-level-apis-for-cross-layer-equalization">Higher Level APIs for Cross Layer Equalization</a><ul>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.batch_norm_fold.fold_all_batch_norms"><code class="docutils literal notranslate"><span class="pre">fold_all_batch_norms()</span></code></a></li>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.cross_layer_equalization.CrossLayerScaling.scale_model"><code class="docutils literal notranslate"><span class="pre">scale_model()</span></code></a></li>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.cross_layer_equalization.HighBiasFold.bias_fold"><code class="docutils literal notranslate"><span class="pre">bias_fold()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#code-examples-for-higher-level-apis">Code Examples for Higher Level APIs</a></li>
-<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#lower-level-apis-for-cross-layer-equalization">Lower Level APIs for Cross Layer Equalization</a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#lower-level-apis-for-cross-layer-equalization">Lower Level APIs for Cross Layer Equalization</a><ul>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.batch_norm_fold.fold_given_batch_norms"><code class="docutils literal notranslate"><span class="pre">fold_given_batch_norms()</span></code></a></li>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.cross_layer_equalization.CrossLayerScaling.scale_cls_sets"><code class="docutils literal notranslate"><span class="pre">scale_cls_sets()</span></code></a></li>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#id0"><code class="docutils literal notranslate"><span class="pre">bias_fold()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#code-examples-for-lower-level-apis">Code Examples for Lower Level APIs</a></li>
 </ul>
 </li>
@@ -322,7 +372,10 @@
 </li>
 <li class="toctree-l6"><a class="reference internal" href="torch_bias_correction.html"> Bias Correction API</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#user-guide-link">User Guide Link</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#bias-correction-api">Bias Correction API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#bias-correction-api">Bias Correction API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_bias_correction.html#aimet_torch.bias_correction.correct_bias"><code class="docutils literal notranslate"><span class="pre">correct_bias()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#convbninfotype">ConvBnInfoType</a><ul>
 <li class="toctree-l8"><a class="reference internal" href="torch_bias_correction.html#aimet_common.bias_correction.ConvBnInfoType"><code class="docutils literal notranslate"><span class="pre">ConvBnInfoType</span></code></a></li>
 </ul>
@@ -336,7 +389,10 @@
 </li>
 </ul>
 </li>
-<li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#quantization-params">Quantization Params</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#quantization-params">Quantization Params</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_bias_correction.html#aimet_torch.v1.quantsim.QuantParams"><code class="docutils literal notranslate"><span class="pre">QuantParams</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#code-example-1-empirical-bias-correction">Code Example #1 Empirical Bias Correction</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#code-example-2-analytical-empirical-bias-correction">Code Example #2 Analytical + Empirical Bias correction</a></li>
 </ul>
@@ -344,21 +400,46 @@
 <li class="toctree-l6"><a class="reference internal" href="torch_auto_quant.html"> AutoQuant API</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#examples-notebook-link">Examples Notebook Link</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_auto_quant.html#aimet_torch.v1.auto_quant.AutoQuant"><code class="docutils literal notranslate"><span class="pre">AutoQuant</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="torch_batchnorm_re_estimation.html"> BN Re-estimation APIs</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#introduction">Introduction</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#top-level-apis">Top-level APIs</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#top-level-apis">Top-level APIs</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_batchnorm_re_estimation.html#aimet_torch.bn_reestimation.reestimate_bn_stats"><code class="docutils literal notranslate"><span class="pre">reestimate_bn_stats()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_batchnorm_re_estimation.html#aimet_torch.batch_norm_fold.fold_all_batch_norms_to_scale"><code class="docutils literal notranslate"><span class="pre">fold_all_batch_norms_to_scale()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#code-example-bn-reestimation">Code Example - BN-Reestimation</a></li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="torch_multi_gpu.html"> Multi-GPU guidelines</a></li>
 <li class="toctree-l6"><a class="reference internal" href="torch_peft_lora.html"> PEFT LoRA APIs</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_peft_lora.html#user-flow">User flow</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_peft_lora.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_peft_lora.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.AdapterMetaData"><code class="docutils literal notranslate"><span class="pre">AdapterMetaData</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.replace_lora_layers_with_quantizable_layers"><code class="docutils literal notranslate"><span class="pre">peft.replace_lora_layers_with_quantizable_layers()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.track_lora_meta_data"><code class="docutils literal notranslate"><span class="pre">peft.track_lora_meta_data()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.disable_lora_adapters"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.disable_lora_adapters()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.enable_adapter_and_load_weights"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.enable_adapter_and_load_weights()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.export_adapter_weights"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.export_adapter_weights()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.freeze_base_model"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.freeze_base_model()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.freeze_base_model_activation_quantizers"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.freeze_base_model_activation_quantizers()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.freeze_base_model_param_quantizers"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.freeze_base_model_param_quantizers()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.get_fp_lora_layer"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.get_fp_lora_layer()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.get_quantized_lora_layer"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.get_quantized_lora_layer()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.quantize_lora_scale_with_fixed_range"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.quantize_lora_scale_with_fixed_range()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.set_bitwidth_for_lora_adapters"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.set_bitwidth_for_lora_adapters()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 </ul>
 </li>
 </ul>
@@ -370,31 +451,106 @@
 <li class="toctree-l5"><a class="reference internal" href="torch_quantization.html#backwards-compatibility">Backwards Compatibility</a></li>
 <li class="toctree-l5"><a class="reference internal" href="torch_quantization.html#id1">API Reference</a><ul>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/quantized_modules.html">Quantized Modules</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.input_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.input_quantizers</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.output_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.output_quantizers</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.param_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.param_quantizers</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.__quant_init__"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.__quant_init__()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.compute_encodings()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.forward"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.forward()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#configuration">Configuration</a></li>
 <li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#computing-encodings">Computing Encodings</a></li>
 <li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#quantized-module-classes">Quantized Module Classes</a></li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/quantizer.html">Quantizers</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantizer.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantizer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase"><code class="docutils literal notranslate"><span class="pre">QuantizerBase</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.allow_overwrite"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.allow_overwrite()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.compute_encodings()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.get_encoding"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.get_encoding()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.get_legacy_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.get_legacy_encodings()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.is_initialized"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.is_initialized()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.register_quantization_parameter"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.register_quantization_parameter()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.set_legacy_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.set_legacy_encodings()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizeDequantize"><code class="docutils literal notranslate"><span class="pre">QuantizeDequantize</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizeDequantize.forward"><code class="docutils literal notranslate"><span class="pre">QuantizeDequantize.forward()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.Quantize"><code class="docutils literal notranslate"><span class="pre">Quantize</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.Quantize.forward"><code class="docutils literal notranslate"><span class="pre">Quantize.forward()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html">QuantizationMixin</a><ul>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin</span></code></a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.input_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.input_quantizers</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.output_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.output_quantizers</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.param_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.param_quantizers</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.forward"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.forward()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.__quant_init__"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.__quant_init__()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.set_kernel"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.set_kernel()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.set_default_kernel"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.set_default_kernel()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.compute_encodings()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.from_module"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.from_module()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.get_default_kernel"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.get_default_kernel()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.get_kernel"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.get_kernel()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.implements"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.implements()</span></code></a></li>
+</ul>
+</li>
 </ul>
 </li>
-<li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html">QuantizationMixin</a></li>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html">quantization.affine</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#classes">Classes</a></li>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#functions">Functions</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#classes">Classes</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.Quantize"><code class="docutils literal notranslate"><span class="pre">Quantize</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.QuantizeDequantize"><code class="docutils literal notranslate"><span class="pre">QuantizeDequantize</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#functions">Functions</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.quantize"><code class="docutils literal notranslate"><span class="pre">quantize()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.quantize_dequantize"><code class="docutils literal notranslate"><span class="pre">quantize_dequantize()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.dequantize"><code class="docutils literal notranslate"><span class="pre">dequantize()</span></code></a></li>
+</ul>
+</li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html">quantization.float</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html#classes">Classes</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html#classes">Classes</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html#aimet_torch.v2.quantization.float.FloatQuantizeDequantize"><code class="docutils literal notranslate"><span class="pre">FloatQuantizeDequantize</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html#aimet_torch.v2.quantization.float.QuantizeDequantize"><code class="docutils literal notranslate"><span class="pre">QuantizeDequantize</span></code></a></li>
+</ul>
+</li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/encoding_analyzer.html">Encoding Analyzers</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#variants">Variants</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer"><code class="docutils literal notranslate"><span class="pre">EncodingAnalyzer</span></code></a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.compute_encodings"><code class="docutils literal notranslate"><span class="pre">EncodingAnalyzer.compute_encodings()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.reset_stats"><code class="docutils literal notranslate"><span class="pre">EncodingAnalyzer.reset_stats()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.update_stats"><code class="docutils literal notranslate"><span class="pre">EncodingAnalyzer.update_stats()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#variants">Variants</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.MinMaxEncodingAnalyzer"><code class="docutils literal notranslate"><span class="pre">MinMaxEncodingAnalyzer</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.SqnrEncodingAnalyzer"><code class="docutils literal notranslate"><span class="pre">SqnrEncodingAnalyzer</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.PercentileEncodingAnalyzer"><code class="docutils literal notranslate"><span class="pre">PercentileEncodingAnalyzer</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/visualization_tools.html">Visualization Tools</a><ul>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/visualization_tools.html#aimet_torch.v2.visualization_tools.visualize_stats"><code class="docutils literal notranslate"><span class="pre">visualize_stats()</span></code></a></li>
 </ul>
 </li>
-<li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/visualization_tools.html">Visualization Tools</a></li>
 </ul>
 </li>
 </ul>
@@ -403,31 +559,102 @@
 </li>
 <li class="toctree-l3"><a class="reference internal" href="torch_compress.html">PyTorch Model Compression API</a><ul>
 <li class="toctree-l4"><a class="reference internal" href="torch_compress.html#introduction">Introduction</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#top-level-api-for-compression">Top-level API for Compression</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#top-level-api-for-compression">Top-level API for Compression</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.compress.ModelCompressor"><code class="docutils literal notranslate"><span class="pre">ModelCompressor</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.compress.ModelCompressor.compress_model"><code class="docutils literal notranslate"><span class="pre">ModelCompressor.compress_model()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_compress.html#greedy-selection-parameters">Greedy Selection Parameters</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_common.defs.GreedySelectionParameters"><code class="docutils literal notranslate"><span class="pre">GreedySelectionParameters</span></code></a></li>
 </ul>
 </li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#spatial-svd-configuration">Spatial SVD Configuration</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#weight-svd-configuration">Weight SVD Configuration</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#channel-pruning-configuration">Channel Pruning Configuration</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#configuration-definitions">Configuration Definitions</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#spatial-svd-configuration">Spatial SVD Configuration</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.AutoModeParams"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.AutoModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.ManualModeParams"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.ManualModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.Mode"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.Mode.auto"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode.auto</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.Mode.manual"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode.manual</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#weight-svd-configuration">Weight SVD Configuration</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.AutoModeParams"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.AutoModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.ManualModeParams"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.ManualModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.Mode"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.Mode</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.Mode.auto"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.Mode.auto</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.Mode.manual"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.Mode.manual</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#channel-pruning-configuration">Channel Pruning Configuration</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.AutoModeParams"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.AutoModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.ManualModeParams"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.ManualModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.Mode"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.Mode</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.Mode.auto"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.Mode.auto</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.Mode.manual"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.Mode.manual</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#configuration-definitions">Configuration Definitions</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ModuleCompRatioPair"><code class="docutils literal notranslate"><span class="pre">ModuleCompRatioPair</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_compress.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="torch_visualization_compression.html">PyTorch Model Visualization API for Compression</a><ul>
-<li class="toctree-l4"><a class="reference internal" href="torch_visualization_compression.html#top-level-api-compression">Top-level API Compression</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_visualization_compression.html#top-level-api-compression">Top-level API Compression</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_visualization_compression.html#aimet_torch.visualize_serialized_data.VisualizeCompression"><code class="docutils literal notranslate"><span class="pre">VisualizeCompression</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_visualization_compression.html#aimet_torch.visualize_serialized_data.VisualizeCompression.display_eval_scores"><code class="docutils literal notranslate"><span class="pre">VisualizeCompression.display_eval_scores()</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_visualization_compression.html#aimet_torch.visualize_serialized_data.VisualizeCompression.display_comp_ratio_plot"><code class="docutils literal notranslate"><span class="pre">VisualizeCompression.display_comp_ratio_plot()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_visualization_compression.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="torch_visualization_quantization.html">PyTorch Model Visualization API for Quantization</a><ul>
-<li class="toctree-l4"><a class="reference internal" href="torch_visualization_quantization.html#top-level-api-quantization">Top-level API Quantization</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_visualization_quantization.html#top-level-api-quantization">Top-level API Quantization</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_visualization_quantization.html#aimet_torch.visualize_model.visualize_relative_weight_ranges_to_identify_problematic_layers"><code class="docutils literal notranslate"><span class="pre">visualize_relative_weight_ranges_to_identify_problematic_layers()</span></code></a></li>
+<li class="toctree-l5"><a class="reference internal" href="torch_visualization_quantization.html#aimet_torch.visualize_model.visualize_weight_ranges"><code class="docutils literal notranslate"><span class="pre">visualize_weight_ranges()</span></code></a></li>
+<li class="toctree-l5"><a class="reference internal" href="torch_visualization_quantization.html#aimet_torch.visualize_model.visualize_changes_after_optimization"><code class="docutils literal notranslate"><span class="pre">visualize_changes_after_optimization()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_visualization_quantization.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="torch_layer_output_generation.html">PyTorch Debug API</a><ul>
-<li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#top-level-api">Top-level API</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#enum-definition">Enum Definition</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.LayerOutputUtil"><code class="docutils literal notranslate"><span class="pre">LayerOutputUtil</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.LayerOutputUtil.generate_layer_outputs"><code class="docutils literal notranslate"><span class="pre">LayerOutputUtil.generate_layer_outputs()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#enum-definition">Enum Definition</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.NamingScheme"><code class="docutils literal notranslate"><span class="pre">NamingScheme</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.NamingScheme.ONNX"><code class="docutils literal notranslate"><span class="pre">NamingScheme.ONNX</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.NamingScheme.PYTORCH"><code class="docutils literal notranslate"><span class="pre">NamingScheme.PYTORCH</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.NamingScheme.TORCHSCRIPT"><code class="docutils literal notranslate"><span class="pre">NamingScheme.TORCHSCRIPT</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#code-example">Code Example</a></li>
 </ul>
 </li>
@@ -437,27 +664,49 @@
 <li class="toctree-l3"><a class="reference internal" href="keras_quantization.html">TensorFlow Model Quantization API</a><ul>
 <li class="toctree-l4"><a class="reference internal" href="keras_model_guidelines.html"> Model Guidelines</a></li>
 <li class="toctree-l4"><a class="reference internal" href="keras_model_preparer.html"> Model Preparer API</a><ul>
-<li class="toctree-l5"><a class="reference internal" href="keras_model_preparer.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_model_preparer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_model_preparer.html#aimet_tensorflow.keras.model_preparer.prepare_model"><code class="docutils literal notranslate"><span class="pre">prepare_model()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_model_preparer.html#code-examples">Code Examples</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_model_preparer.html#limitations">Limitations</a></li>
 </ul>
 </li>
 <li class="toctree-l4"><a class="reference internal" href="keras_quant_analyzer.html"> Quant Analyzer API</a><ul>
-<li class="toctree-l5"><a class="reference internal" href="keras_quant_analyzer.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_quant_analyzer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_quant_analyzer.html#aimet_tensorflow.keras.quant_analyzer.QuantAnalyzer"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="keras_quant_analyzer.html#aimet_tensorflow.keras.quant_analyzer.QuantAnalyzer.analyze"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.analyze()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_quant_analyzer.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l4"><a class="reference internal" href="keras_quantsim.html"> Quantization Simulation API</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="keras_quantsim.html#user-guide-link">User Guide Link</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_quantsim.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_quantsim.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_quantsim.html#aimet_tensorflow.keras.quantsim.QuantizationSimModel"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="keras_quantsim.html#aimet_tensorflow.keras.quantsim.QuantizationSimModel.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel.compute_encodings()</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="keras_quantsim.html#aimet_tensorflow.keras.quantsim.QuantizationSimModel.export"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel.export()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_quantsim.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l4"><a class="reference internal" href="keras_adaround.html"> Adaptive Rounding API</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#examples-notebook-link">Examples Notebook Link</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#top-level-api">Top-level API</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#adaround-parameters">Adaround Parameters</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_adaround.html#aimet_tensorflow.keras.adaround_weight.Adaround.apply_adaround"><code class="docutils literal notranslate"><span class="pre">apply_adaround()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#adaround-parameters">Adaround Parameters</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_adaround.html#aimet_tensorflow.keras.adaround_weight.AdaroundParameters"><code class="docutils literal notranslate"><span class="pre">AdaroundParameters</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#enum-definition">Enum Definition</a><ul>
 <li class="toctree-l6"><a class="reference internal" href="keras_adaround.html#aimet_common.defs.QuantScheme"><code class="docutils literal notranslate"><span class="pre">QuantScheme</span></code></a><ul>
 <li class="toctree-l7"><a class="reference internal" href="keras_adaround.html#aimet_common.defs.QuantScheme.post_training_percentile"><code class="docutils literal notranslate"><span class="pre">QuantScheme.post_training_percentile</span></code></a></li>
@@ -476,15 +725,34 @@
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#introduction">Introduction</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#cross-layer-equalization-api">Cross Layer Equalization API</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#cross-layer-equalization-api">Cross Layer Equalization API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_cross_layer_equalization.html#aimet_tensorflow.keras.cross_layer_equalization.equalize_model"><code class="docutils literal notranslate"><span class="pre">equalize_model()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#code-example">Code Example</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#primitive-apis">Primitive APIs</a><ul>
 <li class="toctree-l6"><a class="reference internal" href="keras_primitive_apis_cle.html">Primitive APIs for Cross Layer Equalization</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#introduction">Introduction</a></li>
-<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#higher-level-apis-for-cross-layer-equalization">Higher Level APIs for Cross Layer Equalization</a></li>
+<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#higher-level-apis-for-cross-layer-equalization">Higher Level APIs for Cross Layer Equalization</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.batch_norm_fold.fold_all_batch_norms"><code class="docutils literal notranslate"><span class="pre">fold_all_batch_norms()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.CrossLayerScaling.scale_model"><code class="docutils literal notranslate"><span class="pre">scale_model()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.HighBiasFold.bias_fold"><code class="docutils literal notranslate"><span class="pre">bias_fold()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#code-examples-for-higher-level-apis">Code Examples for Higher Level APIs</a></li>
-<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#lower-level-apis-for-cross-layer-equalization">Lower Level APIs for Cross Layer Equalization</a></li>
-<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#custom-datatype-used">Custom Datatype used</a></li>
+<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#lower-level-apis-for-cross-layer-equalization">Lower Level APIs for Cross Layer Equalization</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.batch_norm_fold.fold_given_batch_norms"><code class="docutils literal notranslate"><span class="pre">fold_given_batch_norms()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.CrossLayerScaling.scale_cls_sets"><code class="docutils literal notranslate"><span class="pre">scale_cls_sets()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#id0"><code class="docutils literal notranslate"><span class="pre">bias_fold()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#custom-datatype-used">Custom Datatype used</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.ClsSetInfo"><code class="docutils literal notranslate"><span class="pre">ClsSetInfo</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.ClsSetInfo.ClsSetLayerPairInfo"><code class="docutils literal notranslate"><span class="pre">ClsSetInfo.ClsSetLayerPairInfo</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#code-example-for-lower-level-apis">Code Example for Lower level APIs</a></li>
 <li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#example-helper-methods-to-perform-cle-in-manual-mode">Example helper methods to perform CLE in manual mode</a></li>
 </ul>
@@ -496,7 +764,11 @@
 <li class="toctree-l4"><a class="reference internal" href="keras_batchnorm_re_estimation.html"> BN Re-estimation APIs</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#introduction">Introduction</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#top-level-apis">Top-level APIs</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#top-level-apis">Top-level APIs</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_batchnorm_re_estimation.html#aimet_tensorflow.keras.bn_reestimation.reestimate_bn_stats"><code class="docutils literal notranslate"><span class="pre">reestimate_bn_stats()</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="keras_batchnorm_re_estimation.html#aimet_tensorflow.keras.batch_norm_fold.fold_all_batch_norms_to_scale"><code class="docutils literal notranslate"><span class="pre">fold_all_batch_norms_to_scale()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#code-example">Code Example</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#limitations">Limitations</a></li>
 </ul>
@@ -504,15 +776,39 @@
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="keras_layer_output_generation.html">TensorFlow Debug API</a><ul>
-<li class="toctree-l4"><a class="reference internal" href="keras_layer_output_generation.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l4"><a class="reference internal" href="keras_layer_output_generation.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="keras_layer_output_generation.html#aimet_tensorflow.keras.layer_output_utils.LayerOutputUtil"><code class="docutils literal notranslate"><span class="pre">LayerOutputUtil</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_layer_output_generation.html#aimet_tensorflow.keras.layer_output_utils.LayerOutputUtil.generate_layer_outputs"><code class="docutils literal notranslate"><span class="pre">LayerOutputUtil.generate_layer_outputs()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="keras_layer_output_generation.html#code-example">Code Example</a></li>
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="keras_compression.html">TensorFlow Model Compression API</a><ul>
 <li class="toctree-l4"><a class="reference internal" href="keras_compression.html#introduction">Introduction</a></li>
-<li class="toctree-l4"><a class="reference internal" href="keras_compression.html#top-level-api-for-compression">Top-level API for Compression</a></li>
+<li class="toctree-l4"><a class="reference internal" href="keras_compression.html#top-level-api-for-compression">Top-level API for Compression</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.compress.ModelCompressor"><code class="docutils literal notranslate"><span class="pre">ModelCompressor</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.compress.ModelCompressor.compress_model"><code class="docutils literal notranslate"><span class="pre">ModelCompressor.compress_model()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="keras_compression.html#greedy-selection-parameters">Greedy Selection Parameters</a></li>
-<li class="toctree-l4"><a class="reference internal" href="keras_compression.html#spatial-svd-configuration">Spatial SVD Configuration</a></li>
+<li class="toctree-l4"><a class="reference internal" href="keras_compression.html#spatial-svd-configuration">Spatial SVD Configuration</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.AutoModeParams"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.AutoModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.ManualModeParams"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.ManualModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.Mode"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.Mode.auto"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode.auto</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.Mode.manual"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode.manual</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="keras_compression.html#configuration-definitions">Configuration Definitions</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="keras_compression.html#aimet_common.defs.CostMetric"><code class="docutils literal notranslate"><span class="pre">CostMetric</span></code></a><ul>
 <li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_common.defs.CostMetric.mac"><code class="docutils literal notranslate"><span class="pre">CostMetric.mac</span></code></a></li>
@@ -525,6 +821,7 @@
 <li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_common.defs.CompressionScheme.weight_svd"><code class="docutils literal notranslate"><span class="pre">CompressionScheme.weight_svd</span></code></a></li>
 </ul>
 </li>
+<li class="toctree-l5"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.ModuleCompRatioPair"><code class="docutils literal notranslate"><span class="pre">ModuleCompRatioPair</span></code></a></li>
 </ul>
 </li>
 <li class="toctree-l4"><a class="reference internal" href="keras_compression.html#code-examples">Code Examples</a></li>
diff --git a/releases/1.35.1/api_docs/onnx_adaround.html b/releases/1.35.1/api_docs/onnx_adaround.html
index 7cd5159..2945f40 100644
--- a/releases/1.35.1/api_docs/onnx_adaround.html
+++ b/releases/1.35.1/api_docs/onnx_adaround.html
@@ -243,9 +243,15 @@
 <li class="toctree-l4"><a class="reference internal" href="torch_quantization.html#aimet-torch">aimet_torch</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="torch_quantization.html#api-reference">API Reference</a><ul>
 <li class="toctree-l6"><a class="reference internal" href="torch_model_guidelines.html"> Model Guidelines</a></li>
-<li class="toctree-l6"><a class="reference internal" href="torch_architecture_checker.html"> Architecture Checker API</a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_architecture_checker.html"> Architecture Checker API</a><ul>
+<li class="toctree-l7"><a class="reference internal" href="torch_architecture_checker.html#aimet_torch.arch_checker.arch_checker.ArchChecker.check_model_arch"><code class="docutils literal notranslate"><span class="pre">check_model_arch()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l6"><a class="reference internal" href="torch_model_preparer.html"> Model Preparer API</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="torch_model_preparer.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_model_preparer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_model_preparer.html#aimet_torch.model_preparer.prepare_model"><code class="docutils literal notranslate"><span class="pre">prepare_model()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_model_preparer.html#code-examples">Code Examples</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_model_preparer.html#limitations-of-torch-fx-symbolic-trace-api">Limitations of torch.fx symbolic trace API</a></li>
 </ul>
@@ -255,10 +261,23 @@
 <li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.enable_per_layer_mse_loss"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.enable_per_layer_mse_loss()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.analyze"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.analyze()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_common.utils.CallbackFunc"><code class="docutils literal notranslate"><span class="pre">CallbackFunc</span></code></a></li>
 </ul>
 </li>
-<li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#run-specific-utility">Run specific utility</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#run-specific-utility">Run specific utility</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.check_model_sensitivity_to_quantization"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.check_model_sensitivity_to_quantization()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.perform_per_layer_analysis_by_enabling_quant_wrappers"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.perform_per_layer_analysis_by_enabling_quant_wrappers()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.perform_per_layer_analysis_by_disabling_quant_wrappers"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.perform_per_layer_analysis_by_disabling_quant_wrappers()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.export_per_layer_encoding_min_max_range"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.export_per_layer_encoding_min_max_range()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.export_per_layer_stats_histogram"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.export_per_layer_stats_histogram()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.export_per_layer_mse_loss"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.export_per_layer_mse_loss()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
@@ -266,7 +285,16 @@
 <li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#guidelines">Guidelines</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.QuantizationSimModel"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.QuantizationSimModel.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel.compute_encodings()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.QuantizationSimModel.export"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel.export()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.save_checkpoint"><code class="docutils literal notranslate"><span class="pre">quantsim.save_checkpoint()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.load_checkpoint"><code class="docutils literal notranslate"><span class="pre">quantsim.load_checkpoint()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#enum-definition">Enum Definition</a><ul>
 <li class="toctree-l8"><a class="reference internal" href="torch_quantsim.html#aimet_common.defs.QuantScheme"><code class="docutils literal notranslate"><span class="pre">QuantScheme</span></code></a><ul>
 <li class="toctree-l9"><a class="reference internal" href="torch_quantsim.html#aimet_common.defs.QuantScheme.post_training_percentile"><code class="docutils literal notranslate"><span class="pre">QuantScheme.post_training_percentile</span></code></a></li>
@@ -284,8 +312,14 @@
 <li class="toctree-l6"><a class="reference internal" href="torch_adaround.html"> Adaptive Rounding API</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#examples-notebook-link">Examples Notebook Link</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#top-level-api">Top-level API</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#adaround-parameters">Adaround Parameters</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_adaround.html#aimet_torch.v1.adaround.adaround_weight.Adaround.apply_adaround"><code class="docutils literal notranslate"><span class="pre">apply_adaround()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#adaround-parameters">Adaround Parameters</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_adaround.html#aimet_torch.v1.adaround.adaround_weight.AdaroundParameters"><code class="docutils literal notranslate"><span class="pre">AdaroundParameters</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#enum-definition">Enum Definition</a><ul>
 <li class="toctree-l8"><a class="reference internal" href="torch_adaround.html#aimet_common.defs.QuantScheme"><code class="docutils literal notranslate"><span class="pre">QuantScheme</span></code></a><ul>
 <li class="toctree-l9"><a class="reference internal" href="torch_adaround.html#aimet_common.defs.QuantScheme.post_training_percentile"><code class="docutils literal notranslate"><span class="pre">QuantScheme.post_training_percentile</span></code></a></li>
@@ -304,15 +338,31 @@
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#introduction">Introduction</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#cross-layer-equalization-api">Cross Layer Equalization API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#cross-layer-equalization-api">Cross Layer Equalization API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_cross_layer_equalization.html#aimet_torch.cross_layer_equalization.equalize_model"><code class="docutils literal notranslate"><span class="pre">equalize_model()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#code-example">Code Example</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#primitive-apis">Primitive APIs</a><ul>
 <li class="toctree-l8"><a class="reference internal" href="torch_primitive_apis_cle.html">Primitive APIs for Cross Layer Equalization</a><ul>
 <li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#introduction">Introduction</a></li>
-<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#clssetinfo-definition">ClsSetInfo Definition</a></li>
-<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#higher-level-apis-for-cross-layer-equalization">Higher Level APIs for Cross Layer Equalization</a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#clssetinfo-definition">ClsSetInfo Definition</a><ul>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.cross_layer_equalization.ClsSetInfo"><code class="docutils literal notranslate"><span class="pre">ClsSetInfo</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#higher-level-apis-for-cross-layer-equalization">Higher Level APIs for Cross Layer Equalization</a><ul>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.batch_norm_fold.fold_all_batch_norms"><code class="docutils literal notranslate"><span class="pre">fold_all_batch_norms()</span></code></a></li>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.cross_layer_equalization.CrossLayerScaling.scale_model"><code class="docutils literal notranslate"><span class="pre">scale_model()</span></code></a></li>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.cross_layer_equalization.HighBiasFold.bias_fold"><code class="docutils literal notranslate"><span class="pre">bias_fold()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#code-examples-for-higher-level-apis">Code Examples for Higher Level APIs</a></li>
-<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#lower-level-apis-for-cross-layer-equalization">Lower Level APIs for Cross Layer Equalization</a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#lower-level-apis-for-cross-layer-equalization">Lower Level APIs for Cross Layer Equalization</a><ul>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.batch_norm_fold.fold_given_batch_norms"><code class="docutils literal notranslate"><span class="pre">fold_given_batch_norms()</span></code></a></li>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.cross_layer_equalization.CrossLayerScaling.scale_cls_sets"><code class="docutils literal notranslate"><span class="pre">scale_cls_sets()</span></code></a></li>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#id0"><code class="docutils literal notranslate"><span class="pre">bias_fold()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#code-examples-for-lower-level-apis">Code Examples for Lower Level APIs</a></li>
 </ul>
 </li>
@@ -322,7 +372,10 @@
 </li>
 <li class="toctree-l6"><a class="reference internal" href="torch_bias_correction.html"> Bias Correction API</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#user-guide-link">User Guide Link</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#bias-correction-api">Bias Correction API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#bias-correction-api">Bias Correction API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_bias_correction.html#aimet_torch.bias_correction.correct_bias"><code class="docutils literal notranslate"><span class="pre">correct_bias()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#convbninfotype">ConvBnInfoType</a><ul>
 <li class="toctree-l8"><a class="reference internal" href="torch_bias_correction.html#aimet_common.bias_correction.ConvBnInfoType"><code class="docutils literal notranslate"><span class="pre">ConvBnInfoType</span></code></a></li>
 </ul>
@@ -336,7 +389,10 @@
 </li>
 </ul>
 </li>
-<li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#quantization-params">Quantization Params</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#quantization-params">Quantization Params</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_bias_correction.html#aimet_torch.v1.quantsim.QuantParams"><code class="docutils literal notranslate"><span class="pre">QuantParams</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#code-example-1-empirical-bias-correction">Code Example #1 Empirical Bias Correction</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#code-example-2-analytical-empirical-bias-correction">Code Example #2 Analytical + Empirical Bias correction</a></li>
 </ul>
@@ -344,21 +400,46 @@
 <li class="toctree-l6"><a class="reference internal" href="torch_auto_quant.html"> AutoQuant API</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#examples-notebook-link">Examples Notebook Link</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_auto_quant.html#aimet_torch.v1.auto_quant.AutoQuant"><code class="docutils literal notranslate"><span class="pre">AutoQuant</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="torch_batchnorm_re_estimation.html"> BN Re-estimation APIs</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#introduction">Introduction</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#top-level-apis">Top-level APIs</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#top-level-apis">Top-level APIs</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_batchnorm_re_estimation.html#aimet_torch.bn_reestimation.reestimate_bn_stats"><code class="docutils literal notranslate"><span class="pre">reestimate_bn_stats()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_batchnorm_re_estimation.html#aimet_torch.batch_norm_fold.fold_all_batch_norms_to_scale"><code class="docutils literal notranslate"><span class="pre">fold_all_batch_norms_to_scale()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#code-example-bn-reestimation">Code Example - BN-Reestimation</a></li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="torch_multi_gpu.html"> Multi-GPU guidelines</a></li>
 <li class="toctree-l6"><a class="reference internal" href="torch_peft_lora.html"> PEFT LoRA APIs</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_peft_lora.html#user-flow">User flow</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_peft_lora.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_peft_lora.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.AdapterMetaData"><code class="docutils literal notranslate"><span class="pre">AdapterMetaData</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.replace_lora_layers_with_quantizable_layers"><code class="docutils literal notranslate"><span class="pre">peft.replace_lora_layers_with_quantizable_layers()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.track_lora_meta_data"><code class="docutils literal notranslate"><span class="pre">peft.track_lora_meta_data()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.disable_lora_adapters"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.disable_lora_adapters()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.enable_adapter_and_load_weights"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.enable_adapter_and_load_weights()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.export_adapter_weights"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.export_adapter_weights()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.freeze_base_model"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.freeze_base_model()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.freeze_base_model_activation_quantizers"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.freeze_base_model_activation_quantizers()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.freeze_base_model_param_quantizers"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.freeze_base_model_param_quantizers()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.get_fp_lora_layer"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.get_fp_lora_layer()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.get_quantized_lora_layer"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.get_quantized_lora_layer()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.quantize_lora_scale_with_fixed_range"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.quantize_lora_scale_with_fixed_range()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.set_bitwidth_for_lora_adapters"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.set_bitwidth_for_lora_adapters()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 </ul>
 </li>
 </ul>
@@ -370,31 +451,106 @@
 <li class="toctree-l5"><a class="reference internal" href="torch_quantization.html#backwards-compatibility">Backwards Compatibility</a></li>
 <li class="toctree-l5"><a class="reference internal" href="torch_quantization.html#id1">API Reference</a><ul>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/quantized_modules.html">Quantized Modules</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.input_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.input_quantizers</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.output_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.output_quantizers</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.param_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.param_quantizers</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.__quant_init__"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.__quant_init__()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.compute_encodings()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.forward"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.forward()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#configuration">Configuration</a></li>
 <li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#computing-encodings">Computing Encodings</a></li>
 <li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#quantized-module-classes">Quantized Module Classes</a></li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/quantizer.html">Quantizers</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantizer.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantizer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase"><code class="docutils literal notranslate"><span class="pre">QuantizerBase</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.allow_overwrite"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.allow_overwrite()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.compute_encodings()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.get_encoding"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.get_encoding()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.get_legacy_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.get_legacy_encodings()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.is_initialized"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.is_initialized()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.register_quantization_parameter"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.register_quantization_parameter()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.set_legacy_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.set_legacy_encodings()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizeDequantize"><code class="docutils literal notranslate"><span class="pre">QuantizeDequantize</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizeDequantize.forward"><code class="docutils literal notranslate"><span class="pre">QuantizeDequantize.forward()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.Quantize"><code class="docutils literal notranslate"><span class="pre">Quantize</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.Quantize.forward"><code class="docutils literal notranslate"><span class="pre">Quantize.forward()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html">QuantizationMixin</a><ul>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin</span></code></a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.input_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.input_quantizers</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.output_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.output_quantizers</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.param_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.param_quantizers</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.forward"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.forward()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.__quant_init__"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.__quant_init__()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.set_kernel"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.set_kernel()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.set_default_kernel"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.set_default_kernel()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.compute_encodings()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.from_module"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.from_module()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.get_default_kernel"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.get_default_kernel()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.get_kernel"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.get_kernel()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.implements"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.implements()</span></code></a></li>
+</ul>
+</li>
 </ul>
 </li>
-<li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html">QuantizationMixin</a></li>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html">quantization.affine</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#classes">Classes</a></li>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#functions">Functions</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#classes">Classes</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.Quantize"><code class="docutils literal notranslate"><span class="pre">Quantize</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.QuantizeDequantize"><code class="docutils literal notranslate"><span class="pre">QuantizeDequantize</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#functions">Functions</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.quantize"><code class="docutils literal notranslate"><span class="pre">quantize()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.quantize_dequantize"><code class="docutils literal notranslate"><span class="pre">quantize_dequantize()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.dequantize"><code class="docutils literal notranslate"><span class="pre">dequantize()</span></code></a></li>
+</ul>
+</li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html">quantization.float</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html#classes">Classes</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html#classes">Classes</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html#aimet_torch.v2.quantization.float.FloatQuantizeDequantize"><code class="docutils literal notranslate"><span class="pre">FloatQuantizeDequantize</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html#aimet_torch.v2.quantization.float.QuantizeDequantize"><code class="docutils literal notranslate"><span class="pre">QuantizeDequantize</span></code></a></li>
+</ul>
+</li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/encoding_analyzer.html">Encoding Analyzers</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#variants">Variants</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer"><code class="docutils literal notranslate"><span class="pre">EncodingAnalyzer</span></code></a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.compute_encodings"><code class="docutils literal notranslate"><span class="pre">EncodingAnalyzer.compute_encodings()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.reset_stats"><code class="docutils literal notranslate"><span class="pre">EncodingAnalyzer.reset_stats()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.update_stats"><code class="docutils literal notranslate"><span class="pre">EncodingAnalyzer.update_stats()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#variants">Variants</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.MinMaxEncodingAnalyzer"><code class="docutils literal notranslate"><span class="pre">MinMaxEncodingAnalyzer</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.SqnrEncodingAnalyzer"><code class="docutils literal notranslate"><span class="pre">SqnrEncodingAnalyzer</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.PercentileEncodingAnalyzer"><code class="docutils literal notranslate"><span class="pre">PercentileEncodingAnalyzer</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/visualization_tools.html">Visualization Tools</a><ul>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/visualization_tools.html#aimet_torch.v2.visualization_tools.visualize_stats"><code class="docutils literal notranslate"><span class="pre">visualize_stats()</span></code></a></li>
 </ul>
 </li>
-<li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/visualization_tools.html">Visualization Tools</a></li>
 </ul>
 </li>
 </ul>
@@ -403,31 +559,102 @@
 </li>
 <li class="toctree-l3"><a class="reference internal" href="torch_compress.html">PyTorch Model Compression API</a><ul>
 <li class="toctree-l4"><a class="reference internal" href="torch_compress.html#introduction">Introduction</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#top-level-api-for-compression">Top-level API for Compression</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#top-level-api-for-compression">Top-level API for Compression</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.compress.ModelCompressor"><code class="docutils literal notranslate"><span class="pre">ModelCompressor</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.compress.ModelCompressor.compress_model"><code class="docutils literal notranslate"><span class="pre">ModelCompressor.compress_model()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_compress.html#greedy-selection-parameters">Greedy Selection Parameters</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_common.defs.GreedySelectionParameters"><code class="docutils literal notranslate"><span class="pre">GreedySelectionParameters</span></code></a></li>
 </ul>
 </li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#spatial-svd-configuration">Spatial SVD Configuration</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#weight-svd-configuration">Weight SVD Configuration</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#channel-pruning-configuration">Channel Pruning Configuration</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#configuration-definitions">Configuration Definitions</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#spatial-svd-configuration">Spatial SVD Configuration</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.AutoModeParams"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.AutoModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.ManualModeParams"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.ManualModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.Mode"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.Mode.auto"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode.auto</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.Mode.manual"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode.manual</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#weight-svd-configuration">Weight SVD Configuration</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.AutoModeParams"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.AutoModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.ManualModeParams"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.ManualModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.Mode"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.Mode</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.Mode.auto"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.Mode.auto</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.Mode.manual"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.Mode.manual</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#channel-pruning-configuration">Channel Pruning Configuration</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.AutoModeParams"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.AutoModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.ManualModeParams"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.ManualModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.Mode"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.Mode</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.Mode.auto"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.Mode.auto</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.Mode.manual"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.Mode.manual</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#configuration-definitions">Configuration Definitions</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ModuleCompRatioPair"><code class="docutils literal notranslate"><span class="pre">ModuleCompRatioPair</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_compress.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="torch_visualization_compression.html">PyTorch Model Visualization API for Compression</a><ul>
-<li class="toctree-l4"><a class="reference internal" href="torch_visualization_compression.html#top-level-api-compression">Top-level API Compression</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_visualization_compression.html#top-level-api-compression">Top-level API Compression</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_visualization_compression.html#aimet_torch.visualize_serialized_data.VisualizeCompression"><code class="docutils literal notranslate"><span class="pre">VisualizeCompression</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_visualization_compression.html#aimet_torch.visualize_serialized_data.VisualizeCompression.display_eval_scores"><code class="docutils literal notranslate"><span class="pre">VisualizeCompression.display_eval_scores()</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_visualization_compression.html#aimet_torch.visualize_serialized_data.VisualizeCompression.display_comp_ratio_plot"><code class="docutils literal notranslate"><span class="pre">VisualizeCompression.display_comp_ratio_plot()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_visualization_compression.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="torch_visualization_quantization.html">PyTorch Model Visualization API for Quantization</a><ul>
-<li class="toctree-l4"><a class="reference internal" href="torch_visualization_quantization.html#top-level-api-quantization">Top-level API Quantization</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_visualization_quantization.html#top-level-api-quantization">Top-level API Quantization</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_visualization_quantization.html#aimet_torch.visualize_model.visualize_relative_weight_ranges_to_identify_problematic_layers"><code class="docutils literal notranslate"><span class="pre">visualize_relative_weight_ranges_to_identify_problematic_layers()</span></code></a></li>
+<li class="toctree-l5"><a class="reference internal" href="torch_visualization_quantization.html#aimet_torch.visualize_model.visualize_weight_ranges"><code class="docutils literal notranslate"><span class="pre">visualize_weight_ranges()</span></code></a></li>
+<li class="toctree-l5"><a class="reference internal" href="torch_visualization_quantization.html#aimet_torch.visualize_model.visualize_changes_after_optimization"><code class="docutils literal notranslate"><span class="pre">visualize_changes_after_optimization()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_visualization_quantization.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="torch_layer_output_generation.html">PyTorch Debug API</a><ul>
-<li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#top-level-api">Top-level API</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#enum-definition">Enum Definition</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.LayerOutputUtil"><code class="docutils literal notranslate"><span class="pre">LayerOutputUtil</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.LayerOutputUtil.generate_layer_outputs"><code class="docutils literal notranslate"><span class="pre">LayerOutputUtil.generate_layer_outputs()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#enum-definition">Enum Definition</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.NamingScheme"><code class="docutils literal notranslate"><span class="pre">NamingScheme</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.NamingScheme.ONNX"><code class="docutils literal notranslate"><span class="pre">NamingScheme.ONNX</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.NamingScheme.PYTORCH"><code class="docutils literal notranslate"><span class="pre">NamingScheme.PYTORCH</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.NamingScheme.TORCHSCRIPT"><code class="docutils literal notranslate"><span class="pre">NamingScheme.TORCHSCRIPT</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#code-example">Code Example</a></li>
 </ul>
 </li>
@@ -437,27 +664,49 @@
 <li class="toctree-l3"><a class="reference internal" href="keras_quantization.html">TensorFlow Model Quantization API</a><ul>
 <li class="toctree-l4"><a class="reference internal" href="keras_model_guidelines.html"> Model Guidelines</a></li>
 <li class="toctree-l4"><a class="reference internal" href="keras_model_preparer.html"> Model Preparer API</a><ul>
-<li class="toctree-l5"><a class="reference internal" href="keras_model_preparer.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_model_preparer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_model_preparer.html#aimet_tensorflow.keras.model_preparer.prepare_model"><code class="docutils literal notranslate"><span class="pre">prepare_model()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_model_preparer.html#code-examples">Code Examples</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_model_preparer.html#limitations">Limitations</a></li>
 </ul>
 </li>
 <li class="toctree-l4"><a class="reference internal" href="keras_quant_analyzer.html"> Quant Analyzer API</a><ul>
-<li class="toctree-l5"><a class="reference internal" href="keras_quant_analyzer.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_quant_analyzer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_quant_analyzer.html#aimet_tensorflow.keras.quant_analyzer.QuantAnalyzer"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="keras_quant_analyzer.html#aimet_tensorflow.keras.quant_analyzer.QuantAnalyzer.analyze"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.analyze()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_quant_analyzer.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l4"><a class="reference internal" href="keras_quantsim.html"> Quantization Simulation API</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="keras_quantsim.html#user-guide-link">User Guide Link</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_quantsim.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_quantsim.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_quantsim.html#aimet_tensorflow.keras.quantsim.QuantizationSimModel"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="keras_quantsim.html#aimet_tensorflow.keras.quantsim.QuantizationSimModel.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel.compute_encodings()</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="keras_quantsim.html#aimet_tensorflow.keras.quantsim.QuantizationSimModel.export"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel.export()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_quantsim.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l4"><a class="reference internal" href="keras_adaround.html"> Adaptive Rounding API</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#examples-notebook-link">Examples Notebook Link</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#top-level-api">Top-level API</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#adaround-parameters">Adaround Parameters</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_adaround.html#aimet_tensorflow.keras.adaround_weight.Adaround.apply_adaround"><code class="docutils literal notranslate"><span class="pre">apply_adaround()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#adaround-parameters">Adaround Parameters</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_adaround.html#aimet_tensorflow.keras.adaround_weight.AdaroundParameters"><code class="docutils literal notranslate"><span class="pre">AdaroundParameters</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#enum-definition">Enum Definition</a><ul>
 <li class="toctree-l6"><a class="reference internal" href="keras_adaround.html#aimet_common.defs.QuantScheme"><code class="docutils literal notranslate"><span class="pre">QuantScheme</span></code></a><ul>
 <li class="toctree-l7"><a class="reference internal" href="keras_adaround.html#aimet_common.defs.QuantScheme.post_training_percentile"><code class="docutils literal notranslate"><span class="pre">QuantScheme.post_training_percentile</span></code></a></li>
@@ -476,15 +725,34 @@
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#introduction">Introduction</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#cross-layer-equalization-api">Cross Layer Equalization API</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#cross-layer-equalization-api">Cross Layer Equalization API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_cross_layer_equalization.html#aimet_tensorflow.keras.cross_layer_equalization.equalize_model"><code class="docutils literal notranslate"><span class="pre">equalize_model()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#code-example">Code Example</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#primitive-apis">Primitive APIs</a><ul>
 <li class="toctree-l6"><a class="reference internal" href="keras_primitive_apis_cle.html">Primitive APIs for Cross Layer Equalization</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#introduction">Introduction</a></li>
-<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#higher-level-apis-for-cross-layer-equalization">Higher Level APIs for Cross Layer Equalization</a></li>
+<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#higher-level-apis-for-cross-layer-equalization">Higher Level APIs for Cross Layer Equalization</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.batch_norm_fold.fold_all_batch_norms"><code class="docutils literal notranslate"><span class="pre">fold_all_batch_norms()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.CrossLayerScaling.scale_model"><code class="docutils literal notranslate"><span class="pre">scale_model()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.HighBiasFold.bias_fold"><code class="docutils literal notranslate"><span class="pre">bias_fold()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#code-examples-for-higher-level-apis">Code Examples for Higher Level APIs</a></li>
-<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#lower-level-apis-for-cross-layer-equalization">Lower Level APIs for Cross Layer Equalization</a></li>
-<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#custom-datatype-used">Custom Datatype used</a></li>
+<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#lower-level-apis-for-cross-layer-equalization">Lower Level APIs for Cross Layer Equalization</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.batch_norm_fold.fold_given_batch_norms"><code class="docutils literal notranslate"><span class="pre">fold_given_batch_norms()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.CrossLayerScaling.scale_cls_sets"><code class="docutils literal notranslate"><span class="pre">scale_cls_sets()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#id0"><code class="docutils literal notranslate"><span class="pre">bias_fold()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#custom-datatype-used">Custom Datatype used</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.ClsSetInfo"><code class="docutils literal notranslate"><span class="pre">ClsSetInfo</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.ClsSetInfo.ClsSetLayerPairInfo"><code class="docutils literal notranslate"><span class="pre">ClsSetInfo.ClsSetLayerPairInfo</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#code-example-for-lower-level-apis">Code Example for Lower level APIs</a></li>
 <li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#example-helper-methods-to-perform-cle-in-manual-mode">Example helper methods to perform CLE in manual mode</a></li>
 </ul>
@@ -496,7 +764,11 @@
 <li class="toctree-l4"><a class="reference internal" href="keras_batchnorm_re_estimation.html"> BN Re-estimation APIs</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#introduction">Introduction</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#top-level-apis">Top-level APIs</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#top-level-apis">Top-level APIs</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_batchnorm_re_estimation.html#aimet_tensorflow.keras.bn_reestimation.reestimate_bn_stats"><code class="docutils literal notranslate"><span class="pre">reestimate_bn_stats()</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="keras_batchnorm_re_estimation.html#aimet_tensorflow.keras.batch_norm_fold.fold_all_batch_norms_to_scale"><code class="docutils literal notranslate"><span class="pre">fold_all_batch_norms_to_scale()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#code-example">Code Example</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#limitations">Limitations</a></li>
 </ul>
@@ -504,15 +776,39 @@
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="keras_layer_output_generation.html">TensorFlow Debug API</a><ul>
-<li class="toctree-l4"><a class="reference internal" href="keras_layer_output_generation.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l4"><a class="reference internal" href="keras_layer_output_generation.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="keras_layer_output_generation.html#aimet_tensorflow.keras.layer_output_utils.LayerOutputUtil"><code class="docutils literal notranslate"><span class="pre">LayerOutputUtil</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_layer_output_generation.html#aimet_tensorflow.keras.layer_output_utils.LayerOutputUtil.generate_layer_outputs"><code class="docutils literal notranslate"><span class="pre">LayerOutputUtil.generate_layer_outputs()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="keras_layer_output_generation.html#code-example">Code Example</a></li>
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="keras_compression.html">TensorFlow Model Compression API</a><ul>
 <li class="toctree-l4"><a class="reference internal" href="keras_compression.html#introduction">Introduction</a></li>
-<li class="toctree-l4"><a class="reference internal" href="keras_compression.html#top-level-api-for-compression">Top-level API for Compression</a></li>
+<li class="toctree-l4"><a class="reference internal" href="keras_compression.html#top-level-api-for-compression">Top-level API for Compression</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.compress.ModelCompressor"><code class="docutils literal notranslate"><span class="pre">ModelCompressor</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.compress.ModelCompressor.compress_model"><code class="docutils literal notranslate"><span class="pre">ModelCompressor.compress_model()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="keras_compression.html#greedy-selection-parameters">Greedy Selection Parameters</a></li>
-<li class="toctree-l4"><a class="reference internal" href="keras_compression.html#spatial-svd-configuration">Spatial SVD Configuration</a></li>
+<li class="toctree-l4"><a class="reference internal" href="keras_compression.html#spatial-svd-configuration">Spatial SVD Configuration</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.AutoModeParams"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.AutoModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.ManualModeParams"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.ManualModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.Mode"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.Mode.auto"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode.auto</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.Mode.manual"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode.manual</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="keras_compression.html#configuration-definitions">Configuration Definitions</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="keras_compression.html#aimet_common.defs.CostMetric"><code class="docutils literal notranslate"><span class="pre">CostMetric</span></code></a><ul>
 <li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_common.defs.CostMetric.mac"><code class="docutils literal notranslate"><span class="pre">CostMetric.mac</span></code></a></li>
@@ -525,6 +821,7 @@
 <li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_common.defs.CompressionScheme.weight_svd"><code class="docutils literal notranslate"><span class="pre">CompressionScheme.weight_svd</span></code></a></li>
 </ul>
 </li>
+<li class="toctree-l5"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.ModuleCompRatioPair"><code class="docutils literal notranslate"><span class="pre">ModuleCompRatioPair</span></code></a></li>
 </ul>
 </li>
 <li class="toctree-l4"><a class="reference internal" href="keras_compression.html#code-examples">Code Examples</a></li>
diff --git a/releases/1.35.1/api_docs/onnx_auto_quant.html b/releases/1.35.1/api_docs/onnx_auto_quant.html
index 04f730a..bdaca5b 100644
--- a/releases/1.35.1/api_docs/onnx_auto_quant.html
+++ b/releases/1.35.1/api_docs/onnx_auto_quant.html
@@ -243,9 +243,15 @@
 <li class="toctree-l4"><a class="reference internal" href="torch_quantization.html#aimet-torch">aimet_torch</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="torch_quantization.html#api-reference">API Reference</a><ul>
 <li class="toctree-l6"><a class="reference internal" href="torch_model_guidelines.html"> Model Guidelines</a></li>
-<li class="toctree-l6"><a class="reference internal" href="torch_architecture_checker.html"> Architecture Checker API</a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_architecture_checker.html"> Architecture Checker API</a><ul>
+<li class="toctree-l7"><a class="reference internal" href="torch_architecture_checker.html#aimet_torch.arch_checker.arch_checker.ArchChecker.check_model_arch"><code class="docutils literal notranslate"><span class="pre">check_model_arch()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l6"><a class="reference internal" href="torch_model_preparer.html"> Model Preparer API</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="torch_model_preparer.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_model_preparer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_model_preparer.html#aimet_torch.model_preparer.prepare_model"><code class="docutils literal notranslate"><span class="pre">prepare_model()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_model_preparer.html#code-examples">Code Examples</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_model_preparer.html#limitations-of-torch-fx-symbolic-trace-api">Limitations of torch.fx symbolic trace API</a></li>
 </ul>
@@ -255,10 +261,23 @@
 <li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.enable_per_layer_mse_loss"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.enable_per_layer_mse_loss()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.analyze"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.analyze()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_common.utils.CallbackFunc"><code class="docutils literal notranslate"><span class="pre">CallbackFunc</span></code></a></li>
 </ul>
 </li>
-<li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#run-specific-utility">Run specific utility</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#run-specific-utility">Run specific utility</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.check_model_sensitivity_to_quantization"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.check_model_sensitivity_to_quantization()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.perform_per_layer_analysis_by_enabling_quant_wrappers"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.perform_per_layer_analysis_by_enabling_quant_wrappers()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.perform_per_layer_analysis_by_disabling_quant_wrappers"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.perform_per_layer_analysis_by_disabling_quant_wrappers()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.export_per_layer_encoding_min_max_range"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.export_per_layer_encoding_min_max_range()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.export_per_layer_stats_histogram"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.export_per_layer_stats_histogram()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.export_per_layer_mse_loss"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.export_per_layer_mse_loss()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
@@ -266,7 +285,16 @@
 <li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#guidelines">Guidelines</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.QuantizationSimModel"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.QuantizationSimModel.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel.compute_encodings()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.QuantizationSimModel.export"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel.export()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.save_checkpoint"><code class="docutils literal notranslate"><span class="pre">quantsim.save_checkpoint()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.load_checkpoint"><code class="docutils literal notranslate"><span class="pre">quantsim.load_checkpoint()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#enum-definition">Enum Definition</a><ul>
 <li class="toctree-l8"><a class="reference internal" href="torch_quantsim.html#aimet_common.defs.QuantScheme"><code class="docutils literal notranslate"><span class="pre">QuantScheme</span></code></a><ul>
 <li class="toctree-l9"><a class="reference internal" href="torch_quantsim.html#aimet_common.defs.QuantScheme.post_training_percentile"><code class="docutils literal notranslate"><span class="pre">QuantScheme.post_training_percentile</span></code></a></li>
@@ -284,8 +312,14 @@
 <li class="toctree-l6"><a class="reference internal" href="torch_adaround.html"> Adaptive Rounding API</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#examples-notebook-link">Examples Notebook Link</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#top-level-api">Top-level API</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#adaround-parameters">Adaround Parameters</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_adaround.html#aimet_torch.v1.adaround.adaround_weight.Adaround.apply_adaround"><code class="docutils literal notranslate"><span class="pre">apply_adaround()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#adaround-parameters">Adaround Parameters</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_adaround.html#aimet_torch.v1.adaround.adaround_weight.AdaroundParameters"><code class="docutils literal notranslate"><span class="pre">AdaroundParameters</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#enum-definition">Enum Definition</a><ul>
 <li class="toctree-l8"><a class="reference internal" href="torch_adaround.html#aimet_common.defs.QuantScheme"><code class="docutils literal notranslate"><span class="pre">QuantScheme</span></code></a><ul>
 <li class="toctree-l9"><a class="reference internal" href="torch_adaround.html#aimet_common.defs.QuantScheme.post_training_percentile"><code class="docutils literal notranslate"><span class="pre">QuantScheme.post_training_percentile</span></code></a></li>
@@ -304,15 +338,31 @@
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#introduction">Introduction</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#cross-layer-equalization-api">Cross Layer Equalization API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#cross-layer-equalization-api">Cross Layer Equalization API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_cross_layer_equalization.html#aimet_torch.cross_layer_equalization.equalize_model"><code class="docutils literal notranslate"><span class="pre">equalize_model()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#code-example">Code Example</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#primitive-apis">Primitive APIs</a><ul>
 <li class="toctree-l8"><a class="reference internal" href="torch_primitive_apis_cle.html">Primitive APIs for Cross Layer Equalization</a><ul>
 <li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#introduction">Introduction</a></li>
-<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#clssetinfo-definition">ClsSetInfo Definition</a></li>
-<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#higher-level-apis-for-cross-layer-equalization">Higher Level APIs for Cross Layer Equalization</a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#clssetinfo-definition">ClsSetInfo Definition</a><ul>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.cross_layer_equalization.ClsSetInfo"><code class="docutils literal notranslate"><span class="pre">ClsSetInfo</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#higher-level-apis-for-cross-layer-equalization">Higher Level APIs for Cross Layer Equalization</a><ul>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.batch_norm_fold.fold_all_batch_norms"><code class="docutils literal notranslate"><span class="pre">fold_all_batch_norms()</span></code></a></li>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.cross_layer_equalization.CrossLayerScaling.scale_model"><code class="docutils literal notranslate"><span class="pre">scale_model()</span></code></a></li>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.cross_layer_equalization.HighBiasFold.bias_fold"><code class="docutils literal notranslate"><span class="pre">bias_fold()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#code-examples-for-higher-level-apis">Code Examples for Higher Level APIs</a></li>
-<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#lower-level-apis-for-cross-layer-equalization">Lower Level APIs for Cross Layer Equalization</a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#lower-level-apis-for-cross-layer-equalization">Lower Level APIs for Cross Layer Equalization</a><ul>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.batch_norm_fold.fold_given_batch_norms"><code class="docutils literal notranslate"><span class="pre">fold_given_batch_norms()</span></code></a></li>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.cross_layer_equalization.CrossLayerScaling.scale_cls_sets"><code class="docutils literal notranslate"><span class="pre">scale_cls_sets()</span></code></a></li>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#id0"><code class="docutils literal notranslate"><span class="pre">bias_fold()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#code-examples-for-lower-level-apis">Code Examples for Lower Level APIs</a></li>
 </ul>
 </li>
@@ -322,7 +372,10 @@
 </li>
 <li class="toctree-l6"><a class="reference internal" href="torch_bias_correction.html"> Bias Correction API</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#user-guide-link">User Guide Link</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#bias-correction-api">Bias Correction API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#bias-correction-api">Bias Correction API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_bias_correction.html#aimet_torch.bias_correction.correct_bias"><code class="docutils literal notranslate"><span class="pre">correct_bias()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#convbninfotype">ConvBnInfoType</a><ul>
 <li class="toctree-l8"><a class="reference internal" href="torch_bias_correction.html#aimet_common.bias_correction.ConvBnInfoType"><code class="docutils literal notranslate"><span class="pre">ConvBnInfoType</span></code></a></li>
 </ul>
@@ -336,7 +389,10 @@
 </li>
 </ul>
 </li>
-<li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#quantization-params">Quantization Params</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#quantization-params">Quantization Params</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_bias_correction.html#aimet_torch.v1.quantsim.QuantParams"><code class="docutils literal notranslate"><span class="pre">QuantParams</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#code-example-1-empirical-bias-correction">Code Example #1 Empirical Bias Correction</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#code-example-2-analytical-empirical-bias-correction">Code Example #2 Analytical + Empirical Bias correction</a></li>
 </ul>
@@ -344,21 +400,46 @@
 <li class="toctree-l6"><a class="reference internal" href="torch_auto_quant.html"> AutoQuant API</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#examples-notebook-link">Examples Notebook Link</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_auto_quant.html#aimet_torch.v1.auto_quant.AutoQuant"><code class="docutils literal notranslate"><span class="pre">AutoQuant</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="torch_batchnorm_re_estimation.html"> BN Re-estimation APIs</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#introduction">Introduction</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#top-level-apis">Top-level APIs</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#top-level-apis">Top-level APIs</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_batchnorm_re_estimation.html#aimet_torch.bn_reestimation.reestimate_bn_stats"><code class="docutils literal notranslate"><span class="pre">reestimate_bn_stats()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_batchnorm_re_estimation.html#aimet_torch.batch_norm_fold.fold_all_batch_norms_to_scale"><code class="docutils literal notranslate"><span class="pre">fold_all_batch_norms_to_scale()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#code-example-bn-reestimation">Code Example - BN-Reestimation</a></li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="torch_multi_gpu.html"> Multi-GPU guidelines</a></li>
 <li class="toctree-l6"><a class="reference internal" href="torch_peft_lora.html"> PEFT LoRA APIs</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_peft_lora.html#user-flow">User flow</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_peft_lora.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_peft_lora.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.AdapterMetaData"><code class="docutils literal notranslate"><span class="pre">AdapterMetaData</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.replace_lora_layers_with_quantizable_layers"><code class="docutils literal notranslate"><span class="pre">peft.replace_lora_layers_with_quantizable_layers()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.track_lora_meta_data"><code class="docutils literal notranslate"><span class="pre">peft.track_lora_meta_data()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.disable_lora_adapters"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.disable_lora_adapters()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.enable_adapter_and_load_weights"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.enable_adapter_and_load_weights()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.export_adapter_weights"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.export_adapter_weights()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.freeze_base_model"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.freeze_base_model()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.freeze_base_model_activation_quantizers"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.freeze_base_model_activation_quantizers()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.freeze_base_model_param_quantizers"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.freeze_base_model_param_quantizers()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.get_fp_lora_layer"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.get_fp_lora_layer()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.get_quantized_lora_layer"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.get_quantized_lora_layer()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.quantize_lora_scale_with_fixed_range"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.quantize_lora_scale_with_fixed_range()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.set_bitwidth_for_lora_adapters"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.set_bitwidth_for_lora_adapters()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 </ul>
 </li>
 </ul>
@@ -370,31 +451,106 @@
 <li class="toctree-l5"><a class="reference internal" href="torch_quantization.html#backwards-compatibility">Backwards Compatibility</a></li>
 <li class="toctree-l5"><a class="reference internal" href="torch_quantization.html#id1">API Reference</a><ul>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/quantized_modules.html">Quantized Modules</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.input_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.input_quantizers</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.output_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.output_quantizers</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.param_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.param_quantizers</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.__quant_init__"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.__quant_init__()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.compute_encodings()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.forward"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.forward()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#configuration">Configuration</a></li>
 <li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#computing-encodings">Computing Encodings</a></li>
 <li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#quantized-module-classes">Quantized Module Classes</a></li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/quantizer.html">Quantizers</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantizer.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantizer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase"><code class="docutils literal notranslate"><span class="pre">QuantizerBase</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.allow_overwrite"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.allow_overwrite()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.compute_encodings()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.get_encoding"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.get_encoding()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.get_legacy_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.get_legacy_encodings()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.is_initialized"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.is_initialized()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.register_quantization_parameter"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.register_quantization_parameter()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.set_legacy_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.set_legacy_encodings()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizeDequantize"><code class="docutils literal notranslate"><span class="pre">QuantizeDequantize</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizeDequantize.forward"><code class="docutils literal notranslate"><span class="pre">QuantizeDequantize.forward()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.Quantize"><code class="docutils literal notranslate"><span class="pre">Quantize</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.Quantize.forward"><code class="docutils literal notranslate"><span class="pre">Quantize.forward()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html">QuantizationMixin</a><ul>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin</span></code></a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.input_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.input_quantizers</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.output_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.output_quantizers</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.param_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.param_quantizers</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.forward"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.forward()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.__quant_init__"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.__quant_init__()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.set_kernel"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.set_kernel()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.set_default_kernel"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.set_default_kernel()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.compute_encodings()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.from_module"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.from_module()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.get_default_kernel"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.get_default_kernel()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.get_kernel"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.get_kernel()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.implements"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.implements()</span></code></a></li>
+</ul>
+</li>
 </ul>
 </li>
-<li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html">QuantizationMixin</a></li>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html">quantization.affine</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#classes">Classes</a></li>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#functions">Functions</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#classes">Classes</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.Quantize"><code class="docutils literal notranslate"><span class="pre">Quantize</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.QuantizeDequantize"><code class="docutils literal notranslate"><span class="pre">QuantizeDequantize</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#functions">Functions</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.quantize"><code class="docutils literal notranslate"><span class="pre">quantize()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.quantize_dequantize"><code class="docutils literal notranslate"><span class="pre">quantize_dequantize()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.dequantize"><code class="docutils literal notranslate"><span class="pre">dequantize()</span></code></a></li>
+</ul>
+</li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html">quantization.float</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html#classes">Classes</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html#classes">Classes</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html#aimet_torch.v2.quantization.float.FloatQuantizeDequantize"><code class="docutils literal notranslate"><span class="pre">FloatQuantizeDequantize</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html#aimet_torch.v2.quantization.float.QuantizeDequantize"><code class="docutils literal notranslate"><span class="pre">QuantizeDequantize</span></code></a></li>
+</ul>
+</li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/encoding_analyzer.html">Encoding Analyzers</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#variants">Variants</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer"><code class="docutils literal notranslate"><span class="pre">EncodingAnalyzer</span></code></a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.compute_encodings"><code class="docutils literal notranslate"><span class="pre">EncodingAnalyzer.compute_encodings()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.reset_stats"><code class="docutils literal notranslate"><span class="pre">EncodingAnalyzer.reset_stats()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.update_stats"><code class="docutils literal notranslate"><span class="pre">EncodingAnalyzer.update_stats()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#variants">Variants</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.MinMaxEncodingAnalyzer"><code class="docutils literal notranslate"><span class="pre">MinMaxEncodingAnalyzer</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.SqnrEncodingAnalyzer"><code class="docutils literal notranslate"><span class="pre">SqnrEncodingAnalyzer</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.PercentileEncodingAnalyzer"><code class="docutils literal notranslate"><span class="pre">PercentileEncodingAnalyzer</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/visualization_tools.html">Visualization Tools</a><ul>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/visualization_tools.html#aimet_torch.v2.visualization_tools.visualize_stats"><code class="docutils literal notranslate"><span class="pre">visualize_stats()</span></code></a></li>
 </ul>
 </li>
-<li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/visualization_tools.html">Visualization Tools</a></li>
 </ul>
 </li>
 </ul>
@@ -403,31 +559,102 @@
 </li>
 <li class="toctree-l3"><a class="reference internal" href="torch_compress.html">PyTorch Model Compression API</a><ul>
 <li class="toctree-l4"><a class="reference internal" href="torch_compress.html#introduction">Introduction</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#top-level-api-for-compression">Top-level API for Compression</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#top-level-api-for-compression">Top-level API for Compression</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.compress.ModelCompressor"><code class="docutils literal notranslate"><span class="pre">ModelCompressor</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.compress.ModelCompressor.compress_model"><code class="docutils literal notranslate"><span class="pre">ModelCompressor.compress_model()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_compress.html#greedy-selection-parameters">Greedy Selection Parameters</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_common.defs.GreedySelectionParameters"><code class="docutils literal notranslate"><span class="pre">GreedySelectionParameters</span></code></a></li>
 </ul>
 </li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#spatial-svd-configuration">Spatial SVD Configuration</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#weight-svd-configuration">Weight SVD Configuration</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#channel-pruning-configuration">Channel Pruning Configuration</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#configuration-definitions">Configuration Definitions</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#spatial-svd-configuration">Spatial SVD Configuration</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.AutoModeParams"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.AutoModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.ManualModeParams"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.ManualModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.Mode"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.Mode.auto"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode.auto</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.Mode.manual"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode.manual</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#weight-svd-configuration">Weight SVD Configuration</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.AutoModeParams"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.AutoModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.ManualModeParams"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.ManualModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.Mode"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.Mode</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.Mode.auto"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.Mode.auto</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.Mode.manual"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.Mode.manual</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#channel-pruning-configuration">Channel Pruning Configuration</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.AutoModeParams"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.AutoModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.ManualModeParams"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.ManualModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.Mode"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.Mode</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.Mode.auto"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.Mode.auto</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.Mode.manual"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.Mode.manual</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#configuration-definitions">Configuration Definitions</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ModuleCompRatioPair"><code class="docutils literal notranslate"><span class="pre">ModuleCompRatioPair</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_compress.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="torch_visualization_compression.html">PyTorch Model Visualization API for Compression</a><ul>
-<li class="toctree-l4"><a class="reference internal" href="torch_visualization_compression.html#top-level-api-compression">Top-level API Compression</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_visualization_compression.html#top-level-api-compression">Top-level API Compression</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_visualization_compression.html#aimet_torch.visualize_serialized_data.VisualizeCompression"><code class="docutils literal notranslate"><span class="pre">VisualizeCompression</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_visualization_compression.html#aimet_torch.visualize_serialized_data.VisualizeCompression.display_eval_scores"><code class="docutils literal notranslate"><span class="pre">VisualizeCompression.display_eval_scores()</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_visualization_compression.html#aimet_torch.visualize_serialized_data.VisualizeCompression.display_comp_ratio_plot"><code class="docutils literal notranslate"><span class="pre">VisualizeCompression.display_comp_ratio_plot()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_visualization_compression.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="torch_visualization_quantization.html">PyTorch Model Visualization API for Quantization</a><ul>
-<li class="toctree-l4"><a class="reference internal" href="torch_visualization_quantization.html#top-level-api-quantization">Top-level API Quantization</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_visualization_quantization.html#top-level-api-quantization">Top-level API Quantization</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_visualization_quantization.html#aimet_torch.visualize_model.visualize_relative_weight_ranges_to_identify_problematic_layers"><code class="docutils literal notranslate"><span class="pre">visualize_relative_weight_ranges_to_identify_problematic_layers()</span></code></a></li>
+<li class="toctree-l5"><a class="reference internal" href="torch_visualization_quantization.html#aimet_torch.visualize_model.visualize_weight_ranges"><code class="docutils literal notranslate"><span class="pre">visualize_weight_ranges()</span></code></a></li>
+<li class="toctree-l5"><a class="reference internal" href="torch_visualization_quantization.html#aimet_torch.visualize_model.visualize_changes_after_optimization"><code class="docutils literal notranslate"><span class="pre">visualize_changes_after_optimization()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_visualization_quantization.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="torch_layer_output_generation.html">PyTorch Debug API</a><ul>
-<li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#top-level-api">Top-level API</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#enum-definition">Enum Definition</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.LayerOutputUtil"><code class="docutils literal notranslate"><span class="pre">LayerOutputUtil</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.LayerOutputUtil.generate_layer_outputs"><code class="docutils literal notranslate"><span class="pre">LayerOutputUtil.generate_layer_outputs()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#enum-definition">Enum Definition</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.NamingScheme"><code class="docutils literal notranslate"><span class="pre">NamingScheme</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.NamingScheme.ONNX"><code class="docutils literal notranslate"><span class="pre">NamingScheme.ONNX</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.NamingScheme.PYTORCH"><code class="docutils literal notranslate"><span class="pre">NamingScheme.PYTORCH</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.NamingScheme.TORCHSCRIPT"><code class="docutils literal notranslate"><span class="pre">NamingScheme.TORCHSCRIPT</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#code-example">Code Example</a></li>
 </ul>
 </li>
@@ -437,27 +664,49 @@
 <li class="toctree-l3"><a class="reference internal" href="keras_quantization.html">TensorFlow Model Quantization API</a><ul>
 <li class="toctree-l4"><a class="reference internal" href="keras_model_guidelines.html"> Model Guidelines</a></li>
 <li class="toctree-l4"><a class="reference internal" href="keras_model_preparer.html"> Model Preparer API</a><ul>
-<li class="toctree-l5"><a class="reference internal" href="keras_model_preparer.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_model_preparer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_model_preparer.html#aimet_tensorflow.keras.model_preparer.prepare_model"><code class="docutils literal notranslate"><span class="pre">prepare_model()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_model_preparer.html#code-examples">Code Examples</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_model_preparer.html#limitations">Limitations</a></li>
 </ul>
 </li>
 <li class="toctree-l4"><a class="reference internal" href="keras_quant_analyzer.html"> Quant Analyzer API</a><ul>
-<li class="toctree-l5"><a class="reference internal" href="keras_quant_analyzer.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_quant_analyzer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_quant_analyzer.html#aimet_tensorflow.keras.quant_analyzer.QuantAnalyzer"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="keras_quant_analyzer.html#aimet_tensorflow.keras.quant_analyzer.QuantAnalyzer.analyze"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.analyze()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_quant_analyzer.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l4"><a class="reference internal" href="keras_quantsim.html"> Quantization Simulation API</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="keras_quantsim.html#user-guide-link">User Guide Link</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_quantsim.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_quantsim.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_quantsim.html#aimet_tensorflow.keras.quantsim.QuantizationSimModel"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="keras_quantsim.html#aimet_tensorflow.keras.quantsim.QuantizationSimModel.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel.compute_encodings()</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="keras_quantsim.html#aimet_tensorflow.keras.quantsim.QuantizationSimModel.export"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel.export()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_quantsim.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l4"><a class="reference internal" href="keras_adaround.html"> Adaptive Rounding API</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#examples-notebook-link">Examples Notebook Link</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#top-level-api">Top-level API</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#adaround-parameters">Adaround Parameters</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_adaround.html#aimet_tensorflow.keras.adaround_weight.Adaround.apply_adaround"><code class="docutils literal notranslate"><span class="pre">apply_adaround()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#adaround-parameters">Adaround Parameters</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_adaround.html#aimet_tensorflow.keras.adaround_weight.AdaroundParameters"><code class="docutils literal notranslate"><span class="pre">AdaroundParameters</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#enum-definition">Enum Definition</a><ul>
 <li class="toctree-l6"><a class="reference internal" href="keras_adaround.html#aimet_common.defs.QuantScheme"><code class="docutils literal notranslate"><span class="pre">QuantScheme</span></code></a><ul>
 <li class="toctree-l7"><a class="reference internal" href="keras_adaround.html#aimet_common.defs.QuantScheme.post_training_percentile"><code class="docutils literal notranslate"><span class="pre">QuantScheme.post_training_percentile</span></code></a></li>
@@ -476,15 +725,34 @@
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#introduction">Introduction</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#cross-layer-equalization-api">Cross Layer Equalization API</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#cross-layer-equalization-api">Cross Layer Equalization API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_cross_layer_equalization.html#aimet_tensorflow.keras.cross_layer_equalization.equalize_model"><code class="docutils literal notranslate"><span class="pre">equalize_model()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#code-example">Code Example</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#primitive-apis">Primitive APIs</a><ul>
 <li class="toctree-l6"><a class="reference internal" href="keras_primitive_apis_cle.html">Primitive APIs for Cross Layer Equalization</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#introduction">Introduction</a></li>
-<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#higher-level-apis-for-cross-layer-equalization">Higher Level APIs for Cross Layer Equalization</a></li>
+<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#higher-level-apis-for-cross-layer-equalization">Higher Level APIs for Cross Layer Equalization</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.batch_norm_fold.fold_all_batch_norms"><code class="docutils literal notranslate"><span class="pre">fold_all_batch_norms()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.CrossLayerScaling.scale_model"><code class="docutils literal notranslate"><span class="pre">scale_model()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.HighBiasFold.bias_fold"><code class="docutils literal notranslate"><span class="pre">bias_fold()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#code-examples-for-higher-level-apis">Code Examples for Higher Level APIs</a></li>
-<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#lower-level-apis-for-cross-layer-equalization">Lower Level APIs for Cross Layer Equalization</a></li>
-<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#custom-datatype-used">Custom Datatype used</a></li>
+<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#lower-level-apis-for-cross-layer-equalization">Lower Level APIs for Cross Layer Equalization</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.batch_norm_fold.fold_given_batch_norms"><code class="docutils literal notranslate"><span class="pre">fold_given_batch_norms()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.CrossLayerScaling.scale_cls_sets"><code class="docutils literal notranslate"><span class="pre">scale_cls_sets()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#id0"><code class="docutils literal notranslate"><span class="pre">bias_fold()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#custom-datatype-used">Custom Datatype used</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.ClsSetInfo"><code class="docutils literal notranslate"><span class="pre">ClsSetInfo</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.ClsSetInfo.ClsSetLayerPairInfo"><code class="docutils literal notranslate"><span class="pre">ClsSetInfo.ClsSetLayerPairInfo</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#code-example-for-lower-level-apis">Code Example for Lower level APIs</a></li>
 <li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#example-helper-methods-to-perform-cle-in-manual-mode">Example helper methods to perform CLE in manual mode</a></li>
 </ul>
@@ -496,7 +764,11 @@
 <li class="toctree-l4"><a class="reference internal" href="keras_batchnorm_re_estimation.html"> BN Re-estimation APIs</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#introduction">Introduction</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#top-level-apis">Top-level APIs</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#top-level-apis">Top-level APIs</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_batchnorm_re_estimation.html#aimet_tensorflow.keras.bn_reestimation.reestimate_bn_stats"><code class="docutils literal notranslate"><span class="pre">reestimate_bn_stats()</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="keras_batchnorm_re_estimation.html#aimet_tensorflow.keras.batch_norm_fold.fold_all_batch_norms_to_scale"><code class="docutils literal notranslate"><span class="pre">fold_all_batch_norms_to_scale()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#code-example">Code Example</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#limitations">Limitations</a></li>
 </ul>
@@ -504,15 +776,39 @@
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="keras_layer_output_generation.html">TensorFlow Debug API</a><ul>
-<li class="toctree-l4"><a class="reference internal" href="keras_layer_output_generation.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l4"><a class="reference internal" href="keras_layer_output_generation.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="keras_layer_output_generation.html#aimet_tensorflow.keras.layer_output_utils.LayerOutputUtil"><code class="docutils literal notranslate"><span class="pre">LayerOutputUtil</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_layer_output_generation.html#aimet_tensorflow.keras.layer_output_utils.LayerOutputUtil.generate_layer_outputs"><code class="docutils literal notranslate"><span class="pre">LayerOutputUtil.generate_layer_outputs()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="keras_layer_output_generation.html#code-example">Code Example</a></li>
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="keras_compression.html">TensorFlow Model Compression API</a><ul>
 <li class="toctree-l4"><a class="reference internal" href="keras_compression.html#introduction">Introduction</a></li>
-<li class="toctree-l4"><a class="reference internal" href="keras_compression.html#top-level-api-for-compression">Top-level API for Compression</a></li>
+<li class="toctree-l4"><a class="reference internal" href="keras_compression.html#top-level-api-for-compression">Top-level API for Compression</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.compress.ModelCompressor"><code class="docutils literal notranslate"><span class="pre">ModelCompressor</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.compress.ModelCompressor.compress_model"><code class="docutils literal notranslate"><span class="pre">ModelCompressor.compress_model()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="keras_compression.html#greedy-selection-parameters">Greedy Selection Parameters</a></li>
-<li class="toctree-l4"><a class="reference internal" href="keras_compression.html#spatial-svd-configuration">Spatial SVD Configuration</a></li>
+<li class="toctree-l4"><a class="reference internal" href="keras_compression.html#spatial-svd-configuration">Spatial SVD Configuration</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.AutoModeParams"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.AutoModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.ManualModeParams"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.ManualModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.Mode"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.Mode.auto"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode.auto</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.Mode.manual"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode.manual</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="keras_compression.html#configuration-definitions">Configuration Definitions</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="keras_compression.html#aimet_common.defs.CostMetric"><code class="docutils literal notranslate"><span class="pre">CostMetric</span></code></a><ul>
 <li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_common.defs.CostMetric.mac"><code class="docutils literal notranslate"><span class="pre">CostMetric.mac</span></code></a></li>
@@ -525,6 +821,7 @@
 <li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_common.defs.CompressionScheme.weight_svd"><code class="docutils literal notranslate"><span class="pre">CompressionScheme.weight_svd</span></code></a></li>
 </ul>
 </li>
+<li class="toctree-l5"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.ModuleCompRatioPair"><code class="docutils literal notranslate"><span class="pre">ModuleCompRatioPair</span></code></a></li>
 </ul>
 </li>
 <li class="toctree-l4"><a class="reference internal" href="keras_compression.html#code-examples">Code Examples</a></li>
diff --git a/releases/1.35.1/api_docs/onnx_cross_layer_equalization.html b/releases/1.35.1/api_docs/onnx_cross_layer_equalization.html
index 7612751..9a091b4 100644
--- a/releases/1.35.1/api_docs/onnx_cross_layer_equalization.html
+++ b/releases/1.35.1/api_docs/onnx_cross_layer_equalization.html
@@ -243,9 +243,15 @@
 <li class="toctree-l4"><a class="reference internal" href="torch_quantization.html#aimet-torch">aimet_torch</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="torch_quantization.html#api-reference">API Reference</a><ul>
 <li class="toctree-l6"><a class="reference internal" href="torch_model_guidelines.html"> Model Guidelines</a></li>
-<li class="toctree-l6"><a class="reference internal" href="torch_architecture_checker.html"> Architecture Checker API</a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_architecture_checker.html"> Architecture Checker API</a><ul>
+<li class="toctree-l7"><a class="reference internal" href="torch_architecture_checker.html#aimet_torch.arch_checker.arch_checker.ArchChecker.check_model_arch"><code class="docutils literal notranslate"><span class="pre">check_model_arch()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l6"><a class="reference internal" href="torch_model_preparer.html"> Model Preparer API</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="torch_model_preparer.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_model_preparer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_model_preparer.html#aimet_torch.model_preparer.prepare_model"><code class="docutils literal notranslate"><span class="pre">prepare_model()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_model_preparer.html#code-examples">Code Examples</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_model_preparer.html#limitations-of-torch-fx-symbolic-trace-api">Limitations of torch.fx symbolic trace API</a></li>
 </ul>
@@ -255,10 +261,23 @@
 <li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.enable_per_layer_mse_loss"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.enable_per_layer_mse_loss()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.analyze"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.analyze()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_common.utils.CallbackFunc"><code class="docutils literal notranslate"><span class="pre">CallbackFunc</span></code></a></li>
 </ul>
 </li>
-<li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#run-specific-utility">Run specific utility</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#run-specific-utility">Run specific utility</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.check_model_sensitivity_to_quantization"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.check_model_sensitivity_to_quantization()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.perform_per_layer_analysis_by_enabling_quant_wrappers"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.perform_per_layer_analysis_by_enabling_quant_wrappers()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.perform_per_layer_analysis_by_disabling_quant_wrappers"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.perform_per_layer_analysis_by_disabling_quant_wrappers()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.export_per_layer_encoding_min_max_range"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.export_per_layer_encoding_min_max_range()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.export_per_layer_stats_histogram"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.export_per_layer_stats_histogram()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.export_per_layer_mse_loss"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.export_per_layer_mse_loss()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
@@ -266,7 +285,16 @@
 <li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#guidelines">Guidelines</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.QuantizationSimModel"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.QuantizationSimModel.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel.compute_encodings()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.QuantizationSimModel.export"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel.export()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.save_checkpoint"><code class="docutils literal notranslate"><span class="pre">quantsim.save_checkpoint()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.load_checkpoint"><code class="docutils literal notranslate"><span class="pre">quantsim.load_checkpoint()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#enum-definition">Enum Definition</a><ul>
 <li class="toctree-l8"><a class="reference internal" href="torch_quantsim.html#aimet_common.defs.QuantScheme"><code class="docutils literal notranslate"><span class="pre">QuantScheme</span></code></a><ul>
 <li class="toctree-l9"><a class="reference internal" href="torch_quantsim.html#aimet_common.defs.QuantScheme.post_training_percentile"><code class="docutils literal notranslate"><span class="pre">QuantScheme.post_training_percentile</span></code></a></li>
@@ -284,8 +312,14 @@
 <li class="toctree-l6"><a class="reference internal" href="torch_adaround.html"> Adaptive Rounding API</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#examples-notebook-link">Examples Notebook Link</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#top-level-api">Top-level API</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#adaround-parameters">Adaround Parameters</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_adaround.html#aimet_torch.v1.adaround.adaround_weight.Adaround.apply_adaround"><code class="docutils literal notranslate"><span class="pre">apply_adaround()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#adaround-parameters">Adaround Parameters</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_adaround.html#aimet_torch.v1.adaround.adaround_weight.AdaroundParameters"><code class="docutils literal notranslate"><span class="pre">AdaroundParameters</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#enum-definition">Enum Definition</a><ul>
 <li class="toctree-l8"><a class="reference internal" href="torch_adaround.html#aimet_common.defs.QuantScheme"><code class="docutils literal notranslate"><span class="pre">QuantScheme</span></code></a><ul>
 <li class="toctree-l9"><a class="reference internal" href="torch_adaround.html#aimet_common.defs.QuantScheme.post_training_percentile"><code class="docutils literal notranslate"><span class="pre">QuantScheme.post_training_percentile</span></code></a></li>
@@ -304,15 +338,31 @@
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#introduction">Introduction</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#cross-layer-equalization-api">Cross Layer Equalization API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#cross-layer-equalization-api">Cross Layer Equalization API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_cross_layer_equalization.html#aimet_torch.cross_layer_equalization.equalize_model"><code class="docutils literal notranslate"><span class="pre">equalize_model()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#code-example">Code Example</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#primitive-apis">Primitive APIs</a><ul>
 <li class="toctree-l8"><a class="reference internal" href="torch_primitive_apis_cle.html">Primitive APIs for Cross Layer Equalization</a><ul>
 <li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#introduction">Introduction</a></li>
-<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#clssetinfo-definition">ClsSetInfo Definition</a></li>
-<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#higher-level-apis-for-cross-layer-equalization">Higher Level APIs for Cross Layer Equalization</a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#clssetinfo-definition">ClsSetInfo Definition</a><ul>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.cross_layer_equalization.ClsSetInfo"><code class="docutils literal notranslate"><span class="pre">ClsSetInfo</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#higher-level-apis-for-cross-layer-equalization">Higher Level APIs for Cross Layer Equalization</a><ul>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.batch_norm_fold.fold_all_batch_norms"><code class="docutils literal notranslate"><span class="pre">fold_all_batch_norms()</span></code></a></li>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.cross_layer_equalization.CrossLayerScaling.scale_model"><code class="docutils literal notranslate"><span class="pre">scale_model()</span></code></a></li>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.cross_layer_equalization.HighBiasFold.bias_fold"><code class="docutils literal notranslate"><span class="pre">bias_fold()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#code-examples-for-higher-level-apis">Code Examples for Higher Level APIs</a></li>
-<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#lower-level-apis-for-cross-layer-equalization">Lower Level APIs for Cross Layer Equalization</a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#lower-level-apis-for-cross-layer-equalization">Lower Level APIs for Cross Layer Equalization</a><ul>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.batch_norm_fold.fold_given_batch_norms"><code class="docutils literal notranslate"><span class="pre">fold_given_batch_norms()</span></code></a></li>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.cross_layer_equalization.CrossLayerScaling.scale_cls_sets"><code class="docutils literal notranslate"><span class="pre">scale_cls_sets()</span></code></a></li>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#id0"><code class="docutils literal notranslate"><span class="pre">bias_fold()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#code-examples-for-lower-level-apis">Code Examples for Lower Level APIs</a></li>
 </ul>
 </li>
@@ -322,7 +372,10 @@
 </li>
 <li class="toctree-l6"><a class="reference internal" href="torch_bias_correction.html"> Bias Correction API</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#user-guide-link">User Guide Link</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#bias-correction-api">Bias Correction API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#bias-correction-api">Bias Correction API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_bias_correction.html#aimet_torch.bias_correction.correct_bias"><code class="docutils literal notranslate"><span class="pre">correct_bias()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#convbninfotype">ConvBnInfoType</a><ul>
 <li class="toctree-l8"><a class="reference internal" href="torch_bias_correction.html#aimet_common.bias_correction.ConvBnInfoType"><code class="docutils literal notranslate"><span class="pre">ConvBnInfoType</span></code></a></li>
 </ul>
@@ -336,7 +389,10 @@
 </li>
 </ul>
 </li>
-<li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#quantization-params">Quantization Params</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#quantization-params">Quantization Params</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_bias_correction.html#aimet_torch.v1.quantsim.QuantParams"><code class="docutils literal notranslate"><span class="pre">QuantParams</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#code-example-1-empirical-bias-correction">Code Example #1 Empirical Bias Correction</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#code-example-2-analytical-empirical-bias-correction">Code Example #2 Analytical + Empirical Bias correction</a></li>
 </ul>
@@ -344,21 +400,46 @@
 <li class="toctree-l6"><a class="reference internal" href="torch_auto_quant.html"> AutoQuant API</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#examples-notebook-link">Examples Notebook Link</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_auto_quant.html#aimet_torch.v1.auto_quant.AutoQuant"><code class="docutils literal notranslate"><span class="pre">AutoQuant</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="torch_batchnorm_re_estimation.html"> BN Re-estimation APIs</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#introduction">Introduction</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#top-level-apis">Top-level APIs</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#top-level-apis">Top-level APIs</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_batchnorm_re_estimation.html#aimet_torch.bn_reestimation.reestimate_bn_stats"><code class="docutils literal notranslate"><span class="pre">reestimate_bn_stats()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_batchnorm_re_estimation.html#aimet_torch.batch_norm_fold.fold_all_batch_norms_to_scale"><code class="docutils literal notranslate"><span class="pre">fold_all_batch_norms_to_scale()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#code-example-bn-reestimation">Code Example - BN-Reestimation</a></li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="torch_multi_gpu.html"> Multi-GPU guidelines</a></li>
 <li class="toctree-l6"><a class="reference internal" href="torch_peft_lora.html"> PEFT LoRA APIs</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_peft_lora.html#user-flow">User flow</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_peft_lora.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_peft_lora.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.AdapterMetaData"><code class="docutils literal notranslate"><span class="pre">AdapterMetaData</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.replace_lora_layers_with_quantizable_layers"><code class="docutils literal notranslate"><span class="pre">peft.replace_lora_layers_with_quantizable_layers()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.track_lora_meta_data"><code class="docutils literal notranslate"><span class="pre">peft.track_lora_meta_data()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.disable_lora_adapters"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.disable_lora_adapters()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.enable_adapter_and_load_weights"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.enable_adapter_and_load_weights()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.export_adapter_weights"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.export_adapter_weights()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.freeze_base_model"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.freeze_base_model()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.freeze_base_model_activation_quantizers"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.freeze_base_model_activation_quantizers()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.freeze_base_model_param_quantizers"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.freeze_base_model_param_quantizers()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.get_fp_lora_layer"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.get_fp_lora_layer()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.get_quantized_lora_layer"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.get_quantized_lora_layer()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.quantize_lora_scale_with_fixed_range"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.quantize_lora_scale_with_fixed_range()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.set_bitwidth_for_lora_adapters"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.set_bitwidth_for_lora_adapters()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 </ul>
 </li>
 </ul>
@@ -370,31 +451,106 @@
 <li class="toctree-l5"><a class="reference internal" href="torch_quantization.html#backwards-compatibility">Backwards Compatibility</a></li>
 <li class="toctree-l5"><a class="reference internal" href="torch_quantization.html#id1">API Reference</a><ul>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/quantized_modules.html">Quantized Modules</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.input_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.input_quantizers</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.output_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.output_quantizers</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.param_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.param_quantizers</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.__quant_init__"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.__quant_init__()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.compute_encodings()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.forward"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.forward()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#configuration">Configuration</a></li>
 <li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#computing-encodings">Computing Encodings</a></li>
 <li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#quantized-module-classes">Quantized Module Classes</a></li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/quantizer.html">Quantizers</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantizer.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantizer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase"><code class="docutils literal notranslate"><span class="pre">QuantizerBase</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.allow_overwrite"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.allow_overwrite()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.compute_encodings()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.get_encoding"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.get_encoding()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.get_legacy_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.get_legacy_encodings()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.is_initialized"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.is_initialized()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.register_quantization_parameter"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.register_quantization_parameter()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.set_legacy_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.set_legacy_encodings()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizeDequantize"><code class="docutils literal notranslate"><span class="pre">QuantizeDequantize</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizeDequantize.forward"><code class="docutils literal notranslate"><span class="pre">QuantizeDequantize.forward()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.Quantize"><code class="docutils literal notranslate"><span class="pre">Quantize</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.Quantize.forward"><code class="docutils literal notranslate"><span class="pre">Quantize.forward()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html">QuantizationMixin</a><ul>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin</span></code></a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.input_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.input_quantizers</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.output_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.output_quantizers</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.param_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.param_quantizers</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.forward"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.forward()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.__quant_init__"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.__quant_init__()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.set_kernel"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.set_kernel()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.set_default_kernel"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.set_default_kernel()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.compute_encodings()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.from_module"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.from_module()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.get_default_kernel"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.get_default_kernel()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.get_kernel"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.get_kernel()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.implements"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.implements()</span></code></a></li>
+</ul>
+</li>
 </ul>
 </li>
-<li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html">QuantizationMixin</a></li>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html">quantization.affine</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#classes">Classes</a></li>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#functions">Functions</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#classes">Classes</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.Quantize"><code class="docutils literal notranslate"><span class="pre">Quantize</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.QuantizeDequantize"><code class="docutils literal notranslate"><span class="pre">QuantizeDequantize</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#functions">Functions</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.quantize"><code class="docutils literal notranslate"><span class="pre">quantize()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.quantize_dequantize"><code class="docutils literal notranslate"><span class="pre">quantize_dequantize()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.dequantize"><code class="docutils literal notranslate"><span class="pre">dequantize()</span></code></a></li>
+</ul>
+</li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html">quantization.float</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html#classes">Classes</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html#classes">Classes</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html#aimet_torch.v2.quantization.float.FloatQuantizeDequantize"><code class="docutils literal notranslate"><span class="pre">FloatQuantizeDequantize</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html#aimet_torch.v2.quantization.float.QuantizeDequantize"><code class="docutils literal notranslate"><span class="pre">QuantizeDequantize</span></code></a></li>
+</ul>
+</li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/encoding_analyzer.html">Encoding Analyzers</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#variants">Variants</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer"><code class="docutils literal notranslate"><span class="pre">EncodingAnalyzer</span></code></a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.compute_encodings"><code class="docutils literal notranslate"><span class="pre">EncodingAnalyzer.compute_encodings()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.reset_stats"><code class="docutils literal notranslate"><span class="pre">EncodingAnalyzer.reset_stats()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.update_stats"><code class="docutils literal notranslate"><span class="pre">EncodingAnalyzer.update_stats()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#variants">Variants</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.MinMaxEncodingAnalyzer"><code class="docutils literal notranslate"><span class="pre">MinMaxEncodingAnalyzer</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.SqnrEncodingAnalyzer"><code class="docutils literal notranslate"><span class="pre">SqnrEncodingAnalyzer</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.PercentileEncodingAnalyzer"><code class="docutils literal notranslate"><span class="pre">PercentileEncodingAnalyzer</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/visualization_tools.html">Visualization Tools</a><ul>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/visualization_tools.html#aimet_torch.v2.visualization_tools.visualize_stats"><code class="docutils literal notranslate"><span class="pre">visualize_stats()</span></code></a></li>
 </ul>
 </li>
-<li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/visualization_tools.html">Visualization Tools</a></li>
 </ul>
 </li>
 </ul>
@@ -403,31 +559,102 @@
 </li>
 <li class="toctree-l3"><a class="reference internal" href="torch_compress.html">PyTorch Model Compression API</a><ul>
 <li class="toctree-l4"><a class="reference internal" href="torch_compress.html#introduction">Introduction</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#top-level-api-for-compression">Top-level API for Compression</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#top-level-api-for-compression">Top-level API for Compression</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.compress.ModelCompressor"><code class="docutils literal notranslate"><span class="pre">ModelCompressor</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.compress.ModelCompressor.compress_model"><code class="docutils literal notranslate"><span class="pre">ModelCompressor.compress_model()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_compress.html#greedy-selection-parameters">Greedy Selection Parameters</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_common.defs.GreedySelectionParameters"><code class="docutils literal notranslate"><span class="pre">GreedySelectionParameters</span></code></a></li>
 </ul>
 </li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#spatial-svd-configuration">Spatial SVD Configuration</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#weight-svd-configuration">Weight SVD Configuration</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#channel-pruning-configuration">Channel Pruning Configuration</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#configuration-definitions">Configuration Definitions</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#spatial-svd-configuration">Spatial SVD Configuration</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.AutoModeParams"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.AutoModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.ManualModeParams"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.ManualModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.Mode"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.Mode.auto"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode.auto</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.Mode.manual"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode.manual</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#weight-svd-configuration">Weight SVD Configuration</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.AutoModeParams"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.AutoModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.ManualModeParams"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.ManualModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.Mode"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.Mode</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.Mode.auto"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.Mode.auto</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.Mode.manual"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.Mode.manual</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#channel-pruning-configuration">Channel Pruning Configuration</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.AutoModeParams"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.AutoModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.ManualModeParams"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.ManualModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.Mode"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.Mode</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.Mode.auto"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.Mode.auto</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.Mode.manual"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.Mode.manual</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#configuration-definitions">Configuration Definitions</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ModuleCompRatioPair"><code class="docutils literal notranslate"><span class="pre">ModuleCompRatioPair</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_compress.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="torch_visualization_compression.html">PyTorch Model Visualization API for Compression</a><ul>
-<li class="toctree-l4"><a class="reference internal" href="torch_visualization_compression.html#top-level-api-compression">Top-level API Compression</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_visualization_compression.html#top-level-api-compression">Top-level API Compression</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_visualization_compression.html#aimet_torch.visualize_serialized_data.VisualizeCompression"><code class="docutils literal notranslate"><span class="pre">VisualizeCompression</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_visualization_compression.html#aimet_torch.visualize_serialized_data.VisualizeCompression.display_eval_scores"><code class="docutils literal notranslate"><span class="pre">VisualizeCompression.display_eval_scores()</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_visualization_compression.html#aimet_torch.visualize_serialized_data.VisualizeCompression.display_comp_ratio_plot"><code class="docutils literal notranslate"><span class="pre">VisualizeCompression.display_comp_ratio_plot()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_visualization_compression.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="torch_visualization_quantization.html">PyTorch Model Visualization API for Quantization</a><ul>
-<li class="toctree-l4"><a class="reference internal" href="torch_visualization_quantization.html#top-level-api-quantization">Top-level API Quantization</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_visualization_quantization.html#top-level-api-quantization">Top-level API Quantization</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_visualization_quantization.html#aimet_torch.visualize_model.visualize_relative_weight_ranges_to_identify_problematic_layers"><code class="docutils literal notranslate"><span class="pre">visualize_relative_weight_ranges_to_identify_problematic_layers()</span></code></a></li>
+<li class="toctree-l5"><a class="reference internal" href="torch_visualization_quantization.html#aimet_torch.visualize_model.visualize_weight_ranges"><code class="docutils literal notranslate"><span class="pre">visualize_weight_ranges()</span></code></a></li>
+<li class="toctree-l5"><a class="reference internal" href="torch_visualization_quantization.html#aimet_torch.visualize_model.visualize_changes_after_optimization"><code class="docutils literal notranslate"><span class="pre">visualize_changes_after_optimization()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_visualization_quantization.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="torch_layer_output_generation.html">PyTorch Debug API</a><ul>
-<li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#top-level-api">Top-level API</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#enum-definition">Enum Definition</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.LayerOutputUtil"><code class="docutils literal notranslate"><span class="pre">LayerOutputUtil</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.LayerOutputUtil.generate_layer_outputs"><code class="docutils literal notranslate"><span class="pre">LayerOutputUtil.generate_layer_outputs()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#enum-definition">Enum Definition</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.NamingScheme"><code class="docutils literal notranslate"><span class="pre">NamingScheme</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.NamingScheme.ONNX"><code class="docutils literal notranslate"><span class="pre">NamingScheme.ONNX</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.NamingScheme.PYTORCH"><code class="docutils literal notranslate"><span class="pre">NamingScheme.PYTORCH</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.NamingScheme.TORCHSCRIPT"><code class="docutils literal notranslate"><span class="pre">NamingScheme.TORCHSCRIPT</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#code-example">Code Example</a></li>
 </ul>
 </li>
@@ -437,27 +664,49 @@
 <li class="toctree-l3"><a class="reference internal" href="keras_quantization.html">TensorFlow Model Quantization API</a><ul>
 <li class="toctree-l4"><a class="reference internal" href="keras_model_guidelines.html"> Model Guidelines</a></li>
 <li class="toctree-l4"><a class="reference internal" href="keras_model_preparer.html"> Model Preparer API</a><ul>
-<li class="toctree-l5"><a class="reference internal" href="keras_model_preparer.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_model_preparer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_model_preparer.html#aimet_tensorflow.keras.model_preparer.prepare_model"><code class="docutils literal notranslate"><span class="pre">prepare_model()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_model_preparer.html#code-examples">Code Examples</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_model_preparer.html#limitations">Limitations</a></li>
 </ul>
 </li>
 <li class="toctree-l4"><a class="reference internal" href="keras_quant_analyzer.html"> Quant Analyzer API</a><ul>
-<li class="toctree-l5"><a class="reference internal" href="keras_quant_analyzer.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_quant_analyzer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_quant_analyzer.html#aimet_tensorflow.keras.quant_analyzer.QuantAnalyzer"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="keras_quant_analyzer.html#aimet_tensorflow.keras.quant_analyzer.QuantAnalyzer.analyze"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.analyze()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_quant_analyzer.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l4"><a class="reference internal" href="keras_quantsim.html"> Quantization Simulation API</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="keras_quantsim.html#user-guide-link">User Guide Link</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_quantsim.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_quantsim.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_quantsim.html#aimet_tensorflow.keras.quantsim.QuantizationSimModel"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="keras_quantsim.html#aimet_tensorflow.keras.quantsim.QuantizationSimModel.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel.compute_encodings()</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="keras_quantsim.html#aimet_tensorflow.keras.quantsim.QuantizationSimModel.export"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel.export()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_quantsim.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l4"><a class="reference internal" href="keras_adaround.html"> Adaptive Rounding API</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#examples-notebook-link">Examples Notebook Link</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#top-level-api">Top-level API</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#adaround-parameters">Adaround Parameters</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_adaround.html#aimet_tensorflow.keras.adaround_weight.Adaround.apply_adaround"><code class="docutils literal notranslate"><span class="pre">apply_adaround()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#adaround-parameters">Adaround Parameters</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_adaround.html#aimet_tensorflow.keras.adaround_weight.AdaroundParameters"><code class="docutils literal notranslate"><span class="pre">AdaroundParameters</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#enum-definition">Enum Definition</a><ul>
 <li class="toctree-l6"><a class="reference internal" href="keras_adaround.html#aimet_common.defs.QuantScheme"><code class="docutils literal notranslate"><span class="pre">QuantScheme</span></code></a><ul>
 <li class="toctree-l7"><a class="reference internal" href="keras_adaround.html#aimet_common.defs.QuantScheme.post_training_percentile"><code class="docutils literal notranslate"><span class="pre">QuantScheme.post_training_percentile</span></code></a></li>
@@ -476,15 +725,34 @@
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#introduction">Introduction</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#cross-layer-equalization-api">Cross Layer Equalization API</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#cross-layer-equalization-api">Cross Layer Equalization API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_cross_layer_equalization.html#aimet_tensorflow.keras.cross_layer_equalization.equalize_model"><code class="docutils literal notranslate"><span class="pre">equalize_model()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#code-example">Code Example</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#primitive-apis">Primitive APIs</a><ul>
 <li class="toctree-l6"><a class="reference internal" href="keras_primitive_apis_cle.html">Primitive APIs for Cross Layer Equalization</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#introduction">Introduction</a></li>
-<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#higher-level-apis-for-cross-layer-equalization">Higher Level APIs for Cross Layer Equalization</a></li>
+<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#higher-level-apis-for-cross-layer-equalization">Higher Level APIs for Cross Layer Equalization</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.batch_norm_fold.fold_all_batch_norms"><code class="docutils literal notranslate"><span class="pre">fold_all_batch_norms()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.CrossLayerScaling.scale_model"><code class="docutils literal notranslate"><span class="pre">scale_model()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.HighBiasFold.bias_fold"><code class="docutils literal notranslate"><span class="pre">bias_fold()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#code-examples-for-higher-level-apis">Code Examples for Higher Level APIs</a></li>
-<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#lower-level-apis-for-cross-layer-equalization">Lower Level APIs for Cross Layer Equalization</a></li>
-<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#custom-datatype-used">Custom Datatype used</a></li>
+<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#lower-level-apis-for-cross-layer-equalization">Lower Level APIs for Cross Layer Equalization</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.batch_norm_fold.fold_given_batch_norms"><code class="docutils literal notranslate"><span class="pre">fold_given_batch_norms()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.CrossLayerScaling.scale_cls_sets"><code class="docutils literal notranslate"><span class="pre">scale_cls_sets()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#id0"><code class="docutils literal notranslate"><span class="pre">bias_fold()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#custom-datatype-used">Custom Datatype used</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.ClsSetInfo"><code class="docutils literal notranslate"><span class="pre">ClsSetInfo</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.ClsSetInfo.ClsSetLayerPairInfo"><code class="docutils literal notranslate"><span class="pre">ClsSetInfo.ClsSetLayerPairInfo</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#code-example-for-lower-level-apis">Code Example for Lower level APIs</a></li>
 <li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#example-helper-methods-to-perform-cle-in-manual-mode">Example helper methods to perform CLE in manual mode</a></li>
 </ul>
@@ -496,7 +764,11 @@
 <li class="toctree-l4"><a class="reference internal" href="keras_batchnorm_re_estimation.html"> BN Re-estimation APIs</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#introduction">Introduction</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#top-level-apis">Top-level APIs</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#top-level-apis">Top-level APIs</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_batchnorm_re_estimation.html#aimet_tensorflow.keras.bn_reestimation.reestimate_bn_stats"><code class="docutils literal notranslate"><span class="pre">reestimate_bn_stats()</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="keras_batchnorm_re_estimation.html#aimet_tensorflow.keras.batch_norm_fold.fold_all_batch_norms_to_scale"><code class="docutils literal notranslate"><span class="pre">fold_all_batch_norms_to_scale()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#code-example">Code Example</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#limitations">Limitations</a></li>
 </ul>
@@ -504,15 +776,39 @@
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="keras_layer_output_generation.html">TensorFlow Debug API</a><ul>
-<li class="toctree-l4"><a class="reference internal" href="keras_layer_output_generation.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l4"><a class="reference internal" href="keras_layer_output_generation.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="keras_layer_output_generation.html#aimet_tensorflow.keras.layer_output_utils.LayerOutputUtil"><code class="docutils literal notranslate"><span class="pre">LayerOutputUtil</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_layer_output_generation.html#aimet_tensorflow.keras.layer_output_utils.LayerOutputUtil.generate_layer_outputs"><code class="docutils literal notranslate"><span class="pre">LayerOutputUtil.generate_layer_outputs()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="keras_layer_output_generation.html#code-example">Code Example</a></li>
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="keras_compression.html">TensorFlow Model Compression API</a><ul>
 <li class="toctree-l4"><a class="reference internal" href="keras_compression.html#introduction">Introduction</a></li>
-<li class="toctree-l4"><a class="reference internal" href="keras_compression.html#top-level-api-for-compression">Top-level API for Compression</a></li>
+<li class="toctree-l4"><a class="reference internal" href="keras_compression.html#top-level-api-for-compression">Top-level API for Compression</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.compress.ModelCompressor"><code class="docutils literal notranslate"><span class="pre">ModelCompressor</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.compress.ModelCompressor.compress_model"><code class="docutils literal notranslate"><span class="pre">ModelCompressor.compress_model()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="keras_compression.html#greedy-selection-parameters">Greedy Selection Parameters</a></li>
-<li class="toctree-l4"><a class="reference internal" href="keras_compression.html#spatial-svd-configuration">Spatial SVD Configuration</a></li>
+<li class="toctree-l4"><a class="reference internal" href="keras_compression.html#spatial-svd-configuration">Spatial SVD Configuration</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.AutoModeParams"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.AutoModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.ManualModeParams"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.ManualModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.Mode"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.Mode.auto"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode.auto</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.Mode.manual"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode.manual</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="keras_compression.html#configuration-definitions">Configuration Definitions</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="keras_compression.html#aimet_common.defs.CostMetric"><code class="docutils literal notranslate"><span class="pre">CostMetric</span></code></a><ul>
 <li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_common.defs.CostMetric.mac"><code class="docutils literal notranslate"><span class="pre">CostMetric.mac</span></code></a></li>
@@ -525,6 +821,7 @@
 <li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_common.defs.CompressionScheme.weight_svd"><code class="docutils literal notranslate"><span class="pre">CompressionScheme.weight_svd</span></code></a></li>
 </ul>
 </li>
+<li class="toctree-l5"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.ModuleCompRatioPair"><code class="docutils literal notranslate"><span class="pre">ModuleCompRatioPair</span></code></a></li>
 </ul>
 </li>
 <li class="toctree-l4"><a class="reference internal" href="keras_compression.html#code-examples">Code Examples</a></li>
diff --git a/releases/1.35.1/api_docs/onnx_layer_output_generation.html b/releases/1.35.1/api_docs/onnx_layer_output_generation.html
index 76e616d..49aba5b 100644
--- a/releases/1.35.1/api_docs/onnx_layer_output_generation.html
+++ b/releases/1.35.1/api_docs/onnx_layer_output_generation.html
@@ -243,9 +243,15 @@
 <li class="toctree-l4"><a class="reference internal" href="torch_quantization.html#aimet-torch">aimet_torch</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="torch_quantization.html#api-reference">API Reference</a><ul>
 <li class="toctree-l6"><a class="reference internal" href="torch_model_guidelines.html"> Model Guidelines</a></li>
-<li class="toctree-l6"><a class="reference internal" href="torch_architecture_checker.html"> Architecture Checker API</a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_architecture_checker.html"> Architecture Checker API</a><ul>
+<li class="toctree-l7"><a class="reference internal" href="torch_architecture_checker.html#aimet_torch.arch_checker.arch_checker.ArchChecker.check_model_arch"><code class="docutils literal notranslate"><span class="pre">check_model_arch()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l6"><a class="reference internal" href="torch_model_preparer.html"> Model Preparer API</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="torch_model_preparer.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_model_preparer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_model_preparer.html#aimet_torch.model_preparer.prepare_model"><code class="docutils literal notranslate"><span class="pre">prepare_model()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_model_preparer.html#code-examples">Code Examples</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_model_preparer.html#limitations-of-torch-fx-symbolic-trace-api">Limitations of torch.fx symbolic trace API</a></li>
 </ul>
@@ -255,10 +261,23 @@
 <li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.enable_per_layer_mse_loss"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.enable_per_layer_mse_loss()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.analyze"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.analyze()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_common.utils.CallbackFunc"><code class="docutils literal notranslate"><span class="pre">CallbackFunc</span></code></a></li>
 </ul>
 </li>
-<li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#run-specific-utility">Run specific utility</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#run-specific-utility">Run specific utility</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.check_model_sensitivity_to_quantization"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.check_model_sensitivity_to_quantization()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.perform_per_layer_analysis_by_enabling_quant_wrappers"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.perform_per_layer_analysis_by_enabling_quant_wrappers()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.perform_per_layer_analysis_by_disabling_quant_wrappers"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.perform_per_layer_analysis_by_disabling_quant_wrappers()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.export_per_layer_encoding_min_max_range"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.export_per_layer_encoding_min_max_range()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.export_per_layer_stats_histogram"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.export_per_layer_stats_histogram()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.export_per_layer_mse_loss"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.export_per_layer_mse_loss()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
@@ -266,7 +285,16 @@
 <li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#guidelines">Guidelines</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.QuantizationSimModel"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.QuantizationSimModel.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel.compute_encodings()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.QuantizationSimModel.export"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel.export()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.save_checkpoint"><code class="docutils literal notranslate"><span class="pre">quantsim.save_checkpoint()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.load_checkpoint"><code class="docutils literal notranslate"><span class="pre">quantsim.load_checkpoint()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#enum-definition">Enum Definition</a><ul>
 <li class="toctree-l8"><a class="reference internal" href="torch_quantsim.html#aimet_common.defs.QuantScheme"><code class="docutils literal notranslate"><span class="pre">QuantScheme</span></code></a><ul>
 <li class="toctree-l9"><a class="reference internal" href="torch_quantsim.html#aimet_common.defs.QuantScheme.post_training_percentile"><code class="docutils literal notranslate"><span class="pre">QuantScheme.post_training_percentile</span></code></a></li>
@@ -284,8 +312,14 @@
 <li class="toctree-l6"><a class="reference internal" href="torch_adaround.html"> Adaptive Rounding API</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#examples-notebook-link">Examples Notebook Link</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#top-level-api">Top-level API</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#adaround-parameters">Adaround Parameters</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_adaround.html#aimet_torch.v1.adaround.adaround_weight.Adaround.apply_adaround"><code class="docutils literal notranslate"><span class="pre">apply_adaround()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#adaround-parameters">Adaround Parameters</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_adaround.html#aimet_torch.v1.adaround.adaround_weight.AdaroundParameters"><code class="docutils literal notranslate"><span class="pre">AdaroundParameters</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#enum-definition">Enum Definition</a><ul>
 <li class="toctree-l8"><a class="reference internal" href="torch_adaround.html#aimet_common.defs.QuantScheme"><code class="docutils literal notranslate"><span class="pre">QuantScheme</span></code></a><ul>
 <li class="toctree-l9"><a class="reference internal" href="torch_adaround.html#aimet_common.defs.QuantScheme.post_training_percentile"><code class="docutils literal notranslate"><span class="pre">QuantScheme.post_training_percentile</span></code></a></li>
@@ -304,15 +338,31 @@
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#introduction">Introduction</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#cross-layer-equalization-api">Cross Layer Equalization API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#cross-layer-equalization-api">Cross Layer Equalization API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_cross_layer_equalization.html#aimet_torch.cross_layer_equalization.equalize_model"><code class="docutils literal notranslate"><span class="pre">equalize_model()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#code-example">Code Example</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#primitive-apis">Primitive APIs</a><ul>
 <li class="toctree-l8"><a class="reference internal" href="torch_primitive_apis_cle.html">Primitive APIs for Cross Layer Equalization</a><ul>
 <li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#introduction">Introduction</a></li>
-<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#clssetinfo-definition">ClsSetInfo Definition</a></li>
-<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#higher-level-apis-for-cross-layer-equalization">Higher Level APIs for Cross Layer Equalization</a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#clssetinfo-definition">ClsSetInfo Definition</a><ul>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.cross_layer_equalization.ClsSetInfo"><code class="docutils literal notranslate"><span class="pre">ClsSetInfo</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#higher-level-apis-for-cross-layer-equalization">Higher Level APIs for Cross Layer Equalization</a><ul>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.batch_norm_fold.fold_all_batch_norms"><code class="docutils literal notranslate"><span class="pre">fold_all_batch_norms()</span></code></a></li>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.cross_layer_equalization.CrossLayerScaling.scale_model"><code class="docutils literal notranslate"><span class="pre">scale_model()</span></code></a></li>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.cross_layer_equalization.HighBiasFold.bias_fold"><code class="docutils literal notranslate"><span class="pre">bias_fold()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#code-examples-for-higher-level-apis">Code Examples for Higher Level APIs</a></li>
-<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#lower-level-apis-for-cross-layer-equalization">Lower Level APIs for Cross Layer Equalization</a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#lower-level-apis-for-cross-layer-equalization">Lower Level APIs for Cross Layer Equalization</a><ul>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.batch_norm_fold.fold_given_batch_norms"><code class="docutils literal notranslate"><span class="pre">fold_given_batch_norms()</span></code></a></li>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.cross_layer_equalization.CrossLayerScaling.scale_cls_sets"><code class="docutils literal notranslate"><span class="pre">scale_cls_sets()</span></code></a></li>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#id0"><code class="docutils literal notranslate"><span class="pre">bias_fold()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#code-examples-for-lower-level-apis">Code Examples for Lower Level APIs</a></li>
 </ul>
 </li>
@@ -322,7 +372,10 @@
 </li>
 <li class="toctree-l6"><a class="reference internal" href="torch_bias_correction.html"> Bias Correction API</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#user-guide-link">User Guide Link</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#bias-correction-api">Bias Correction API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#bias-correction-api">Bias Correction API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_bias_correction.html#aimet_torch.bias_correction.correct_bias"><code class="docutils literal notranslate"><span class="pre">correct_bias()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#convbninfotype">ConvBnInfoType</a><ul>
 <li class="toctree-l8"><a class="reference internal" href="torch_bias_correction.html#aimet_common.bias_correction.ConvBnInfoType"><code class="docutils literal notranslate"><span class="pre">ConvBnInfoType</span></code></a></li>
 </ul>
@@ -336,7 +389,10 @@
 </li>
 </ul>
 </li>
-<li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#quantization-params">Quantization Params</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#quantization-params">Quantization Params</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_bias_correction.html#aimet_torch.v1.quantsim.QuantParams"><code class="docutils literal notranslate"><span class="pre">QuantParams</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#code-example-1-empirical-bias-correction">Code Example #1 Empirical Bias Correction</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#code-example-2-analytical-empirical-bias-correction">Code Example #2 Analytical + Empirical Bias correction</a></li>
 </ul>
@@ -344,21 +400,46 @@
 <li class="toctree-l6"><a class="reference internal" href="torch_auto_quant.html"> AutoQuant API</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#examples-notebook-link">Examples Notebook Link</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_auto_quant.html#aimet_torch.v1.auto_quant.AutoQuant"><code class="docutils literal notranslate"><span class="pre">AutoQuant</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="torch_batchnorm_re_estimation.html"> BN Re-estimation APIs</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#introduction">Introduction</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#top-level-apis">Top-level APIs</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#top-level-apis">Top-level APIs</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_batchnorm_re_estimation.html#aimet_torch.bn_reestimation.reestimate_bn_stats"><code class="docutils literal notranslate"><span class="pre">reestimate_bn_stats()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_batchnorm_re_estimation.html#aimet_torch.batch_norm_fold.fold_all_batch_norms_to_scale"><code class="docutils literal notranslate"><span class="pre">fold_all_batch_norms_to_scale()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#code-example-bn-reestimation">Code Example - BN-Reestimation</a></li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="torch_multi_gpu.html"> Multi-GPU guidelines</a></li>
 <li class="toctree-l6"><a class="reference internal" href="torch_peft_lora.html"> PEFT LoRA APIs</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_peft_lora.html#user-flow">User flow</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_peft_lora.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_peft_lora.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.AdapterMetaData"><code class="docutils literal notranslate"><span class="pre">AdapterMetaData</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.replace_lora_layers_with_quantizable_layers"><code class="docutils literal notranslate"><span class="pre">peft.replace_lora_layers_with_quantizable_layers()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.track_lora_meta_data"><code class="docutils literal notranslate"><span class="pre">peft.track_lora_meta_data()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.disable_lora_adapters"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.disable_lora_adapters()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.enable_adapter_and_load_weights"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.enable_adapter_and_load_weights()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.export_adapter_weights"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.export_adapter_weights()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.freeze_base_model"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.freeze_base_model()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.freeze_base_model_activation_quantizers"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.freeze_base_model_activation_quantizers()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.freeze_base_model_param_quantizers"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.freeze_base_model_param_quantizers()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.get_fp_lora_layer"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.get_fp_lora_layer()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.get_quantized_lora_layer"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.get_quantized_lora_layer()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.quantize_lora_scale_with_fixed_range"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.quantize_lora_scale_with_fixed_range()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.set_bitwidth_for_lora_adapters"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.set_bitwidth_for_lora_adapters()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 </ul>
 </li>
 </ul>
@@ -370,31 +451,106 @@
 <li class="toctree-l5"><a class="reference internal" href="torch_quantization.html#backwards-compatibility">Backwards Compatibility</a></li>
 <li class="toctree-l5"><a class="reference internal" href="torch_quantization.html#id1">API Reference</a><ul>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/quantized_modules.html">Quantized Modules</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.input_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.input_quantizers</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.output_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.output_quantizers</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.param_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.param_quantizers</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.__quant_init__"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.__quant_init__()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.compute_encodings()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.forward"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.forward()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#configuration">Configuration</a></li>
 <li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#computing-encodings">Computing Encodings</a></li>
 <li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#quantized-module-classes">Quantized Module Classes</a></li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/quantizer.html">Quantizers</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantizer.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantizer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase"><code class="docutils literal notranslate"><span class="pre">QuantizerBase</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.allow_overwrite"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.allow_overwrite()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.compute_encodings()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.get_encoding"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.get_encoding()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.get_legacy_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.get_legacy_encodings()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.is_initialized"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.is_initialized()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.register_quantization_parameter"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.register_quantization_parameter()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.set_legacy_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.set_legacy_encodings()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizeDequantize"><code class="docutils literal notranslate"><span class="pre">QuantizeDequantize</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizeDequantize.forward"><code class="docutils literal notranslate"><span class="pre">QuantizeDequantize.forward()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.Quantize"><code class="docutils literal notranslate"><span class="pre">Quantize</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.Quantize.forward"><code class="docutils literal notranslate"><span class="pre">Quantize.forward()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html">QuantizationMixin</a><ul>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin</span></code></a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.input_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.input_quantizers</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.output_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.output_quantizers</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.param_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.param_quantizers</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.forward"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.forward()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.__quant_init__"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.__quant_init__()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.set_kernel"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.set_kernel()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.set_default_kernel"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.set_default_kernel()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.compute_encodings()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.from_module"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.from_module()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.get_default_kernel"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.get_default_kernel()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.get_kernel"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.get_kernel()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.implements"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.implements()</span></code></a></li>
+</ul>
+</li>
 </ul>
 </li>
-<li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html">QuantizationMixin</a></li>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html">quantization.affine</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#classes">Classes</a></li>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#functions">Functions</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#classes">Classes</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.Quantize"><code class="docutils literal notranslate"><span class="pre">Quantize</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.QuantizeDequantize"><code class="docutils literal notranslate"><span class="pre">QuantizeDequantize</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#functions">Functions</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.quantize"><code class="docutils literal notranslate"><span class="pre">quantize()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.quantize_dequantize"><code class="docutils literal notranslate"><span class="pre">quantize_dequantize()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.dequantize"><code class="docutils literal notranslate"><span class="pre">dequantize()</span></code></a></li>
+</ul>
+</li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html">quantization.float</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html#classes">Classes</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html#classes">Classes</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html#aimet_torch.v2.quantization.float.FloatQuantizeDequantize"><code class="docutils literal notranslate"><span class="pre">FloatQuantizeDequantize</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html#aimet_torch.v2.quantization.float.QuantizeDequantize"><code class="docutils literal notranslate"><span class="pre">QuantizeDequantize</span></code></a></li>
+</ul>
+</li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/encoding_analyzer.html">Encoding Analyzers</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#variants">Variants</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer"><code class="docutils literal notranslate"><span class="pre">EncodingAnalyzer</span></code></a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.compute_encodings"><code class="docutils literal notranslate"><span class="pre">EncodingAnalyzer.compute_encodings()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.reset_stats"><code class="docutils literal notranslate"><span class="pre">EncodingAnalyzer.reset_stats()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.update_stats"><code class="docutils literal notranslate"><span class="pre">EncodingAnalyzer.update_stats()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#variants">Variants</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.MinMaxEncodingAnalyzer"><code class="docutils literal notranslate"><span class="pre">MinMaxEncodingAnalyzer</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.SqnrEncodingAnalyzer"><code class="docutils literal notranslate"><span class="pre">SqnrEncodingAnalyzer</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.PercentileEncodingAnalyzer"><code class="docutils literal notranslate"><span class="pre">PercentileEncodingAnalyzer</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/visualization_tools.html">Visualization Tools</a><ul>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/visualization_tools.html#aimet_torch.v2.visualization_tools.visualize_stats"><code class="docutils literal notranslate"><span class="pre">visualize_stats()</span></code></a></li>
 </ul>
 </li>
-<li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/visualization_tools.html">Visualization Tools</a></li>
 </ul>
 </li>
 </ul>
@@ -403,31 +559,102 @@
 </li>
 <li class="toctree-l3"><a class="reference internal" href="torch_compress.html">PyTorch Model Compression API</a><ul>
 <li class="toctree-l4"><a class="reference internal" href="torch_compress.html#introduction">Introduction</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#top-level-api-for-compression">Top-level API for Compression</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#top-level-api-for-compression">Top-level API for Compression</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.compress.ModelCompressor"><code class="docutils literal notranslate"><span class="pre">ModelCompressor</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.compress.ModelCompressor.compress_model"><code class="docutils literal notranslate"><span class="pre">ModelCompressor.compress_model()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_compress.html#greedy-selection-parameters">Greedy Selection Parameters</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_common.defs.GreedySelectionParameters"><code class="docutils literal notranslate"><span class="pre">GreedySelectionParameters</span></code></a></li>
 </ul>
 </li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#spatial-svd-configuration">Spatial SVD Configuration</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#weight-svd-configuration">Weight SVD Configuration</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#channel-pruning-configuration">Channel Pruning Configuration</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#configuration-definitions">Configuration Definitions</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#spatial-svd-configuration">Spatial SVD Configuration</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.AutoModeParams"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.AutoModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.ManualModeParams"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.ManualModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.Mode"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.Mode.auto"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode.auto</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.Mode.manual"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode.manual</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#weight-svd-configuration">Weight SVD Configuration</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.AutoModeParams"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.AutoModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.ManualModeParams"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.ManualModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.Mode"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.Mode</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.Mode.auto"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.Mode.auto</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.Mode.manual"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.Mode.manual</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#channel-pruning-configuration">Channel Pruning Configuration</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.AutoModeParams"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.AutoModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.ManualModeParams"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.ManualModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.Mode"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.Mode</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.Mode.auto"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.Mode.auto</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.Mode.manual"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.Mode.manual</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#configuration-definitions">Configuration Definitions</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ModuleCompRatioPair"><code class="docutils literal notranslate"><span class="pre">ModuleCompRatioPair</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_compress.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="torch_visualization_compression.html">PyTorch Model Visualization API for Compression</a><ul>
-<li class="toctree-l4"><a class="reference internal" href="torch_visualization_compression.html#top-level-api-compression">Top-level API Compression</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_visualization_compression.html#top-level-api-compression">Top-level API Compression</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_visualization_compression.html#aimet_torch.visualize_serialized_data.VisualizeCompression"><code class="docutils literal notranslate"><span class="pre">VisualizeCompression</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_visualization_compression.html#aimet_torch.visualize_serialized_data.VisualizeCompression.display_eval_scores"><code class="docutils literal notranslate"><span class="pre">VisualizeCompression.display_eval_scores()</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_visualization_compression.html#aimet_torch.visualize_serialized_data.VisualizeCompression.display_comp_ratio_plot"><code class="docutils literal notranslate"><span class="pre">VisualizeCompression.display_comp_ratio_plot()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_visualization_compression.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="torch_visualization_quantization.html">PyTorch Model Visualization API for Quantization</a><ul>
-<li class="toctree-l4"><a class="reference internal" href="torch_visualization_quantization.html#top-level-api-quantization">Top-level API Quantization</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_visualization_quantization.html#top-level-api-quantization">Top-level API Quantization</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_visualization_quantization.html#aimet_torch.visualize_model.visualize_relative_weight_ranges_to_identify_problematic_layers"><code class="docutils literal notranslate"><span class="pre">visualize_relative_weight_ranges_to_identify_problematic_layers()</span></code></a></li>
+<li class="toctree-l5"><a class="reference internal" href="torch_visualization_quantization.html#aimet_torch.visualize_model.visualize_weight_ranges"><code class="docutils literal notranslate"><span class="pre">visualize_weight_ranges()</span></code></a></li>
+<li class="toctree-l5"><a class="reference internal" href="torch_visualization_quantization.html#aimet_torch.visualize_model.visualize_changes_after_optimization"><code class="docutils literal notranslate"><span class="pre">visualize_changes_after_optimization()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_visualization_quantization.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="torch_layer_output_generation.html">PyTorch Debug API</a><ul>
-<li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#top-level-api">Top-level API</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#enum-definition">Enum Definition</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.LayerOutputUtil"><code class="docutils literal notranslate"><span class="pre">LayerOutputUtil</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.LayerOutputUtil.generate_layer_outputs"><code class="docutils literal notranslate"><span class="pre">LayerOutputUtil.generate_layer_outputs()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#enum-definition">Enum Definition</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.NamingScheme"><code class="docutils literal notranslate"><span class="pre">NamingScheme</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.NamingScheme.ONNX"><code class="docutils literal notranslate"><span class="pre">NamingScheme.ONNX</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.NamingScheme.PYTORCH"><code class="docutils literal notranslate"><span class="pre">NamingScheme.PYTORCH</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.NamingScheme.TORCHSCRIPT"><code class="docutils literal notranslate"><span class="pre">NamingScheme.TORCHSCRIPT</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#code-example">Code Example</a></li>
 </ul>
 </li>
@@ -437,27 +664,49 @@
 <li class="toctree-l3"><a class="reference internal" href="keras_quantization.html">TensorFlow Model Quantization API</a><ul>
 <li class="toctree-l4"><a class="reference internal" href="keras_model_guidelines.html"> Model Guidelines</a></li>
 <li class="toctree-l4"><a class="reference internal" href="keras_model_preparer.html"> Model Preparer API</a><ul>
-<li class="toctree-l5"><a class="reference internal" href="keras_model_preparer.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_model_preparer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_model_preparer.html#aimet_tensorflow.keras.model_preparer.prepare_model"><code class="docutils literal notranslate"><span class="pre">prepare_model()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_model_preparer.html#code-examples">Code Examples</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_model_preparer.html#limitations">Limitations</a></li>
 </ul>
 </li>
 <li class="toctree-l4"><a class="reference internal" href="keras_quant_analyzer.html"> Quant Analyzer API</a><ul>
-<li class="toctree-l5"><a class="reference internal" href="keras_quant_analyzer.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_quant_analyzer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_quant_analyzer.html#aimet_tensorflow.keras.quant_analyzer.QuantAnalyzer"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="keras_quant_analyzer.html#aimet_tensorflow.keras.quant_analyzer.QuantAnalyzer.analyze"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.analyze()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_quant_analyzer.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l4"><a class="reference internal" href="keras_quantsim.html"> Quantization Simulation API</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="keras_quantsim.html#user-guide-link">User Guide Link</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_quantsim.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_quantsim.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_quantsim.html#aimet_tensorflow.keras.quantsim.QuantizationSimModel"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="keras_quantsim.html#aimet_tensorflow.keras.quantsim.QuantizationSimModel.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel.compute_encodings()</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="keras_quantsim.html#aimet_tensorflow.keras.quantsim.QuantizationSimModel.export"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel.export()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_quantsim.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l4"><a class="reference internal" href="keras_adaround.html"> Adaptive Rounding API</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#examples-notebook-link">Examples Notebook Link</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#top-level-api">Top-level API</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#adaround-parameters">Adaround Parameters</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_adaround.html#aimet_tensorflow.keras.adaround_weight.Adaround.apply_adaround"><code class="docutils literal notranslate"><span class="pre">apply_adaround()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#adaround-parameters">Adaround Parameters</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_adaround.html#aimet_tensorflow.keras.adaround_weight.AdaroundParameters"><code class="docutils literal notranslate"><span class="pre">AdaroundParameters</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#enum-definition">Enum Definition</a><ul>
 <li class="toctree-l6"><a class="reference internal" href="keras_adaround.html#aimet_common.defs.QuantScheme"><code class="docutils literal notranslate"><span class="pre">QuantScheme</span></code></a><ul>
 <li class="toctree-l7"><a class="reference internal" href="keras_adaround.html#aimet_common.defs.QuantScheme.post_training_percentile"><code class="docutils literal notranslate"><span class="pre">QuantScheme.post_training_percentile</span></code></a></li>
@@ -476,15 +725,34 @@
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#introduction">Introduction</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#cross-layer-equalization-api">Cross Layer Equalization API</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#cross-layer-equalization-api">Cross Layer Equalization API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_cross_layer_equalization.html#aimet_tensorflow.keras.cross_layer_equalization.equalize_model"><code class="docutils literal notranslate"><span class="pre">equalize_model()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#code-example">Code Example</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#primitive-apis">Primitive APIs</a><ul>
 <li class="toctree-l6"><a class="reference internal" href="keras_primitive_apis_cle.html">Primitive APIs for Cross Layer Equalization</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#introduction">Introduction</a></li>
-<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#higher-level-apis-for-cross-layer-equalization">Higher Level APIs for Cross Layer Equalization</a></li>
+<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#higher-level-apis-for-cross-layer-equalization">Higher Level APIs for Cross Layer Equalization</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.batch_norm_fold.fold_all_batch_norms"><code class="docutils literal notranslate"><span class="pre">fold_all_batch_norms()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.CrossLayerScaling.scale_model"><code class="docutils literal notranslate"><span class="pre">scale_model()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.HighBiasFold.bias_fold"><code class="docutils literal notranslate"><span class="pre">bias_fold()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#code-examples-for-higher-level-apis">Code Examples for Higher Level APIs</a></li>
-<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#lower-level-apis-for-cross-layer-equalization">Lower Level APIs for Cross Layer Equalization</a></li>
-<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#custom-datatype-used">Custom Datatype used</a></li>
+<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#lower-level-apis-for-cross-layer-equalization">Lower Level APIs for Cross Layer Equalization</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.batch_norm_fold.fold_given_batch_norms"><code class="docutils literal notranslate"><span class="pre">fold_given_batch_norms()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.CrossLayerScaling.scale_cls_sets"><code class="docutils literal notranslate"><span class="pre">scale_cls_sets()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#id0"><code class="docutils literal notranslate"><span class="pre">bias_fold()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#custom-datatype-used">Custom Datatype used</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.ClsSetInfo"><code class="docutils literal notranslate"><span class="pre">ClsSetInfo</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.ClsSetInfo.ClsSetLayerPairInfo"><code class="docutils literal notranslate"><span class="pre">ClsSetInfo.ClsSetLayerPairInfo</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#code-example-for-lower-level-apis">Code Example for Lower level APIs</a></li>
 <li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#example-helper-methods-to-perform-cle-in-manual-mode">Example helper methods to perform CLE in manual mode</a></li>
 </ul>
@@ -496,7 +764,11 @@
 <li class="toctree-l4"><a class="reference internal" href="keras_batchnorm_re_estimation.html"> BN Re-estimation APIs</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#introduction">Introduction</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#top-level-apis">Top-level APIs</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#top-level-apis">Top-level APIs</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_batchnorm_re_estimation.html#aimet_tensorflow.keras.bn_reestimation.reestimate_bn_stats"><code class="docutils literal notranslate"><span class="pre">reestimate_bn_stats()</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="keras_batchnorm_re_estimation.html#aimet_tensorflow.keras.batch_norm_fold.fold_all_batch_norms_to_scale"><code class="docutils literal notranslate"><span class="pre">fold_all_batch_norms_to_scale()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#code-example">Code Example</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#limitations">Limitations</a></li>
 </ul>
@@ -504,15 +776,39 @@
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="keras_layer_output_generation.html">TensorFlow Debug API</a><ul>
-<li class="toctree-l4"><a class="reference internal" href="keras_layer_output_generation.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l4"><a class="reference internal" href="keras_layer_output_generation.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="keras_layer_output_generation.html#aimet_tensorflow.keras.layer_output_utils.LayerOutputUtil"><code class="docutils literal notranslate"><span class="pre">LayerOutputUtil</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_layer_output_generation.html#aimet_tensorflow.keras.layer_output_utils.LayerOutputUtil.generate_layer_outputs"><code class="docutils literal notranslate"><span class="pre">LayerOutputUtil.generate_layer_outputs()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="keras_layer_output_generation.html#code-example">Code Example</a></li>
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="keras_compression.html">TensorFlow Model Compression API</a><ul>
 <li class="toctree-l4"><a class="reference internal" href="keras_compression.html#introduction">Introduction</a></li>
-<li class="toctree-l4"><a class="reference internal" href="keras_compression.html#top-level-api-for-compression">Top-level API for Compression</a></li>
+<li class="toctree-l4"><a class="reference internal" href="keras_compression.html#top-level-api-for-compression">Top-level API for Compression</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.compress.ModelCompressor"><code class="docutils literal notranslate"><span class="pre">ModelCompressor</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.compress.ModelCompressor.compress_model"><code class="docutils literal notranslate"><span class="pre">ModelCompressor.compress_model()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="keras_compression.html#greedy-selection-parameters">Greedy Selection Parameters</a></li>
-<li class="toctree-l4"><a class="reference internal" href="keras_compression.html#spatial-svd-configuration">Spatial SVD Configuration</a></li>
+<li class="toctree-l4"><a class="reference internal" href="keras_compression.html#spatial-svd-configuration">Spatial SVD Configuration</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.AutoModeParams"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.AutoModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.ManualModeParams"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.ManualModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.Mode"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.Mode.auto"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode.auto</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.Mode.manual"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode.manual</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="keras_compression.html#configuration-definitions">Configuration Definitions</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="keras_compression.html#aimet_common.defs.CostMetric"><code class="docutils literal notranslate"><span class="pre">CostMetric</span></code></a><ul>
 <li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_common.defs.CostMetric.mac"><code class="docutils literal notranslate"><span class="pre">CostMetric.mac</span></code></a></li>
@@ -525,6 +821,7 @@
 <li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_common.defs.CompressionScheme.weight_svd"><code class="docutils literal notranslate"><span class="pre">CompressionScheme.weight_svd</span></code></a></li>
 </ul>
 </li>
+<li class="toctree-l5"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.ModuleCompRatioPair"><code class="docutils literal notranslate"><span class="pre">ModuleCompRatioPair</span></code></a></li>
 </ul>
 </li>
 <li class="toctree-l4"><a class="reference internal" href="keras_compression.html#code-examples">Code Examples</a></li>
diff --git a/releases/1.35.1/api_docs/onnx_mixed_precision.html b/releases/1.35.1/api_docs/onnx_mixed_precision.html
index 7a81c83..1d713c7 100644
--- a/releases/1.35.1/api_docs/onnx_mixed_precision.html
+++ b/releases/1.35.1/api_docs/onnx_mixed_precision.html
@@ -241,9 +241,15 @@
 <li class="toctree-l4"><a class="reference internal" href="torch_quantization.html#aimet-torch">aimet_torch</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="torch_quantization.html#api-reference">API Reference</a><ul>
 <li class="toctree-l6"><a class="reference internal" href="torch_model_guidelines.html"> Model Guidelines</a></li>
-<li class="toctree-l6"><a class="reference internal" href="torch_architecture_checker.html"> Architecture Checker API</a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_architecture_checker.html"> Architecture Checker API</a><ul>
+<li class="toctree-l7"><a class="reference internal" href="torch_architecture_checker.html#aimet_torch.arch_checker.arch_checker.ArchChecker.check_model_arch"><code class="docutils literal notranslate"><span class="pre">check_model_arch()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l6"><a class="reference internal" href="torch_model_preparer.html"> Model Preparer API</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="torch_model_preparer.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_model_preparer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_model_preparer.html#aimet_torch.model_preparer.prepare_model"><code class="docutils literal notranslate"><span class="pre">prepare_model()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_model_preparer.html#code-examples">Code Examples</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_model_preparer.html#limitations-of-torch-fx-symbolic-trace-api">Limitations of torch.fx symbolic trace API</a></li>
 </ul>
@@ -253,10 +259,23 @@
 <li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.enable_per_layer_mse_loss"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.enable_per_layer_mse_loss()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.analyze"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.analyze()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_common.utils.CallbackFunc"><code class="docutils literal notranslate"><span class="pre">CallbackFunc</span></code></a></li>
 </ul>
 </li>
-<li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#run-specific-utility">Run specific utility</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#run-specific-utility">Run specific utility</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.check_model_sensitivity_to_quantization"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.check_model_sensitivity_to_quantization()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.perform_per_layer_analysis_by_enabling_quant_wrappers"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.perform_per_layer_analysis_by_enabling_quant_wrappers()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.perform_per_layer_analysis_by_disabling_quant_wrappers"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.perform_per_layer_analysis_by_disabling_quant_wrappers()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.export_per_layer_encoding_min_max_range"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.export_per_layer_encoding_min_max_range()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.export_per_layer_stats_histogram"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.export_per_layer_stats_histogram()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.export_per_layer_mse_loss"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.export_per_layer_mse_loss()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
@@ -264,7 +283,16 @@
 <li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#guidelines">Guidelines</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.QuantizationSimModel"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.QuantizationSimModel.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel.compute_encodings()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.QuantizationSimModel.export"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel.export()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.save_checkpoint"><code class="docutils literal notranslate"><span class="pre">quantsim.save_checkpoint()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.load_checkpoint"><code class="docutils literal notranslate"><span class="pre">quantsim.load_checkpoint()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#enum-definition">Enum Definition</a><ul>
 <li class="toctree-l8"><a class="reference internal" href="torch_quantsim.html#aimet_common.defs.QuantScheme"><code class="docutils literal notranslate"><span class="pre">QuantScheme</span></code></a><ul>
 <li class="toctree-l9"><a class="reference internal" href="torch_quantsim.html#aimet_common.defs.QuantScheme.post_training_percentile"><code class="docutils literal notranslate"><span class="pre">QuantScheme.post_training_percentile</span></code></a></li>
@@ -282,8 +310,14 @@
 <li class="toctree-l6"><a class="reference internal" href="torch_adaround.html"> Adaptive Rounding API</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#examples-notebook-link">Examples Notebook Link</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#top-level-api">Top-level API</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#adaround-parameters">Adaround Parameters</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_adaround.html#aimet_torch.v1.adaround.adaround_weight.Adaround.apply_adaround"><code class="docutils literal notranslate"><span class="pre">apply_adaround()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#adaround-parameters">Adaround Parameters</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_adaround.html#aimet_torch.v1.adaround.adaround_weight.AdaroundParameters"><code class="docutils literal notranslate"><span class="pre">AdaroundParameters</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#enum-definition">Enum Definition</a><ul>
 <li class="toctree-l8"><a class="reference internal" href="torch_adaround.html#aimet_common.defs.QuantScheme"><code class="docutils literal notranslate"><span class="pre">QuantScheme</span></code></a><ul>
 <li class="toctree-l9"><a class="reference internal" href="torch_adaround.html#aimet_common.defs.QuantScheme.post_training_percentile"><code class="docutils literal notranslate"><span class="pre">QuantScheme.post_training_percentile</span></code></a></li>
@@ -302,15 +336,31 @@
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#introduction">Introduction</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#cross-layer-equalization-api">Cross Layer Equalization API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#cross-layer-equalization-api">Cross Layer Equalization API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_cross_layer_equalization.html#aimet_torch.cross_layer_equalization.equalize_model"><code class="docutils literal notranslate"><span class="pre">equalize_model()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#code-example">Code Example</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#primitive-apis">Primitive APIs</a><ul>
 <li class="toctree-l8"><a class="reference internal" href="torch_primitive_apis_cle.html">Primitive APIs for Cross Layer Equalization</a><ul>
 <li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#introduction">Introduction</a></li>
-<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#clssetinfo-definition">ClsSetInfo Definition</a></li>
-<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#higher-level-apis-for-cross-layer-equalization">Higher Level APIs for Cross Layer Equalization</a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#clssetinfo-definition">ClsSetInfo Definition</a><ul>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.cross_layer_equalization.ClsSetInfo"><code class="docutils literal notranslate"><span class="pre">ClsSetInfo</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#higher-level-apis-for-cross-layer-equalization">Higher Level APIs for Cross Layer Equalization</a><ul>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.batch_norm_fold.fold_all_batch_norms"><code class="docutils literal notranslate"><span class="pre">fold_all_batch_norms()</span></code></a></li>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.cross_layer_equalization.CrossLayerScaling.scale_model"><code class="docutils literal notranslate"><span class="pre">scale_model()</span></code></a></li>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.cross_layer_equalization.HighBiasFold.bias_fold"><code class="docutils literal notranslate"><span class="pre">bias_fold()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#code-examples-for-higher-level-apis">Code Examples for Higher Level APIs</a></li>
-<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#lower-level-apis-for-cross-layer-equalization">Lower Level APIs for Cross Layer Equalization</a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#lower-level-apis-for-cross-layer-equalization">Lower Level APIs for Cross Layer Equalization</a><ul>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.batch_norm_fold.fold_given_batch_norms"><code class="docutils literal notranslate"><span class="pre">fold_given_batch_norms()</span></code></a></li>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.cross_layer_equalization.CrossLayerScaling.scale_cls_sets"><code class="docutils literal notranslate"><span class="pre">scale_cls_sets()</span></code></a></li>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#id0"><code class="docutils literal notranslate"><span class="pre">bias_fold()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#code-examples-for-lower-level-apis">Code Examples for Lower Level APIs</a></li>
 </ul>
 </li>
@@ -320,7 +370,10 @@
 </li>
 <li class="toctree-l6"><a class="reference internal" href="torch_bias_correction.html"> Bias Correction API</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#user-guide-link">User Guide Link</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#bias-correction-api">Bias Correction API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#bias-correction-api">Bias Correction API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_bias_correction.html#aimet_torch.bias_correction.correct_bias"><code class="docutils literal notranslate"><span class="pre">correct_bias()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#convbninfotype">ConvBnInfoType</a><ul>
 <li class="toctree-l8"><a class="reference internal" href="torch_bias_correction.html#aimet_common.bias_correction.ConvBnInfoType"><code class="docutils literal notranslate"><span class="pre">ConvBnInfoType</span></code></a></li>
 </ul>
@@ -334,7 +387,10 @@
 </li>
 </ul>
 </li>
-<li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#quantization-params">Quantization Params</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#quantization-params">Quantization Params</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_bias_correction.html#aimet_torch.v1.quantsim.QuantParams"><code class="docutils literal notranslate"><span class="pre">QuantParams</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#code-example-1-empirical-bias-correction">Code Example #1 Empirical Bias Correction</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#code-example-2-analytical-empirical-bias-correction">Code Example #2 Analytical + Empirical Bias correction</a></li>
 </ul>
@@ -342,21 +398,46 @@
 <li class="toctree-l6"><a class="reference internal" href="torch_auto_quant.html"> AutoQuant API</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#examples-notebook-link">Examples Notebook Link</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_auto_quant.html#aimet_torch.v1.auto_quant.AutoQuant"><code class="docutils literal notranslate"><span class="pre">AutoQuant</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="torch_batchnorm_re_estimation.html"> BN Re-estimation APIs</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#introduction">Introduction</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#top-level-apis">Top-level APIs</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#top-level-apis">Top-level APIs</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_batchnorm_re_estimation.html#aimet_torch.bn_reestimation.reestimate_bn_stats"><code class="docutils literal notranslate"><span class="pre">reestimate_bn_stats()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_batchnorm_re_estimation.html#aimet_torch.batch_norm_fold.fold_all_batch_norms_to_scale"><code class="docutils literal notranslate"><span class="pre">fold_all_batch_norms_to_scale()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#code-example-bn-reestimation">Code Example - BN-Reestimation</a></li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="torch_multi_gpu.html"> Multi-GPU guidelines</a></li>
 <li class="toctree-l6"><a class="reference internal" href="torch_peft_lora.html"> PEFT LoRA APIs</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_peft_lora.html#user-flow">User flow</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_peft_lora.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_peft_lora.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.AdapterMetaData"><code class="docutils literal notranslate"><span class="pre">AdapterMetaData</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.replace_lora_layers_with_quantizable_layers"><code class="docutils literal notranslate"><span class="pre">peft.replace_lora_layers_with_quantizable_layers()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.track_lora_meta_data"><code class="docutils literal notranslate"><span class="pre">peft.track_lora_meta_data()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.disable_lora_adapters"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.disable_lora_adapters()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.enable_adapter_and_load_weights"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.enable_adapter_and_load_weights()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.export_adapter_weights"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.export_adapter_weights()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.freeze_base_model"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.freeze_base_model()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.freeze_base_model_activation_quantizers"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.freeze_base_model_activation_quantizers()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.freeze_base_model_param_quantizers"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.freeze_base_model_param_quantizers()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.get_fp_lora_layer"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.get_fp_lora_layer()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.get_quantized_lora_layer"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.get_quantized_lora_layer()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.quantize_lora_scale_with_fixed_range"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.quantize_lora_scale_with_fixed_range()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.set_bitwidth_for_lora_adapters"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.set_bitwidth_for_lora_adapters()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 </ul>
 </li>
 </ul>
@@ -368,31 +449,106 @@
 <li class="toctree-l5"><a class="reference internal" href="torch_quantization.html#backwards-compatibility">Backwards Compatibility</a></li>
 <li class="toctree-l5"><a class="reference internal" href="torch_quantization.html#id1">API Reference</a><ul>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/quantized_modules.html">Quantized Modules</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.input_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.input_quantizers</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.output_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.output_quantizers</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.param_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.param_quantizers</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.__quant_init__"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.__quant_init__()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.compute_encodings()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.forward"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.forward()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#configuration">Configuration</a></li>
 <li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#computing-encodings">Computing Encodings</a></li>
 <li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#quantized-module-classes">Quantized Module Classes</a></li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/quantizer.html">Quantizers</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantizer.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantizer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase"><code class="docutils literal notranslate"><span class="pre">QuantizerBase</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.allow_overwrite"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.allow_overwrite()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.compute_encodings()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.get_encoding"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.get_encoding()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.get_legacy_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.get_legacy_encodings()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.is_initialized"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.is_initialized()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.register_quantization_parameter"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.register_quantization_parameter()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.set_legacy_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.set_legacy_encodings()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizeDequantize"><code class="docutils literal notranslate"><span class="pre">QuantizeDequantize</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizeDequantize.forward"><code class="docutils literal notranslate"><span class="pre">QuantizeDequantize.forward()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.Quantize"><code class="docutils literal notranslate"><span class="pre">Quantize</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.Quantize.forward"><code class="docutils literal notranslate"><span class="pre">Quantize.forward()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html">QuantizationMixin</a><ul>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin</span></code></a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.input_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.input_quantizers</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.output_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.output_quantizers</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.param_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.param_quantizers</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.forward"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.forward()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.__quant_init__"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.__quant_init__()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.set_kernel"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.set_kernel()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.set_default_kernel"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.set_default_kernel()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.compute_encodings()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.from_module"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.from_module()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.get_default_kernel"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.get_default_kernel()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.get_kernel"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.get_kernel()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.implements"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.implements()</span></code></a></li>
+</ul>
+</li>
 </ul>
 </li>
-<li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html">QuantizationMixin</a></li>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html">quantization.affine</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#classes">Classes</a></li>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#functions">Functions</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#classes">Classes</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.Quantize"><code class="docutils literal notranslate"><span class="pre">Quantize</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.QuantizeDequantize"><code class="docutils literal notranslate"><span class="pre">QuantizeDequantize</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#functions">Functions</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.quantize"><code class="docutils literal notranslate"><span class="pre">quantize()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.quantize_dequantize"><code class="docutils literal notranslate"><span class="pre">quantize_dequantize()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.dequantize"><code class="docutils literal notranslate"><span class="pre">dequantize()</span></code></a></li>
+</ul>
+</li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html">quantization.float</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html#classes">Classes</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html#classes">Classes</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html#aimet_torch.v2.quantization.float.FloatQuantizeDequantize"><code class="docutils literal notranslate"><span class="pre">FloatQuantizeDequantize</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html#aimet_torch.v2.quantization.float.QuantizeDequantize"><code class="docutils literal notranslate"><span class="pre">QuantizeDequantize</span></code></a></li>
+</ul>
+</li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/encoding_analyzer.html">Encoding Analyzers</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#variants">Variants</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer"><code class="docutils literal notranslate"><span class="pre">EncodingAnalyzer</span></code></a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.compute_encodings"><code class="docutils literal notranslate"><span class="pre">EncodingAnalyzer.compute_encodings()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.reset_stats"><code class="docutils literal notranslate"><span class="pre">EncodingAnalyzer.reset_stats()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.update_stats"><code class="docutils literal notranslate"><span class="pre">EncodingAnalyzer.update_stats()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#variants">Variants</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.MinMaxEncodingAnalyzer"><code class="docutils literal notranslate"><span class="pre">MinMaxEncodingAnalyzer</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.SqnrEncodingAnalyzer"><code class="docutils literal notranslate"><span class="pre">SqnrEncodingAnalyzer</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.PercentileEncodingAnalyzer"><code class="docutils literal notranslate"><span class="pre">PercentileEncodingAnalyzer</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/visualization_tools.html">Visualization Tools</a><ul>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/visualization_tools.html#aimet_torch.v2.visualization_tools.visualize_stats"><code class="docutils literal notranslate"><span class="pre">visualize_stats()</span></code></a></li>
 </ul>
 </li>
-<li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/visualization_tools.html">Visualization Tools</a></li>
 </ul>
 </li>
 </ul>
@@ -401,31 +557,102 @@
 </li>
 <li class="toctree-l3"><a class="reference internal" href="torch_compress.html">PyTorch Model Compression API</a><ul>
 <li class="toctree-l4"><a class="reference internal" href="torch_compress.html#introduction">Introduction</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#top-level-api-for-compression">Top-level API for Compression</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#top-level-api-for-compression">Top-level API for Compression</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.compress.ModelCompressor"><code class="docutils literal notranslate"><span class="pre">ModelCompressor</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.compress.ModelCompressor.compress_model"><code class="docutils literal notranslate"><span class="pre">ModelCompressor.compress_model()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_compress.html#greedy-selection-parameters">Greedy Selection Parameters</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_common.defs.GreedySelectionParameters"><code class="docutils literal notranslate"><span class="pre">GreedySelectionParameters</span></code></a></li>
 </ul>
 </li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#spatial-svd-configuration">Spatial SVD Configuration</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#weight-svd-configuration">Weight SVD Configuration</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#channel-pruning-configuration">Channel Pruning Configuration</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#configuration-definitions">Configuration Definitions</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#spatial-svd-configuration">Spatial SVD Configuration</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.AutoModeParams"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.AutoModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.ManualModeParams"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.ManualModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.Mode"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.Mode.auto"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode.auto</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.Mode.manual"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode.manual</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#weight-svd-configuration">Weight SVD Configuration</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.AutoModeParams"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.AutoModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.ManualModeParams"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.ManualModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.Mode"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.Mode</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.Mode.auto"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.Mode.auto</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.Mode.manual"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.Mode.manual</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#channel-pruning-configuration">Channel Pruning Configuration</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.AutoModeParams"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.AutoModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.ManualModeParams"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.ManualModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.Mode"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.Mode</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.Mode.auto"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.Mode.auto</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.Mode.manual"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.Mode.manual</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#configuration-definitions">Configuration Definitions</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ModuleCompRatioPair"><code class="docutils literal notranslate"><span class="pre">ModuleCompRatioPair</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_compress.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="torch_visualization_compression.html">PyTorch Model Visualization API for Compression</a><ul>
-<li class="toctree-l4"><a class="reference internal" href="torch_visualization_compression.html#top-level-api-compression">Top-level API Compression</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_visualization_compression.html#top-level-api-compression">Top-level API Compression</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_visualization_compression.html#aimet_torch.visualize_serialized_data.VisualizeCompression"><code class="docutils literal notranslate"><span class="pre">VisualizeCompression</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_visualization_compression.html#aimet_torch.visualize_serialized_data.VisualizeCompression.display_eval_scores"><code class="docutils literal notranslate"><span class="pre">VisualizeCompression.display_eval_scores()</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_visualization_compression.html#aimet_torch.visualize_serialized_data.VisualizeCompression.display_comp_ratio_plot"><code class="docutils literal notranslate"><span class="pre">VisualizeCompression.display_comp_ratio_plot()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_visualization_compression.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="torch_visualization_quantization.html">PyTorch Model Visualization API for Quantization</a><ul>
-<li class="toctree-l4"><a class="reference internal" href="torch_visualization_quantization.html#top-level-api-quantization">Top-level API Quantization</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_visualization_quantization.html#top-level-api-quantization">Top-level API Quantization</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_visualization_quantization.html#aimet_torch.visualize_model.visualize_relative_weight_ranges_to_identify_problematic_layers"><code class="docutils literal notranslate"><span class="pre">visualize_relative_weight_ranges_to_identify_problematic_layers()</span></code></a></li>
+<li class="toctree-l5"><a class="reference internal" href="torch_visualization_quantization.html#aimet_torch.visualize_model.visualize_weight_ranges"><code class="docutils literal notranslate"><span class="pre">visualize_weight_ranges()</span></code></a></li>
+<li class="toctree-l5"><a class="reference internal" href="torch_visualization_quantization.html#aimet_torch.visualize_model.visualize_changes_after_optimization"><code class="docutils literal notranslate"><span class="pre">visualize_changes_after_optimization()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_visualization_quantization.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="torch_layer_output_generation.html">PyTorch Debug API</a><ul>
-<li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#top-level-api">Top-level API</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#enum-definition">Enum Definition</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.LayerOutputUtil"><code class="docutils literal notranslate"><span class="pre">LayerOutputUtil</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.LayerOutputUtil.generate_layer_outputs"><code class="docutils literal notranslate"><span class="pre">LayerOutputUtil.generate_layer_outputs()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#enum-definition">Enum Definition</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.NamingScheme"><code class="docutils literal notranslate"><span class="pre">NamingScheme</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.NamingScheme.ONNX"><code class="docutils literal notranslate"><span class="pre">NamingScheme.ONNX</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.NamingScheme.PYTORCH"><code class="docutils literal notranslate"><span class="pre">NamingScheme.PYTORCH</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.NamingScheme.TORCHSCRIPT"><code class="docutils literal notranslate"><span class="pre">NamingScheme.TORCHSCRIPT</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#code-example">Code Example</a></li>
 </ul>
 </li>
@@ -435,27 +662,49 @@
 <li class="toctree-l3"><a class="reference internal" href="keras_quantization.html">TensorFlow Model Quantization API</a><ul>
 <li class="toctree-l4"><a class="reference internal" href="keras_model_guidelines.html"> Model Guidelines</a></li>
 <li class="toctree-l4"><a class="reference internal" href="keras_model_preparer.html"> Model Preparer API</a><ul>
-<li class="toctree-l5"><a class="reference internal" href="keras_model_preparer.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_model_preparer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_model_preparer.html#aimet_tensorflow.keras.model_preparer.prepare_model"><code class="docutils literal notranslate"><span class="pre">prepare_model()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_model_preparer.html#code-examples">Code Examples</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_model_preparer.html#limitations">Limitations</a></li>
 </ul>
 </li>
 <li class="toctree-l4"><a class="reference internal" href="keras_quant_analyzer.html"> Quant Analyzer API</a><ul>
-<li class="toctree-l5"><a class="reference internal" href="keras_quant_analyzer.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_quant_analyzer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_quant_analyzer.html#aimet_tensorflow.keras.quant_analyzer.QuantAnalyzer"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="keras_quant_analyzer.html#aimet_tensorflow.keras.quant_analyzer.QuantAnalyzer.analyze"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.analyze()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_quant_analyzer.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l4"><a class="reference internal" href="keras_quantsim.html"> Quantization Simulation API</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="keras_quantsim.html#user-guide-link">User Guide Link</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_quantsim.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_quantsim.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_quantsim.html#aimet_tensorflow.keras.quantsim.QuantizationSimModel"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="keras_quantsim.html#aimet_tensorflow.keras.quantsim.QuantizationSimModel.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel.compute_encodings()</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="keras_quantsim.html#aimet_tensorflow.keras.quantsim.QuantizationSimModel.export"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel.export()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_quantsim.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l4"><a class="reference internal" href="keras_adaround.html"> Adaptive Rounding API</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#examples-notebook-link">Examples Notebook Link</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#top-level-api">Top-level API</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#adaround-parameters">Adaround Parameters</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_adaround.html#aimet_tensorflow.keras.adaround_weight.Adaround.apply_adaround"><code class="docutils literal notranslate"><span class="pre">apply_adaround()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#adaround-parameters">Adaround Parameters</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_adaround.html#aimet_tensorflow.keras.adaround_weight.AdaroundParameters"><code class="docutils literal notranslate"><span class="pre">AdaroundParameters</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#enum-definition">Enum Definition</a><ul>
 <li class="toctree-l6"><a class="reference internal" href="keras_adaround.html#aimet_common.defs.QuantScheme"><code class="docutils literal notranslate"><span class="pre">QuantScheme</span></code></a><ul>
 <li class="toctree-l7"><a class="reference internal" href="keras_adaround.html#aimet_common.defs.QuantScheme.post_training_percentile"><code class="docutils literal notranslate"><span class="pre">QuantScheme.post_training_percentile</span></code></a></li>
@@ -474,15 +723,34 @@
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#introduction">Introduction</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#cross-layer-equalization-api">Cross Layer Equalization API</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#cross-layer-equalization-api">Cross Layer Equalization API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_cross_layer_equalization.html#aimet_tensorflow.keras.cross_layer_equalization.equalize_model"><code class="docutils literal notranslate"><span class="pre">equalize_model()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#code-example">Code Example</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#primitive-apis">Primitive APIs</a><ul>
 <li class="toctree-l6"><a class="reference internal" href="keras_primitive_apis_cle.html">Primitive APIs for Cross Layer Equalization</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#introduction">Introduction</a></li>
-<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#higher-level-apis-for-cross-layer-equalization">Higher Level APIs for Cross Layer Equalization</a></li>
+<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#higher-level-apis-for-cross-layer-equalization">Higher Level APIs for Cross Layer Equalization</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.batch_norm_fold.fold_all_batch_norms"><code class="docutils literal notranslate"><span class="pre">fold_all_batch_norms()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.CrossLayerScaling.scale_model"><code class="docutils literal notranslate"><span class="pre">scale_model()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.HighBiasFold.bias_fold"><code class="docutils literal notranslate"><span class="pre">bias_fold()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#code-examples-for-higher-level-apis">Code Examples for Higher Level APIs</a></li>
-<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#lower-level-apis-for-cross-layer-equalization">Lower Level APIs for Cross Layer Equalization</a></li>
-<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#custom-datatype-used">Custom Datatype used</a></li>
+<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#lower-level-apis-for-cross-layer-equalization">Lower Level APIs for Cross Layer Equalization</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.batch_norm_fold.fold_given_batch_norms"><code class="docutils literal notranslate"><span class="pre">fold_given_batch_norms()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.CrossLayerScaling.scale_cls_sets"><code class="docutils literal notranslate"><span class="pre">scale_cls_sets()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#id0"><code class="docutils literal notranslate"><span class="pre">bias_fold()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#custom-datatype-used">Custom Datatype used</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.ClsSetInfo"><code class="docutils literal notranslate"><span class="pre">ClsSetInfo</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.ClsSetInfo.ClsSetLayerPairInfo"><code class="docutils literal notranslate"><span class="pre">ClsSetInfo.ClsSetLayerPairInfo</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#code-example-for-lower-level-apis">Code Example for Lower level APIs</a></li>
 <li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#example-helper-methods-to-perform-cle-in-manual-mode">Example helper methods to perform CLE in manual mode</a></li>
 </ul>
@@ -494,7 +762,11 @@
 <li class="toctree-l4"><a class="reference internal" href="keras_batchnorm_re_estimation.html"> BN Re-estimation APIs</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#introduction">Introduction</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#top-level-apis">Top-level APIs</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#top-level-apis">Top-level APIs</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_batchnorm_re_estimation.html#aimet_tensorflow.keras.bn_reestimation.reestimate_bn_stats"><code class="docutils literal notranslate"><span class="pre">reestimate_bn_stats()</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="keras_batchnorm_re_estimation.html#aimet_tensorflow.keras.batch_norm_fold.fold_all_batch_norms_to_scale"><code class="docutils literal notranslate"><span class="pre">fold_all_batch_norms_to_scale()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#code-example">Code Example</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#limitations">Limitations</a></li>
 </ul>
@@ -502,15 +774,39 @@
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="keras_layer_output_generation.html">TensorFlow Debug API</a><ul>
-<li class="toctree-l4"><a class="reference internal" href="keras_layer_output_generation.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l4"><a class="reference internal" href="keras_layer_output_generation.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="keras_layer_output_generation.html#aimet_tensorflow.keras.layer_output_utils.LayerOutputUtil"><code class="docutils literal notranslate"><span class="pre">LayerOutputUtil</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_layer_output_generation.html#aimet_tensorflow.keras.layer_output_utils.LayerOutputUtil.generate_layer_outputs"><code class="docutils literal notranslate"><span class="pre">LayerOutputUtil.generate_layer_outputs()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="keras_layer_output_generation.html#code-example">Code Example</a></li>
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="keras_compression.html">TensorFlow Model Compression API</a><ul>
 <li class="toctree-l4"><a class="reference internal" href="keras_compression.html#introduction">Introduction</a></li>
-<li class="toctree-l4"><a class="reference internal" href="keras_compression.html#top-level-api-for-compression">Top-level API for Compression</a></li>
+<li class="toctree-l4"><a class="reference internal" href="keras_compression.html#top-level-api-for-compression">Top-level API for Compression</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.compress.ModelCompressor"><code class="docutils literal notranslate"><span class="pre">ModelCompressor</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.compress.ModelCompressor.compress_model"><code class="docutils literal notranslate"><span class="pre">ModelCompressor.compress_model()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="keras_compression.html#greedy-selection-parameters">Greedy Selection Parameters</a></li>
-<li class="toctree-l4"><a class="reference internal" href="keras_compression.html#spatial-svd-configuration">Spatial SVD Configuration</a></li>
+<li class="toctree-l4"><a class="reference internal" href="keras_compression.html#spatial-svd-configuration">Spatial SVD Configuration</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.AutoModeParams"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.AutoModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.ManualModeParams"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.ManualModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.Mode"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.Mode.auto"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode.auto</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.Mode.manual"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode.manual</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="keras_compression.html#configuration-definitions">Configuration Definitions</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="keras_compression.html#aimet_common.defs.CostMetric"><code class="docutils literal notranslate"><span class="pre">CostMetric</span></code></a><ul>
 <li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_common.defs.CostMetric.mac"><code class="docutils literal notranslate"><span class="pre">CostMetric.mac</span></code></a></li>
@@ -523,6 +819,7 @@
 <li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_common.defs.CompressionScheme.weight_svd"><code class="docutils literal notranslate"><span class="pre">CompressionScheme.weight_svd</span></code></a></li>
 </ul>
 </li>
+<li class="toctree-l5"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.ModuleCompRatioPair"><code class="docutils literal notranslate"><span class="pre">ModuleCompRatioPair</span></code></a></li>
 </ul>
 </li>
 <li class="toctree-l4"><a class="reference internal" href="keras_compression.html#code-examples">Code Examples</a></li>
diff --git a/releases/1.35.1/api_docs/onnx_quant_analyzer.html b/releases/1.35.1/api_docs/onnx_quant_analyzer.html
index 50f87f6..7630c11 100644
--- a/releases/1.35.1/api_docs/onnx_quant_analyzer.html
+++ b/releases/1.35.1/api_docs/onnx_quant_analyzer.html
@@ -243,9 +243,15 @@
 <li class="toctree-l4"><a class="reference internal" href="torch_quantization.html#aimet-torch">aimet_torch</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="torch_quantization.html#api-reference">API Reference</a><ul>
 <li class="toctree-l6"><a class="reference internal" href="torch_model_guidelines.html"> Model Guidelines</a></li>
-<li class="toctree-l6"><a class="reference internal" href="torch_architecture_checker.html"> Architecture Checker API</a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_architecture_checker.html"> Architecture Checker API</a><ul>
+<li class="toctree-l7"><a class="reference internal" href="torch_architecture_checker.html#aimet_torch.arch_checker.arch_checker.ArchChecker.check_model_arch"><code class="docutils literal notranslate"><span class="pre">check_model_arch()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l6"><a class="reference internal" href="torch_model_preparer.html"> Model Preparer API</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="torch_model_preparer.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_model_preparer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_model_preparer.html#aimet_torch.model_preparer.prepare_model"><code class="docutils literal notranslate"><span class="pre">prepare_model()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_model_preparer.html#code-examples">Code Examples</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_model_preparer.html#limitations-of-torch-fx-symbolic-trace-api">Limitations of torch.fx symbolic trace API</a></li>
 </ul>
@@ -255,10 +261,23 @@
 <li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.enable_per_layer_mse_loss"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.enable_per_layer_mse_loss()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.analyze"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.analyze()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_common.utils.CallbackFunc"><code class="docutils literal notranslate"><span class="pre">CallbackFunc</span></code></a></li>
 </ul>
 </li>
-<li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#run-specific-utility">Run specific utility</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#run-specific-utility">Run specific utility</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.check_model_sensitivity_to_quantization"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.check_model_sensitivity_to_quantization()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.perform_per_layer_analysis_by_enabling_quant_wrappers"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.perform_per_layer_analysis_by_enabling_quant_wrappers()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.perform_per_layer_analysis_by_disabling_quant_wrappers"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.perform_per_layer_analysis_by_disabling_quant_wrappers()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.export_per_layer_encoding_min_max_range"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.export_per_layer_encoding_min_max_range()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.export_per_layer_stats_histogram"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.export_per_layer_stats_histogram()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.export_per_layer_mse_loss"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.export_per_layer_mse_loss()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
@@ -266,7 +285,16 @@
 <li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#guidelines">Guidelines</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.QuantizationSimModel"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.QuantizationSimModel.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel.compute_encodings()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.QuantizationSimModel.export"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel.export()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.save_checkpoint"><code class="docutils literal notranslate"><span class="pre">quantsim.save_checkpoint()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.load_checkpoint"><code class="docutils literal notranslate"><span class="pre">quantsim.load_checkpoint()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#enum-definition">Enum Definition</a><ul>
 <li class="toctree-l8"><a class="reference internal" href="torch_quantsim.html#aimet_common.defs.QuantScheme"><code class="docutils literal notranslate"><span class="pre">QuantScheme</span></code></a><ul>
 <li class="toctree-l9"><a class="reference internal" href="torch_quantsim.html#aimet_common.defs.QuantScheme.post_training_percentile"><code class="docutils literal notranslate"><span class="pre">QuantScheme.post_training_percentile</span></code></a></li>
@@ -284,8 +312,14 @@
 <li class="toctree-l6"><a class="reference internal" href="torch_adaround.html"> Adaptive Rounding API</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#examples-notebook-link">Examples Notebook Link</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#top-level-api">Top-level API</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#adaround-parameters">Adaround Parameters</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_adaround.html#aimet_torch.v1.adaround.adaround_weight.Adaround.apply_adaround"><code class="docutils literal notranslate"><span class="pre">apply_adaround()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#adaround-parameters">Adaround Parameters</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_adaround.html#aimet_torch.v1.adaround.adaround_weight.AdaroundParameters"><code class="docutils literal notranslate"><span class="pre">AdaroundParameters</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#enum-definition">Enum Definition</a><ul>
 <li class="toctree-l8"><a class="reference internal" href="torch_adaround.html#aimet_common.defs.QuantScheme"><code class="docutils literal notranslate"><span class="pre">QuantScheme</span></code></a><ul>
 <li class="toctree-l9"><a class="reference internal" href="torch_adaround.html#aimet_common.defs.QuantScheme.post_training_percentile"><code class="docutils literal notranslate"><span class="pre">QuantScheme.post_training_percentile</span></code></a></li>
@@ -304,15 +338,31 @@
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#introduction">Introduction</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#cross-layer-equalization-api">Cross Layer Equalization API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#cross-layer-equalization-api">Cross Layer Equalization API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_cross_layer_equalization.html#aimet_torch.cross_layer_equalization.equalize_model"><code class="docutils literal notranslate"><span class="pre">equalize_model()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#code-example">Code Example</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#primitive-apis">Primitive APIs</a><ul>
 <li class="toctree-l8"><a class="reference internal" href="torch_primitive_apis_cle.html">Primitive APIs for Cross Layer Equalization</a><ul>
 <li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#introduction">Introduction</a></li>
-<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#clssetinfo-definition">ClsSetInfo Definition</a></li>
-<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#higher-level-apis-for-cross-layer-equalization">Higher Level APIs for Cross Layer Equalization</a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#clssetinfo-definition">ClsSetInfo Definition</a><ul>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.cross_layer_equalization.ClsSetInfo"><code class="docutils literal notranslate"><span class="pre">ClsSetInfo</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#higher-level-apis-for-cross-layer-equalization">Higher Level APIs for Cross Layer Equalization</a><ul>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.batch_norm_fold.fold_all_batch_norms"><code class="docutils literal notranslate"><span class="pre">fold_all_batch_norms()</span></code></a></li>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.cross_layer_equalization.CrossLayerScaling.scale_model"><code class="docutils literal notranslate"><span class="pre">scale_model()</span></code></a></li>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.cross_layer_equalization.HighBiasFold.bias_fold"><code class="docutils literal notranslate"><span class="pre">bias_fold()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#code-examples-for-higher-level-apis">Code Examples for Higher Level APIs</a></li>
-<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#lower-level-apis-for-cross-layer-equalization">Lower Level APIs for Cross Layer Equalization</a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#lower-level-apis-for-cross-layer-equalization">Lower Level APIs for Cross Layer Equalization</a><ul>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.batch_norm_fold.fold_given_batch_norms"><code class="docutils literal notranslate"><span class="pre">fold_given_batch_norms()</span></code></a></li>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.cross_layer_equalization.CrossLayerScaling.scale_cls_sets"><code class="docutils literal notranslate"><span class="pre">scale_cls_sets()</span></code></a></li>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#id0"><code class="docutils literal notranslate"><span class="pre">bias_fold()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#code-examples-for-lower-level-apis">Code Examples for Lower Level APIs</a></li>
 </ul>
 </li>
@@ -322,7 +372,10 @@
 </li>
 <li class="toctree-l6"><a class="reference internal" href="torch_bias_correction.html"> Bias Correction API</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#user-guide-link">User Guide Link</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#bias-correction-api">Bias Correction API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#bias-correction-api">Bias Correction API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_bias_correction.html#aimet_torch.bias_correction.correct_bias"><code class="docutils literal notranslate"><span class="pre">correct_bias()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#convbninfotype">ConvBnInfoType</a><ul>
 <li class="toctree-l8"><a class="reference internal" href="torch_bias_correction.html#aimet_common.bias_correction.ConvBnInfoType"><code class="docutils literal notranslate"><span class="pre">ConvBnInfoType</span></code></a></li>
 </ul>
@@ -336,7 +389,10 @@
 </li>
 </ul>
 </li>
-<li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#quantization-params">Quantization Params</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#quantization-params">Quantization Params</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_bias_correction.html#aimet_torch.v1.quantsim.QuantParams"><code class="docutils literal notranslate"><span class="pre">QuantParams</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#code-example-1-empirical-bias-correction">Code Example #1 Empirical Bias Correction</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#code-example-2-analytical-empirical-bias-correction">Code Example #2 Analytical + Empirical Bias correction</a></li>
 </ul>
@@ -344,21 +400,46 @@
 <li class="toctree-l6"><a class="reference internal" href="torch_auto_quant.html"> AutoQuant API</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#examples-notebook-link">Examples Notebook Link</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_auto_quant.html#aimet_torch.v1.auto_quant.AutoQuant"><code class="docutils literal notranslate"><span class="pre">AutoQuant</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="torch_batchnorm_re_estimation.html"> BN Re-estimation APIs</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#introduction">Introduction</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#top-level-apis">Top-level APIs</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#top-level-apis">Top-level APIs</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_batchnorm_re_estimation.html#aimet_torch.bn_reestimation.reestimate_bn_stats"><code class="docutils literal notranslate"><span class="pre">reestimate_bn_stats()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_batchnorm_re_estimation.html#aimet_torch.batch_norm_fold.fold_all_batch_norms_to_scale"><code class="docutils literal notranslate"><span class="pre">fold_all_batch_norms_to_scale()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#code-example-bn-reestimation">Code Example - BN-Reestimation</a></li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="torch_multi_gpu.html"> Multi-GPU guidelines</a></li>
 <li class="toctree-l6"><a class="reference internal" href="torch_peft_lora.html"> PEFT LoRA APIs</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_peft_lora.html#user-flow">User flow</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_peft_lora.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_peft_lora.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.AdapterMetaData"><code class="docutils literal notranslate"><span class="pre">AdapterMetaData</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.replace_lora_layers_with_quantizable_layers"><code class="docutils literal notranslate"><span class="pre">peft.replace_lora_layers_with_quantizable_layers()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.track_lora_meta_data"><code class="docutils literal notranslate"><span class="pre">peft.track_lora_meta_data()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.disable_lora_adapters"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.disable_lora_adapters()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.enable_adapter_and_load_weights"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.enable_adapter_and_load_weights()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.export_adapter_weights"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.export_adapter_weights()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.freeze_base_model"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.freeze_base_model()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.freeze_base_model_activation_quantizers"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.freeze_base_model_activation_quantizers()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.freeze_base_model_param_quantizers"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.freeze_base_model_param_quantizers()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.get_fp_lora_layer"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.get_fp_lora_layer()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.get_quantized_lora_layer"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.get_quantized_lora_layer()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.quantize_lora_scale_with_fixed_range"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.quantize_lora_scale_with_fixed_range()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.set_bitwidth_for_lora_adapters"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.set_bitwidth_for_lora_adapters()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 </ul>
 </li>
 </ul>
@@ -370,31 +451,106 @@
 <li class="toctree-l5"><a class="reference internal" href="torch_quantization.html#backwards-compatibility">Backwards Compatibility</a></li>
 <li class="toctree-l5"><a class="reference internal" href="torch_quantization.html#id1">API Reference</a><ul>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/quantized_modules.html">Quantized Modules</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.input_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.input_quantizers</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.output_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.output_quantizers</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.param_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.param_quantizers</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.__quant_init__"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.__quant_init__()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.compute_encodings()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.forward"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.forward()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#configuration">Configuration</a></li>
 <li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#computing-encodings">Computing Encodings</a></li>
 <li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#quantized-module-classes">Quantized Module Classes</a></li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/quantizer.html">Quantizers</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantizer.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantizer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase"><code class="docutils literal notranslate"><span class="pre">QuantizerBase</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.allow_overwrite"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.allow_overwrite()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.compute_encodings()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.get_encoding"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.get_encoding()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.get_legacy_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.get_legacy_encodings()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.is_initialized"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.is_initialized()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.register_quantization_parameter"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.register_quantization_parameter()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.set_legacy_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.set_legacy_encodings()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizeDequantize"><code class="docutils literal notranslate"><span class="pre">QuantizeDequantize</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizeDequantize.forward"><code class="docutils literal notranslate"><span class="pre">QuantizeDequantize.forward()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.Quantize"><code class="docutils literal notranslate"><span class="pre">Quantize</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.Quantize.forward"><code class="docutils literal notranslate"><span class="pre">Quantize.forward()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html">QuantizationMixin</a><ul>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin</span></code></a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.input_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.input_quantizers</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.output_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.output_quantizers</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.param_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.param_quantizers</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.forward"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.forward()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.__quant_init__"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.__quant_init__()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.set_kernel"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.set_kernel()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.set_default_kernel"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.set_default_kernel()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.compute_encodings()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.from_module"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.from_module()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.get_default_kernel"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.get_default_kernel()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.get_kernel"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.get_kernel()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.implements"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.implements()</span></code></a></li>
+</ul>
+</li>
 </ul>
 </li>
-<li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html">QuantizationMixin</a></li>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html">quantization.affine</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#classes">Classes</a></li>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#functions">Functions</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#classes">Classes</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.Quantize"><code class="docutils literal notranslate"><span class="pre">Quantize</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.QuantizeDequantize"><code class="docutils literal notranslate"><span class="pre">QuantizeDequantize</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#functions">Functions</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.quantize"><code class="docutils literal notranslate"><span class="pre">quantize()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.quantize_dequantize"><code class="docutils literal notranslate"><span class="pre">quantize_dequantize()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.dequantize"><code class="docutils literal notranslate"><span class="pre">dequantize()</span></code></a></li>
+</ul>
+</li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html">quantization.float</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html#classes">Classes</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html#classes">Classes</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html#aimet_torch.v2.quantization.float.FloatQuantizeDequantize"><code class="docutils literal notranslate"><span class="pre">FloatQuantizeDequantize</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html#aimet_torch.v2.quantization.float.QuantizeDequantize"><code class="docutils literal notranslate"><span class="pre">QuantizeDequantize</span></code></a></li>
+</ul>
+</li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/encoding_analyzer.html">Encoding Analyzers</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#variants">Variants</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer"><code class="docutils literal notranslate"><span class="pre">EncodingAnalyzer</span></code></a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.compute_encodings"><code class="docutils literal notranslate"><span class="pre">EncodingAnalyzer.compute_encodings()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.reset_stats"><code class="docutils literal notranslate"><span class="pre">EncodingAnalyzer.reset_stats()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.update_stats"><code class="docutils literal notranslate"><span class="pre">EncodingAnalyzer.update_stats()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#variants">Variants</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.MinMaxEncodingAnalyzer"><code class="docutils literal notranslate"><span class="pre">MinMaxEncodingAnalyzer</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.SqnrEncodingAnalyzer"><code class="docutils literal notranslate"><span class="pre">SqnrEncodingAnalyzer</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.PercentileEncodingAnalyzer"><code class="docutils literal notranslate"><span class="pre">PercentileEncodingAnalyzer</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/visualization_tools.html">Visualization Tools</a><ul>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/visualization_tools.html#aimet_torch.v2.visualization_tools.visualize_stats"><code class="docutils literal notranslate"><span class="pre">visualize_stats()</span></code></a></li>
 </ul>
 </li>
-<li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/visualization_tools.html">Visualization Tools</a></li>
 </ul>
 </li>
 </ul>
@@ -403,31 +559,102 @@
 </li>
 <li class="toctree-l3"><a class="reference internal" href="torch_compress.html">PyTorch Model Compression API</a><ul>
 <li class="toctree-l4"><a class="reference internal" href="torch_compress.html#introduction">Introduction</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#top-level-api-for-compression">Top-level API for Compression</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#top-level-api-for-compression">Top-level API for Compression</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.compress.ModelCompressor"><code class="docutils literal notranslate"><span class="pre">ModelCompressor</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.compress.ModelCompressor.compress_model"><code class="docutils literal notranslate"><span class="pre">ModelCompressor.compress_model()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_compress.html#greedy-selection-parameters">Greedy Selection Parameters</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_common.defs.GreedySelectionParameters"><code class="docutils literal notranslate"><span class="pre">GreedySelectionParameters</span></code></a></li>
 </ul>
 </li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#spatial-svd-configuration">Spatial SVD Configuration</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#weight-svd-configuration">Weight SVD Configuration</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#channel-pruning-configuration">Channel Pruning Configuration</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#configuration-definitions">Configuration Definitions</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#spatial-svd-configuration">Spatial SVD Configuration</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.AutoModeParams"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.AutoModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.ManualModeParams"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.ManualModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.Mode"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.Mode.auto"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode.auto</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.Mode.manual"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode.manual</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#weight-svd-configuration">Weight SVD Configuration</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.AutoModeParams"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.AutoModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.ManualModeParams"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.ManualModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.Mode"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.Mode</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.Mode.auto"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.Mode.auto</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.Mode.manual"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.Mode.manual</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#channel-pruning-configuration">Channel Pruning Configuration</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.AutoModeParams"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.AutoModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.ManualModeParams"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.ManualModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.Mode"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.Mode</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.Mode.auto"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.Mode.auto</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.Mode.manual"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.Mode.manual</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#configuration-definitions">Configuration Definitions</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ModuleCompRatioPair"><code class="docutils literal notranslate"><span class="pre">ModuleCompRatioPair</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_compress.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="torch_visualization_compression.html">PyTorch Model Visualization API for Compression</a><ul>
-<li class="toctree-l4"><a class="reference internal" href="torch_visualization_compression.html#top-level-api-compression">Top-level API Compression</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_visualization_compression.html#top-level-api-compression">Top-level API Compression</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_visualization_compression.html#aimet_torch.visualize_serialized_data.VisualizeCompression"><code class="docutils literal notranslate"><span class="pre">VisualizeCompression</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_visualization_compression.html#aimet_torch.visualize_serialized_data.VisualizeCompression.display_eval_scores"><code class="docutils literal notranslate"><span class="pre">VisualizeCompression.display_eval_scores()</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_visualization_compression.html#aimet_torch.visualize_serialized_data.VisualizeCompression.display_comp_ratio_plot"><code class="docutils literal notranslate"><span class="pre">VisualizeCompression.display_comp_ratio_plot()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_visualization_compression.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="torch_visualization_quantization.html">PyTorch Model Visualization API for Quantization</a><ul>
-<li class="toctree-l4"><a class="reference internal" href="torch_visualization_quantization.html#top-level-api-quantization">Top-level API Quantization</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_visualization_quantization.html#top-level-api-quantization">Top-level API Quantization</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_visualization_quantization.html#aimet_torch.visualize_model.visualize_relative_weight_ranges_to_identify_problematic_layers"><code class="docutils literal notranslate"><span class="pre">visualize_relative_weight_ranges_to_identify_problematic_layers()</span></code></a></li>
+<li class="toctree-l5"><a class="reference internal" href="torch_visualization_quantization.html#aimet_torch.visualize_model.visualize_weight_ranges"><code class="docutils literal notranslate"><span class="pre">visualize_weight_ranges()</span></code></a></li>
+<li class="toctree-l5"><a class="reference internal" href="torch_visualization_quantization.html#aimet_torch.visualize_model.visualize_changes_after_optimization"><code class="docutils literal notranslate"><span class="pre">visualize_changes_after_optimization()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_visualization_quantization.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="torch_layer_output_generation.html">PyTorch Debug API</a><ul>
-<li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#top-level-api">Top-level API</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#enum-definition">Enum Definition</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.LayerOutputUtil"><code class="docutils literal notranslate"><span class="pre">LayerOutputUtil</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.LayerOutputUtil.generate_layer_outputs"><code class="docutils literal notranslate"><span class="pre">LayerOutputUtil.generate_layer_outputs()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#enum-definition">Enum Definition</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.NamingScheme"><code class="docutils literal notranslate"><span class="pre">NamingScheme</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.NamingScheme.ONNX"><code class="docutils literal notranslate"><span class="pre">NamingScheme.ONNX</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.NamingScheme.PYTORCH"><code class="docutils literal notranslate"><span class="pre">NamingScheme.PYTORCH</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.NamingScheme.TORCHSCRIPT"><code class="docutils literal notranslate"><span class="pre">NamingScheme.TORCHSCRIPT</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#code-example">Code Example</a></li>
 </ul>
 </li>
@@ -437,27 +664,49 @@
 <li class="toctree-l3"><a class="reference internal" href="keras_quantization.html">TensorFlow Model Quantization API</a><ul>
 <li class="toctree-l4"><a class="reference internal" href="keras_model_guidelines.html"> Model Guidelines</a></li>
 <li class="toctree-l4"><a class="reference internal" href="keras_model_preparer.html"> Model Preparer API</a><ul>
-<li class="toctree-l5"><a class="reference internal" href="keras_model_preparer.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_model_preparer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_model_preparer.html#aimet_tensorflow.keras.model_preparer.prepare_model"><code class="docutils literal notranslate"><span class="pre">prepare_model()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_model_preparer.html#code-examples">Code Examples</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_model_preparer.html#limitations">Limitations</a></li>
 </ul>
 </li>
 <li class="toctree-l4"><a class="reference internal" href="keras_quant_analyzer.html"> Quant Analyzer API</a><ul>
-<li class="toctree-l5"><a class="reference internal" href="keras_quant_analyzer.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_quant_analyzer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_quant_analyzer.html#aimet_tensorflow.keras.quant_analyzer.QuantAnalyzer"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="keras_quant_analyzer.html#aimet_tensorflow.keras.quant_analyzer.QuantAnalyzer.analyze"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.analyze()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_quant_analyzer.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l4"><a class="reference internal" href="keras_quantsim.html"> Quantization Simulation API</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="keras_quantsim.html#user-guide-link">User Guide Link</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_quantsim.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_quantsim.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_quantsim.html#aimet_tensorflow.keras.quantsim.QuantizationSimModel"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="keras_quantsim.html#aimet_tensorflow.keras.quantsim.QuantizationSimModel.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel.compute_encodings()</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="keras_quantsim.html#aimet_tensorflow.keras.quantsim.QuantizationSimModel.export"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel.export()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_quantsim.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l4"><a class="reference internal" href="keras_adaround.html"> Adaptive Rounding API</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#examples-notebook-link">Examples Notebook Link</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#top-level-api">Top-level API</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#adaround-parameters">Adaround Parameters</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_adaround.html#aimet_tensorflow.keras.adaround_weight.Adaround.apply_adaround"><code class="docutils literal notranslate"><span class="pre">apply_adaround()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#adaround-parameters">Adaround Parameters</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_adaround.html#aimet_tensorflow.keras.adaround_weight.AdaroundParameters"><code class="docutils literal notranslate"><span class="pre">AdaroundParameters</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#enum-definition">Enum Definition</a><ul>
 <li class="toctree-l6"><a class="reference internal" href="keras_adaround.html#aimet_common.defs.QuantScheme"><code class="docutils literal notranslate"><span class="pre">QuantScheme</span></code></a><ul>
 <li class="toctree-l7"><a class="reference internal" href="keras_adaround.html#aimet_common.defs.QuantScheme.post_training_percentile"><code class="docutils literal notranslate"><span class="pre">QuantScheme.post_training_percentile</span></code></a></li>
@@ -476,15 +725,34 @@
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#introduction">Introduction</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#cross-layer-equalization-api">Cross Layer Equalization API</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#cross-layer-equalization-api">Cross Layer Equalization API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_cross_layer_equalization.html#aimet_tensorflow.keras.cross_layer_equalization.equalize_model"><code class="docutils literal notranslate"><span class="pre">equalize_model()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#code-example">Code Example</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#primitive-apis">Primitive APIs</a><ul>
 <li class="toctree-l6"><a class="reference internal" href="keras_primitive_apis_cle.html">Primitive APIs for Cross Layer Equalization</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#introduction">Introduction</a></li>
-<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#higher-level-apis-for-cross-layer-equalization">Higher Level APIs for Cross Layer Equalization</a></li>
+<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#higher-level-apis-for-cross-layer-equalization">Higher Level APIs for Cross Layer Equalization</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.batch_norm_fold.fold_all_batch_norms"><code class="docutils literal notranslate"><span class="pre">fold_all_batch_norms()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.CrossLayerScaling.scale_model"><code class="docutils literal notranslate"><span class="pre">scale_model()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.HighBiasFold.bias_fold"><code class="docutils literal notranslate"><span class="pre">bias_fold()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#code-examples-for-higher-level-apis">Code Examples for Higher Level APIs</a></li>
-<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#lower-level-apis-for-cross-layer-equalization">Lower Level APIs for Cross Layer Equalization</a></li>
-<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#custom-datatype-used">Custom Datatype used</a></li>
+<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#lower-level-apis-for-cross-layer-equalization">Lower Level APIs for Cross Layer Equalization</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.batch_norm_fold.fold_given_batch_norms"><code class="docutils literal notranslate"><span class="pre">fold_given_batch_norms()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.CrossLayerScaling.scale_cls_sets"><code class="docutils literal notranslate"><span class="pre">scale_cls_sets()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#id0"><code class="docutils literal notranslate"><span class="pre">bias_fold()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#custom-datatype-used">Custom Datatype used</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.ClsSetInfo"><code class="docutils literal notranslate"><span class="pre">ClsSetInfo</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.ClsSetInfo.ClsSetLayerPairInfo"><code class="docutils literal notranslate"><span class="pre">ClsSetInfo.ClsSetLayerPairInfo</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#code-example-for-lower-level-apis">Code Example for Lower level APIs</a></li>
 <li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#example-helper-methods-to-perform-cle-in-manual-mode">Example helper methods to perform CLE in manual mode</a></li>
 </ul>
@@ -496,7 +764,11 @@
 <li class="toctree-l4"><a class="reference internal" href="keras_batchnorm_re_estimation.html"> BN Re-estimation APIs</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#introduction">Introduction</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#top-level-apis">Top-level APIs</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#top-level-apis">Top-level APIs</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_batchnorm_re_estimation.html#aimet_tensorflow.keras.bn_reestimation.reestimate_bn_stats"><code class="docutils literal notranslate"><span class="pre">reestimate_bn_stats()</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="keras_batchnorm_re_estimation.html#aimet_tensorflow.keras.batch_norm_fold.fold_all_batch_norms_to_scale"><code class="docutils literal notranslate"><span class="pre">fold_all_batch_norms_to_scale()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#code-example">Code Example</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#limitations">Limitations</a></li>
 </ul>
@@ -504,15 +776,39 @@
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="keras_layer_output_generation.html">TensorFlow Debug API</a><ul>
-<li class="toctree-l4"><a class="reference internal" href="keras_layer_output_generation.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l4"><a class="reference internal" href="keras_layer_output_generation.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="keras_layer_output_generation.html#aimet_tensorflow.keras.layer_output_utils.LayerOutputUtil"><code class="docutils literal notranslate"><span class="pre">LayerOutputUtil</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_layer_output_generation.html#aimet_tensorflow.keras.layer_output_utils.LayerOutputUtil.generate_layer_outputs"><code class="docutils literal notranslate"><span class="pre">LayerOutputUtil.generate_layer_outputs()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="keras_layer_output_generation.html#code-example">Code Example</a></li>
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="keras_compression.html">TensorFlow Model Compression API</a><ul>
 <li class="toctree-l4"><a class="reference internal" href="keras_compression.html#introduction">Introduction</a></li>
-<li class="toctree-l4"><a class="reference internal" href="keras_compression.html#top-level-api-for-compression">Top-level API for Compression</a></li>
+<li class="toctree-l4"><a class="reference internal" href="keras_compression.html#top-level-api-for-compression">Top-level API for Compression</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.compress.ModelCompressor"><code class="docutils literal notranslate"><span class="pre">ModelCompressor</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.compress.ModelCompressor.compress_model"><code class="docutils literal notranslate"><span class="pre">ModelCompressor.compress_model()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="keras_compression.html#greedy-selection-parameters">Greedy Selection Parameters</a></li>
-<li class="toctree-l4"><a class="reference internal" href="keras_compression.html#spatial-svd-configuration">Spatial SVD Configuration</a></li>
+<li class="toctree-l4"><a class="reference internal" href="keras_compression.html#spatial-svd-configuration">Spatial SVD Configuration</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.AutoModeParams"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.AutoModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.ManualModeParams"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.ManualModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.Mode"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.Mode.auto"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode.auto</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.Mode.manual"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode.manual</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="keras_compression.html#configuration-definitions">Configuration Definitions</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="keras_compression.html#aimet_common.defs.CostMetric"><code class="docutils literal notranslate"><span class="pre">CostMetric</span></code></a><ul>
 <li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_common.defs.CostMetric.mac"><code class="docutils literal notranslate"><span class="pre">CostMetric.mac</span></code></a></li>
@@ -525,6 +821,7 @@
 <li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_common.defs.CompressionScheme.weight_svd"><code class="docutils literal notranslate"><span class="pre">CompressionScheme.weight_svd</span></code></a></li>
 </ul>
 </li>
+<li class="toctree-l5"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.ModuleCompRatioPair"><code class="docutils literal notranslate"><span class="pre">ModuleCompRatioPair</span></code></a></li>
 </ul>
 </li>
 <li class="toctree-l4"><a class="reference internal" href="keras_compression.html#code-examples">Code Examples</a></li>
diff --git a/releases/1.35.1/api_docs/onnx_quantization.html b/releases/1.35.1/api_docs/onnx_quantization.html
index d77a531..7bb9562 100644
--- a/releases/1.35.1/api_docs/onnx_quantization.html
+++ b/releases/1.35.1/api_docs/onnx_quantization.html
@@ -243,9 +243,15 @@
 <li class="toctree-l4"><a class="reference internal" href="torch_quantization.html#aimet-torch">aimet_torch</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="torch_quantization.html#api-reference">API Reference</a><ul>
 <li class="toctree-l6"><a class="reference internal" href="torch_model_guidelines.html"> Model Guidelines</a></li>
-<li class="toctree-l6"><a class="reference internal" href="torch_architecture_checker.html"> Architecture Checker API</a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_architecture_checker.html"> Architecture Checker API</a><ul>
+<li class="toctree-l7"><a class="reference internal" href="torch_architecture_checker.html#aimet_torch.arch_checker.arch_checker.ArchChecker.check_model_arch"><code class="docutils literal notranslate"><span class="pre">check_model_arch()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l6"><a class="reference internal" href="torch_model_preparer.html"> Model Preparer API</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="torch_model_preparer.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_model_preparer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_model_preparer.html#aimet_torch.model_preparer.prepare_model"><code class="docutils literal notranslate"><span class="pre">prepare_model()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_model_preparer.html#code-examples">Code Examples</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_model_preparer.html#limitations-of-torch-fx-symbolic-trace-api">Limitations of torch.fx symbolic trace API</a></li>
 </ul>
@@ -255,10 +261,23 @@
 <li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.enable_per_layer_mse_loss"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.enable_per_layer_mse_loss()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.analyze"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.analyze()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_common.utils.CallbackFunc"><code class="docutils literal notranslate"><span class="pre">CallbackFunc</span></code></a></li>
 </ul>
 </li>
-<li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#run-specific-utility">Run specific utility</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#run-specific-utility">Run specific utility</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.check_model_sensitivity_to_quantization"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.check_model_sensitivity_to_quantization()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.perform_per_layer_analysis_by_enabling_quant_wrappers"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.perform_per_layer_analysis_by_enabling_quant_wrappers()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.perform_per_layer_analysis_by_disabling_quant_wrappers"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.perform_per_layer_analysis_by_disabling_quant_wrappers()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.export_per_layer_encoding_min_max_range"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.export_per_layer_encoding_min_max_range()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.export_per_layer_stats_histogram"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.export_per_layer_stats_histogram()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.export_per_layer_mse_loss"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.export_per_layer_mse_loss()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
@@ -266,7 +285,16 @@
 <li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#guidelines">Guidelines</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.QuantizationSimModel"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.QuantizationSimModel.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel.compute_encodings()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.QuantizationSimModel.export"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel.export()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.save_checkpoint"><code class="docutils literal notranslate"><span class="pre">quantsim.save_checkpoint()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.load_checkpoint"><code class="docutils literal notranslate"><span class="pre">quantsim.load_checkpoint()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#enum-definition">Enum Definition</a><ul>
 <li class="toctree-l8"><a class="reference internal" href="torch_quantsim.html#aimet_common.defs.QuantScheme"><code class="docutils literal notranslate"><span class="pre">QuantScheme</span></code></a><ul>
 <li class="toctree-l9"><a class="reference internal" href="torch_quantsim.html#aimet_common.defs.QuantScheme.post_training_percentile"><code class="docutils literal notranslate"><span class="pre">QuantScheme.post_training_percentile</span></code></a></li>
@@ -284,8 +312,14 @@
 <li class="toctree-l6"><a class="reference internal" href="torch_adaround.html"> Adaptive Rounding API</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#examples-notebook-link">Examples Notebook Link</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#top-level-api">Top-level API</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#adaround-parameters">Adaround Parameters</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_adaround.html#aimet_torch.v1.adaround.adaround_weight.Adaround.apply_adaround"><code class="docutils literal notranslate"><span class="pre">apply_adaround()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#adaround-parameters">Adaround Parameters</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_adaround.html#aimet_torch.v1.adaround.adaround_weight.AdaroundParameters"><code class="docutils literal notranslate"><span class="pre">AdaroundParameters</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#enum-definition">Enum Definition</a><ul>
 <li class="toctree-l8"><a class="reference internal" href="torch_adaround.html#aimet_common.defs.QuantScheme"><code class="docutils literal notranslate"><span class="pre">QuantScheme</span></code></a><ul>
 <li class="toctree-l9"><a class="reference internal" href="torch_adaround.html#aimet_common.defs.QuantScheme.post_training_percentile"><code class="docutils literal notranslate"><span class="pre">QuantScheme.post_training_percentile</span></code></a></li>
@@ -304,15 +338,31 @@
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#introduction">Introduction</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#cross-layer-equalization-api">Cross Layer Equalization API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#cross-layer-equalization-api">Cross Layer Equalization API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_cross_layer_equalization.html#aimet_torch.cross_layer_equalization.equalize_model"><code class="docutils literal notranslate"><span class="pre">equalize_model()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#code-example">Code Example</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#primitive-apis">Primitive APIs</a><ul>
 <li class="toctree-l8"><a class="reference internal" href="torch_primitive_apis_cle.html">Primitive APIs for Cross Layer Equalization</a><ul>
 <li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#introduction">Introduction</a></li>
-<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#clssetinfo-definition">ClsSetInfo Definition</a></li>
-<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#higher-level-apis-for-cross-layer-equalization">Higher Level APIs for Cross Layer Equalization</a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#clssetinfo-definition">ClsSetInfo Definition</a><ul>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.cross_layer_equalization.ClsSetInfo"><code class="docutils literal notranslate"><span class="pre">ClsSetInfo</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#higher-level-apis-for-cross-layer-equalization">Higher Level APIs for Cross Layer Equalization</a><ul>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.batch_norm_fold.fold_all_batch_norms"><code class="docutils literal notranslate"><span class="pre">fold_all_batch_norms()</span></code></a></li>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.cross_layer_equalization.CrossLayerScaling.scale_model"><code class="docutils literal notranslate"><span class="pre">scale_model()</span></code></a></li>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.cross_layer_equalization.HighBiasFold.bias_fold"><code class="docutils literal notranslate"><span class="pre">bias_fold()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#code-examples-for-higher-level-apis">Code Examples for Higher Level APIs</a></li>
-<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#lower-level-apis-for-cross-layer-equalization">Lower Level APIs for Cross Layer Equalization</a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#lower-level-apis-for-cross-layer-equalization">Lower Level APIs for Cross Layer Equalization</a><ul>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.batch_norm_fold.fold_given_batch_norms"><code class="docutils literal notranslate"><span class="pre">fold_given_batch_norms()</span></code></a></li>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.cross_layer_equalization.CrossLayerScaling.scale_cls_sets"><code class="docutils literal notranslate"><span class="pre">scale_cls_sets()</span></code></a></li>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#id0"><code class="docutils literal notranslate"><span class="pre">bias_fold()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#code-examples-for-lower-level-apis">Code Examples for Lower Level APIs</a></li>
 </ul>
 </li>
@@ -322,7 +372,10 @@
 </li>
 <li class="toctree-l6"><a class="reference internal" href="torch_bias_correction.html"> Bias Correction API</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#user-guide-link">User Guide Link</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#bias-correction-api">Bias Correction API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#bias-correction-api">Bias Correction API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_bias_correction.html#aimet_torch.bias_correction.correct_bias"><code class="docutils literal notranslate"><span class="pre">correct_bias()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#convbninfotype">ConvBnInfoType</a><ul>
 <li class="toctree-l8"><a class="reference internal" href="torch_bias_correction.html#aimet_common.bias_correction.ConvBnInfoType"><code class="docutils literal notranslate"><span class="pre">ConvBnInfoType</span></code></a></li>
 </ul>
@@ -336,7 +389,10 @@
 </li>
 </ul>
 </li>
-<li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#quantization-params">Quantization Params</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#quantization-params">Quantization Params</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_bias_correction.html#aimet_torch.v1.quantsim.QuantParams"><code class="docutils literal notranslate"><span class="pre">QuantParams</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#code-example-1-empirical-bias-correction">Code Example #1 Empirical Bias Correction</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#code-example-2-analytical-empirical-bias-correction">Code Example #2 Analytical + Empirical Bias correction</a></li>
 </ul>
@@ -344,21 +400,46 @@
 <li class="toctree-l6"><a class="reference internal" href="torch_auto_quant.html"> AutoQuant API</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#examples-notebook-link">Examples Notebook Link</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_auto_quant.html#aimet_torch.v1.auto_quant.AutoQuant"><code class="docutils literal notranslate"><span class="pre">AutoQuant</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="torch_batchnorm_re_estimation.html"> BN Re-estimation APIs</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#introduction">Introduction</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#top-level-apis">Top-level APIs</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#top-level-apis">Top-level APIs</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_batchnorm_re_estimation.html#aimet_torch.bn_reestimation.reestimate_bn_stats"><code class="docutils literal notranslate"><span class="pre">reestimate_bn_stats()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_batchnorm_re_estimation.html#aimet_torch.batch_norm_fold.fold_all_batch_norms_to_scale"><code class="docutils literal notranslate"><span class="pre">fold_all_batch_norms_to_scale()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#code-example-bn-reestimation">Code Example - BN-Reestimation</a></li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="torch_multi_gpu.html"> Multi-GPU guidelines</a></li>
 <li class="toctree-l6"><a class="reference internal" href="torch_peft_lora.html"> PEFT LoRA APIs</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_peft_lora.html#user-flow">User flow</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_peft_lora.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_peft_lora.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.AdapterMetaData"><code class="docutils literal notranslate"><span class="pre">AdapterMetaData</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.replace_lora_layers_with_quantizable_layers"><code class="docutils literal notranslate"><span class="pre">peft.replace_lora_layers_with_quantizable_layers()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.track_lora_meta_data"><code class="docutils literal notranslate"><span class="pre">peft.track_lora_meta_data()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.disable_lora_adapters"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.disable_lora_adapters()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.enable_adapter_and_load_weights"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.enable_adapter_and_load_weights()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.export_adapter_weights"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.export_adapter_weights()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.freeze_base_model"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.freeze_base_model()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.freeze_base_model_activation_quantizers"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.freeze_base_model_activation_quantizers()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.freeze_base_model_param_quantizers"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.freeze_base_model_param_quantizers()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.get_fp_lora_layer"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.get_fp_lora_layer()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.get_quantized_lora_layer"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.get_quantized_lora_layer()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.quantize_lora_scale_with_fixed_range"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.quantize_lora_scale_with_fixed_range()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.set_bitwidth_for_lora_adapters"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.set_bitwidth_for_lora_adapters()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 </ul>
 </li>
 </ul>
@@ -370,31 +451,106 @@
 <li class="toctree-l5"><a class="reference internal" href="torch_quantization.html#backwards-compatibility">Backwards Compatibility</a></li>
 <li class="toctree-l5"><a class="reference internal" href="torch_quantization.html#id1">API Reference</a><ul>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/quantized_modules.html">Quantized Modules</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.input_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.input_quantizers</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.output_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.output_quantizers</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.param_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.param_quantizers</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.__quant_init__"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.__quant_init__()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.compute_encodings()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.forward"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.forward()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#configuration">Configuration</a></li>
 <li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#computing-encodings">Computing Encodings</a></li>
 <li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#quantized-module-classes">Quantized Module Classes</a></li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/quantizer.html">Quantizers</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantizer.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantizer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase"><code class="docutils literal notranslate"><span class="pre">QuantizerBase</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.allow_overwrite"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.allow_overwrite()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.compute_encodings()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.get_encoding"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.get_encoding()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.get_legacy_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.get_legacy_encodings()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.is_initialized"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.is_initialized()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.register_quantization_parameter"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.register_quantization_parameter()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.set_legacy_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.set_legacy_encodings()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizeDequantize"><code class="docutils literal notranslate"><span class="pre">QuantizeDequantize</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizeDequantize.forward"><code class="docutils literal notranslate"><span class="pre">QuantizeDequantize.forward()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.Quantize"><code class="docutils literal notranslate"><span class="pre">Quantize</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.Quantize.forward"><code class="docutils literal notranslate"><span class="pre">Quantize.forward()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html">QuantizationMixin</a><ul>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin</span></code></a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.input_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.input_quantizers</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.output_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.output_quantizers</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.param_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.param_quantizers</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.forward"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.forward()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.__quant_init__"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.__quant_init__()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.set_kernel"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.set_kernel()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.set_default_kernel"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.set_default_kernel()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.compute_encodings()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.from_module"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.from_module()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.get_default_kernel"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.get_default_kernel()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.get_kernel"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.get_kernel()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.implements"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.implements()</span></code></a></li>
+</ul>
+</li>
 </ul>
 </li>
-<li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html">QuantizationMixin</a></li>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html">quantization.affine</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#classes">Classes</a></li>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#functions">Functions</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#classes">Classes</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.Quantize"><code class="docutils literal notranslate"><span class="pre">Quantize</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.QuantizeDequantize"><code class="docutils literal notranslate"><span class="pre">QuantizeDequantize</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#functions">Functions</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.quantize"><code class="docutils literal notranslate"><span class="pre">quantize()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.quantize_dequantize"><code class="docutils literal notranslate"><span class="pre">quantize_dequantize()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.dequantize"><code class="docutils literal notranslate"><span class="pre">dequantize()</span></code></a></li>
+</ul>
+</li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html">quantization.float</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html#classes">Classes</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html#classes">Classes</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html#aimet_torch.v2.quantization.float.FloatQuantizeDequantize"><code class="docutils literal notranslate"><span class="pre">FloatQuantizeDequantize</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html#aimet_torch.v2.quantization.float.QuantizeDequantize"><code class="docutils literal notranslate"><span class="pre">QuantizeDequantize</span></code></a></li>
+</ul>
+</li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/encoding_analyzer.html">Encoding Analyzers</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#variants">Variants</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer"><code class="docutils literal notranslate"><span class="pre">EncodingAnalyzer</span></code></a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.compute_encodings"><code class="docutils literal notranslate"><span class="pre">EncodingAnalyzer.compute_encodings()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.reset_stats"><code class="docutils literal notranslate"><span class="pre">EncodingAnalyzer.reset_stats()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.update_stats"><code class="docutils literal notranslate"><span class="pre">EncodingAnalyzer.update_stats()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#variants">Variants</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.MinMaxEncodingAnalyzer"><code class="docutils literal notranslate"><span class="pre">MinMaxEncodingAnalyzer</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.SqnrEncodingAnalyzer"><code class="docutils literal notranslate"><span class="pre">SqnrEncodingAnalyzer</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.PercentileEncodingAnalyzer"><code class="docutils literal notranslate"><span class="pre">PercentileEncodingAnalyzer</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/visualization_tools.html">Visualization Tools</a><ul>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/visualization_tools.html#aimet_torch.v2.visualization_tools.visualize_stats"><code class="docutils literal notranslate"><span class="pre">visualize_stats()</span></code></a></li>
 </ul>
 </li>
-<li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/visualization_tools.html">Visualization Tools</a></li>
 </ul>
 </li>
 </ul>
@@ -403,31 +559,102 @@
 </li>
 <li class="toctree-l3"><a class="reference internal" href="torch_compress.html">PyTorch Model Compression API</a><ul>
 <li class="toctree-l4"><a class="reference internal" href="torch_compress.html#introduction">Introduction</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#top-level-api-for-compression">Top-level API for Compression</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#top-level-api-for-compression">Top-level API for Compression</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.compress.ModelCompressor"><code class="docutils literal notranslate"><span class="pre">ModelCompressor</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.compress.ModelCompressor.compress_model"><code class="docutils literal notranslate"><span class="pre">ModelCompressor.compress_model()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_compress.html#greedy-selection-parameters">Greedy Selection Parameters</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_common.defs.GreedySelectionParameters"><code class="docutils literal notranslate"><span class="pre">GreedySelectionParameters</span></code></a></li>
 </ul>
 </li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#spatial-svd-configuration">Spatial SVD Configuration</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#weight-svd-configuration">Weight SVD Configuration</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#channel-pruning-configuration">Channel Pruning Configuration</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#configuration-definitions">Configuration Definitions</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#spatial-svd-configuration">Spatial SVD Configuration</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.AutoModeParams"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.AutoModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.ManualModeParams"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.ManualModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.Mode"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.Mode.auto"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode.auto</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.Mode.manual"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode.manual</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#weight-svd-configuration">Weight SVD Configuration</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.AutoModeParams"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.AutoModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.ManualModeParams"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.ManualModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.Mode"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.Mode</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.Mode.auto"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.Mode.auto</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.Mode.manual"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.Mode.manual</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#channel-pruning-configuration">Channel Pruning Configuration</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.AutoModeParams"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.AutoModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.ManualModeParams"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.ManualModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.Mode"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.Mode</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.Mode.auto"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.Mode.auto</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.Mode.manual"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.Mode.manual</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#configuration-definitions">Configuration Definitions</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ModuleCompRatioPair"><code class="docutils literal notranslate"><span class="pre">ModuleCompRatioPair</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_compress.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="torch_visualization_compression.html">PyTorch Model Visualization API for Compression</a><ul>
-<li class="toctree-l4"><a class="reference internal" href="torch_visualization_compression.html#top-level-api-compression">Top-level API Compression</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_visualization_compression.html#top-level-api-compression">Top-level API Compression</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_visualization_compression.html#aimet_torch.visualize_serialized_data.VisualizeCompression"><code class="docutils literal notranslate"><span class="pre">VisualizeCompression</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_visualization_compression.html#aimet_torch.visualize_serialized_data.VisualizeCompression.display_eval_scores"><code class="docutils literal notranslate"><span class="pre">VisualizeCompression.display_eval_scores()</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_visualization_compression.html#aimet_torch.visualize_serialized_data.VisualizeCompression.display_comp_ratio_plot"><code class="docutils literal notranslate"><span class="pre">VisualizeCompression.display_comp_ratio_plot()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_visualization_compression.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="torch_visualization_quantization.html">PyTorch Model Visualization API for Quantization</a><ul>
-<li class="toctree-l4"><a class="reference internal" href="torch_visualization_quantization.html#top-level-api-quantization">Top-level API Quantization</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_visualization_quantization.html#top-level-api-quantization">Top-level API Quantization</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_visualization_quantization.html#aimet_torch.visualize_model.visualize_relative_weight_ranges_to_identify_problematic_layers"><code class="docutils literal notranslate"><span class="pre">visualize_relative_weight_ranges_to_identify_problematic_layers()</span></code></a></li>
+<li class="toctree-l5"><a class="reference internal" href="torch_visualization_quantization.html#aimet_torch.visualize_model.visualize_weight_ranges"><code class="docutils literal notranslate"><span class="pre">visualize_weight_ranges()</span></code></a></li>
+<li class="toctree-l5"><a class="reference internal" href="torch_visualization_quantization.html#aimet_torch.visualize_model.visualize_changes_after_optimization"><code class="docutils literal notranslate"><span class="pre">visualize_changes_after_optimization()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_visualization_quantization.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="torch_layer_output_generation.html">PyTorch Debug API</a><ul>
-<li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#top-level-api">Top-level API</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#enum-definition">Enum Definition</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.LayerOutputUtil"><code class="docutils literal notranslate"><span class="pre">LayerOutputUtil</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.LayerOutputUtil.generate_layer_outputs"><code class="docutils literal notranslate"><span class="pre">LayerOutputUtil.generate_layer_outputs()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#enum-definition">Enum Definition</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.NamingScheme"><code class="docutils literal notranslate"><span class="pre">NamingScheme</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.NamingScheme.ONNX"><code class="docutils literal notranslate"><span class="pre">NamingScheme.ONNX</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.NamingScheme.PYTORCH"><code class="docutils literal notranslate"><span class="pre">NamingScheme.PYTORCH</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.NamingScheme.TORCHSCRIPT"><code class="docutils literal notranslate"><span class="pre">NamingScheme.TORCHSCRIPT</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#code-example">Code Example</a></li>
 </ul>
 </li>
@@ -437,27 +664,49 @@
 <li class="toctree-l3"><a class="reference internal" href="keras_quantization.html">TensorFlow Model Quantization API</a><ul>
 <li class="toctree-l4"><a class="reference internal" href="keras_model_guidelines.html"> Model Guidelines</a></li>
 <li class="toctree-l4"><a class="reference internal" href="keras_model_preparer.html"> Model Preparer API</a><ul>
-<li class="toctree-l5"><a class="reference internal" href="keras_model_preparer.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_model_preparer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_model_preparer.html#aimet_tensorflow.keras.model_preparer.prepare_model"><code class="docutils literal notranslate"><span class="pre">prepare_model()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_model_preparer.html#code-examples">Code Examples</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_model_preparer.html#limitations">Limitations</a></li>
 </ul>
 </li>
 <li class="toctree-l4"><a class="reference internal" href="keras_quant_analyzer.html"> Quant Analyzer API</a><ul>
-<li class="toctree-l5"><a class="reference internal" href="keras_quant_analyzer.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_quant_analyzer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_quant_analyzer.html#aimet_tensorflow.keras.quant_analyzer.QuantAnalyzer"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="keras_quant_analyzer.html#aimet_tensorflow.keras.quant_analyzer.QuantAnalyzer.analyze"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.analyze()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_quant_analyzer.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l4"><a class="reference internal" href="keras_quantsim.html"> Quantization Simulation API</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="keras_quantsim.html#user-guide-link">User Guide Link</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_quantsim.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_quantsim.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_quantsim.html#aimet_tensorflow.keras.quantsim.QuantizationSimModel"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="keras_quantsim.html#aimet_tensorflow.keras.quantsim.QuantizationSimModel.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel.compute_encodings()</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="keras_quantsim.html#aimet_tensorflow.keras.quantsim.QuantizationSimModel.export"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel.export()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_quantsim.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l4"><a class="reference internal" href="keras_adaround.html"> Adaptive Rounding API</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#examples-notebook-link">Examples Notebook Link</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#top-level-api">Top-level API</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#adaround-parameters">Adaround Parameters</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_adaround.html#aimet_tensorflow.keras.adaround_weight.Adaround.apply_adaround"><code class="docutils literal notranslate"><span class="pre">apply_adaround()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#adaround-parameters">Adaround Parameters</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_adaround.html#aimet_tensorflow.keras.adaround_weight.AdaroundParameters"><code class="docutils literal notranslate"><span class="pre">AdaroundParameters</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#enum-definition">Enum Definition</a><ul>
 <li class="toctree-l6"><a class="reference internal" href="keras_adaround.html#aimet_common.defs.QuantScheme"><code class="docutils literal notranslate"><span class="pre">QuantScheme</span></code></a><ul>
 <li class="toctree-l7"><a class="reference internal" href="keras_adaround.html#aimet_common.defs.QuantScheme.post_training_percentile"><code class="docutils literal notranslate"><span class="pre">QuantScheme.post_training_percentile</span></code></a></li>
@@ -476,15 +725,34 @@
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#introduction">Introduction</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#cross-layer-equalization-api">Cross Layer Equalization API</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#cross-layer-equalization-api">Cross Layer Equalization API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_cross_layer_equalization.html#aimet_tensorflow.keras.cross_layer_equalization.equalize_model"><code class="docutils literal notranslate"><span class="pre">equalize_model()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#code-example">Code Example</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#primitive-apis">Primitive APIs</a><ul>
 <li class="toctree-l6"><a class="reference internal" href="keras_primitive_apis_cle.html">Primitive APIs for Cross Layer Equalization</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#introduction">Introduction</a></li>
-<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#higher-level-apis-for-cross-layer-equalization">Higher Level APIs for Cross Layer Equalization</a></li>
+<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#higher-level-apis-for-cross-layer-equalization">Higher Level APIs for Cross Layer Equalization</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.batch_norm_fold.fold_all_batch_norms"><code class="docutils literal notranslate"><span class="pre">fold_all_batch_norms()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.CrossLayerScaling.scale_model"><code class="docutils literal notranslate"><span class="pre">scale_model()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.HighBiasFold.bias_fold"><code class="docutils literal notranslate"><span class="pre">bias_fold()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#code-examples-for-higher-level-apis">Code Examples for Higher Level APIs</a></li>
-<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#lower-level-apis-for-cross-layer-equalization">Lower Level APIs for Cross Layer Equalization</a></li>
-<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#custom-datatype-used">Custom Datatype used</a></li>
+<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#lower-level-apis-for-cross-layer-equalization">Lower Level APIs for Cross Layer Equalization</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.batch_norm_fold.fold_given_batch_norms"><code class="docutils literal notranslate"><span class="pre">fold_given_batch_norms()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.CrossLayerScaling.scale_cls_sets"><code class="docutils literal notranslate"><span class="pre">scale_cls_sets()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#id0"><code class="docutils literal notranslate"><span class="pre">bias_fold()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#custom-datatype-used">Custom Datatype used</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.ClsSetInfo"><code class="docutils literal notranslate"><span class="pre">ClsSetInfo</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.ClsSetInfo.ClsSetLayerPairInfo"><code class="docutils literal notranslate"><span class="pre">ClsSetInfo.ClsSetLayerPairInfo</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#code-example-for-lower-level-apis">Code Example for Lower level APIs</a></li>
 <li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#example-helper-methods-to-perform-cle-in-manual-mode">Example helper methods to perform CLE in manual mode</a></li>
 </ul>
@@ -496,7 +764,11 @@
 <li class="toctree-l4"><a class="reference internal" href="keras_batchnorm_re_estimation.html"> BN Re-estimation APIs</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#introduction">Introduction</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#top-level-apis">Top-level APIs</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#top-level-apis">Top-level APIs</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_batchnorm_re_estimation.html#aimet_tensorflow.keras.bn_reestimation.reestimate_bn_stats"><code class="docutils literal notranslate"><span class="pre">reestimate_bn_stats()</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="keras_batchnorm_re_estimation.html#aimet_tensorflow.keras.batch_norm_fold.fold_all_batch_norms_to_scale"><code class="docutils literal notranslate"><span class="pre">fold_all_batch_norms_to_scale()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#code-example">Code Example</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#limitations">Limitations</a></li>
 </ul>
@@ -504,15 +776,39 @@
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="keras_layer_output_generation.html">TensorFlow Debug API</a><ul>
-<li class="toctree-l4"><a class="reference internal" href="keras_layer_output_generation.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l4"><a class="reference internal" href="keras_layer_output_generation.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="keras_layer_output_generation.html#aimet_tensorflow.keras.layer_output_utils.LayerOutputUtil"><code class="docutils literal notranslate"><span class="pre">LayerOutputUtil</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_layer_output_generation.html#aimet_tensorflow.keras.layer_output_utils.LayerOutputUtil.generate_layer_outputs"><code class="docutils literal notranslate"><span class="pre">LayerOutputUtil.generate_layer_outputs()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="keras_layer_output_generation.html#code-example">Code Example</a></li>
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="keras_compression.html">TensorFlow Model Compression API</a><ul>
 <li class="toctree-l4"><a class="reference internal" href="keras_compression.html#introduction">Introduction</a></li>
-<li class="toctree-l4"><a class="reference internal" href="keras_compression.html#top-level-api-for-compression">Top-level API for Compression</a></li>
+<li class="toctree-l4"><a class="reference internal" href="keras_compression.html#top-level-api-for-compression">Top-level API for Compression</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.compress.ModelCompressor"><code class="docutils literal notranslate"><span class="pre">ModelCompressor</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.compress.ModelCompressor.compress_model"><code class="docutils literal notranslate"><span class="pre">ModelCompressor.compress_model()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="keras_compression.html#greedy-selection-parameters">Greedy Selection Parameters</a></li>
-<li class="toctree-l4"><a class="reference internal" href="keras_compression.html#spatial-svd-configuration">Spatial SVD Configuration</a></li>
+<li class="toctree-l4"><a class="reference internal" href="keras_compression.html#spatial-svd-configuration">Spatial SVD Configuration</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.AutoModeParams"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.AutoModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.ManualModeParams"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.ManualModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.Mode"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.Mode.auto"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode.auto</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.Mode.manual"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode.manual</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="keras_compression.html#configuration-definitions">Configuration Definitions</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="keras_compression.html#aimet_common.defs.CostMetric"><code class="docutils literal notranslate"><span class="pre">CostMetric</span></code></a><ul>
 <li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_common.defs.CostMetric.mac"><code class="docutils literal notranslate"><span class="pre">CostMetric.mac</span></code></a></li>
@@ -525,6 +821,7 @@
 <li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_common.defs.CompressionScheme.weight_svd"><code class="docutils literal notranslate"><span class="pre">CompressionScheme.weight_svd</span></code></a></li>
 </ul>
 </li>
+<li class="toctree-l5"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.ModuleCompRatioPair"><code class="docutils literal notranslate"><span class="pre">ModuleCompRatioPair</span></code></a></li>
 </ul>
 </li>
 <li class="toctree-l4"><a class="reference internal" href="keras_compression.html#code-examples">Code Examples</a></li>
diff --git a/releases/1.35.1/api_docs/onnx_quantsim.html b/releases/1.35.1/api_docs/onnx_quantsim.html
index b9e4ebd..b842a46 100644
--- a/releases/1.35.1/api_docs/onnx_quantsim.html
+++ b/releases/1.35.1/api_docs/onnx_quantsim.html
@@ -243,9 +243,15 @@
 <li class="toctree-l4"><a class="reference internal" href="torch_quantization.html#aimet-torch">aimet_torch</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="torch_quantization.html#api-reference">API Reference</a><ul>
 <li class="toctree-l6"><a class="reference internal" href="torch_model_guidelines.html"> Model Guidelines</a></li>
-<li class="toctree-l6"><a class="reference internal" href="torch_architecture_checker.html"> Architecture Checker API</a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_architecture_checker.html"> Architecture Checker API</a><ul>
+<li class="toctree-l7"><a class="reference internal" href="torch_architecture_checker.html#aimet_torch.arch_checker.arch_checker.ArchChecker.check_model_arch"><code class="docutils literal notranslate"><span class="pre">check_model_arch()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l6"><a class="reference internal" href="torch_model_preparer.html"> Model Preparer API</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="torch_model_preparer.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_model_preparer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_model_preparer.html#aimet_torch.model_preparer.prepare_model"><code class="docutils literal notranslate"><span class="pre">prepare_model()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_model_preparer.html#code-examples">Code Examples</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_model_preparer.html#limitations-of-torch-fx-symbolic-trace-api">Limitations of torch.fx symbolic trace API</a></li>
 </ul>
@@ -255,10 +261,23 @@
 <li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.enable_per_layer_mse_loss"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.enable_per_layer_mse_loss()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.analyze"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.analyze()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_common.utils.CallbackFunc"><code class="docutils literal notranslate"><span class="pre">CallbackFunc</span></code></a></li>
 </ul>
 </li>
-<li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#run-specific-utility">Run specific utility</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#run-specific-utility">Run specific utility</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.check_model_sensitivity_to_quantization"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.check_model_sensitivity_to_quantization()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.perform_per_layer_analysis_by_enabling_quant_wrappers"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.perform_per_layer_analysis_by_enabling_quant_wrappers()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.perform_per_layer_analysis_by_disabling_quant_wrappers"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.perform_per_layer_analysis_by_disabling_quant_wrappers()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.export_per_layer_encoding_min_max_range"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.export_per_layer_encoding_min_max_range()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.export_per_layer_stats_histogram"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.export_per_layer_stats_histogram()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.export_per_layer_mse_loss"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.export_per_layer_mse_loss()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
@@ -266,7 +285,16 @@
 <li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#guidelines">Guidelines</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.QuantizationSimModel"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.QuantizationSimModel.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel.compute_encodings()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.QuantizationSimModel.export"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel.export()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.save_checkpoint"><code class="docutils literal notranslate"><span class="pre">quantsim.save_checkpoint()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.load_checkpoint"><code class="docutils literal notranslate"><span class="pre">quantsim.load_checkpoint()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#enum-definition">Enum Definition</a><ul>
 <li class="toctree-l8"><a class="reference internal" href="torch_quantsim.html#aimet_common.defs.QuantScheme"><code class="docutils literal notranslate"><span class="pre">QuantScheme</span></code></a><ul>
 <li class="toctree-l9"><a class="reference internal" href="torch_quantsim.html#aimet_common.defs.QuantScheme.post_training_percentile"><code class="docutils literal notranslate"><span class="pre">QuantScheme.post_training_percentile</span></code></a></li>
@@ -284,8 +312,14 @@
 <li class="toctree-l6"><a class="reference internal" href="torch_adaround.html"> Adaptive Rounding API</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#examples-notebook-link">Examples Notebook Link</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#top-level-api">Top-level API</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#adaround-parameters">Adaround Parameters</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_adaround.html#aimet_torch.v1.adaround.adaround_weight.Adaround.apply_adaround"><code class="docutils literal notranslate"><span class="pre">apply_adaround()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#adaround-parameters">Adaround Parameters</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_adaround.html#aimet_torch.v1.adaround.adaround_weight.AdaroundParameters"><code class="docutils literal notranslate"><span class="pre">AdaroundParameters</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#enum-definition">Enum Definition</a><ul>
 <li class="toctree-l8"><a class="reference internal" href="torch_adaround.html#aimet_common.defs.QuantScheme"><code class="docutils literal notranslate"><span class="pre">QuantScheme</span></code></a><ul>
 <li class="toctree-l9"><a class="reference internal" href="torch_adaround.html#aimet_common.defs.QuantScheme.post_training_percentile"><code class="docutils literal notranslate"><span class="pre">QuantScheme.post_training_percentile</span></code></a></li>
@@ -304,15 +338,31 @@
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#introduction">Introduction</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#cross-layer-equalization-api">Cross Layer Equalization API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#cross-layer-equalization-api">Cross Layer Equalization API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_cross_layer_equalization.html#aimet_torch.cross_layer_equalization.equalize_model"><code class="docutils literal notranslate"><span class="pre">equalize_model()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#code-example">Code Example</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#primitive-apis">Primitive APIs</a><ul>
 <li class="toctree-l8"><a class="reference internal" href="torch_primitive_apis_cle.html">Primitive APIs for Cross Layer Equalization</a><ul>
 <li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#introduction">Introduction</a></li>
-<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#clssetinfo-definition">ClsSetInfo Definition</a></li>
-<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#higher-level-apis-for-cross-layer-equalization">Higher Level APIs for Cross Layer Equalization</a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#clssetinfo-definition">ClsSetInfo Definition</a><ul>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.cross_layer_equalization.ClsSetInfo"><code class="docutils literal notranslate"><span class="pre">ClsSetInfo</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#higher-level-apis-for-cross-layer-equalization">Higher Level APIs for Cross Layer Equalization</a><ul>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.batch_norm_fold.fold_all_batch_norms"><code class="docutils literal notranslate"><span class="pre">fold_all_batch_norms()</span></code></a></li>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.cross_layer_equalization.CrossLayerScaling.scale_model"><code class="docutils literal notranslate"><span class="pre">scale_model()</span></code></a></li>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.cross_layer_equalization.HighBiasFold.bias_fold"><code class="docutils literal notranslate"><span class="pre">bias_fold()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#code-examples-for-higher-level-apis">Code Examples for Higher Level APIs</a></li>
-<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#lower-level-apis-for-cross-layer-equalization">Lower Level APIs for Cross Layer Equalization</a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#lower-level-apis-for-cross-layer-equalization">Lower Level APIs for Cross Layer Equalization</a><ul>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.batch_norm_fold.fold_given_batch_norms"><code class="docutils literal notranslate"><span class="pre">fold_given_batch_norms()</span></code></a></li>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.cross_layer_equalization.CrossLayerScaling.scale_cls_sets"><code class="docutils literal notranslate"><span class="pre">scale_cls_sets()</span></code></a></li>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#id0"><code class="docutils literal notranslate"><span class="pre">bias_fold()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#code-examples-for-lower-level-apis">Code Examples for Lower Level APIs</a></li>
 </ul>
 </li>
@@ -322,7 +372,10 @@
 </li>
 <li class="toctree-l6"><a class="reference internal" href="torch_bias_correction.html"> Bias Correction API</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#user-guide-link">User Guide Link</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#bias-correction-api">Bias Correction API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#bias-correction-api">Bias Correction API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_bias_correction.html#aimet_torch.bias_correction.correct_bias"><code class="docutils literal notranslate"><span class="pre">correct_bias()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#convbninfotype">ConvBnInfoType</a><ul>
 <li class="toctree-l8"><a class="reference internal" href="torch_bias_correction.html#aimet_common.bias_correction.ConvBnInfoType"><code class="docutils literal notranslate"><span class="pre">ConvBnInfoType</span></code></a></li>
 </ul>
@@ -336,7 +389,10 @@
 </li>
 </ul>
 </li>
-<li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#quantization-params">Quantization Params</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#quantization-params">Quantization Params</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_bias_correction.html#aimet_torch.v1.quantsim.QuantParams"><code class="docutils literal notranslate"><span class="pre">QuantParams</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#code-example-1-empirical-bias-correction">Code Example #1 Empirical Bias Correction</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#code-example-2-analytical-empirical-bias-correction">Code Example #2 Analytical + Empirical Bias correction</a></li>
 </ul>
@@ -344,21 +400,46 @@
 <li class="toctree-l6"><a class="reference internal" href="torch_auto_quant.html"> AutoQuant API</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#examples-notebook-link">Examples Notebook Link</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_auto_quant.html#aimet_torch.v1.auto_quant.AutoQuant"><code class="docutils literal notranslate"><span class="pre">AutoQuant</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="torch_batchnorm_re_estimation.html"> BN Re-estimation APIs</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#introduction">Introduction</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#top-level-apis">Top-level APIs</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#top-level-apis">Top-level APIs</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_batchnorm_re_estimation.html#aimet_torch.bn_reestimation.reestimate_bn_stats"><code class="docutils literal notranslate"><span class="pre">reestimate_bn_stats()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_batchnorm_re_estimation.html#aimet_torch.batch_norm_fold.fold_all_batch_norms_to_scale"><code class="docutils literal notranslate"><span class="pre">fold_all_batch_norms_to_scale()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#code-example-bn-reestimation">Code Example - BN-Reestimation</a></li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="torch_multi_gpu.html"> Multi-GPU guidelines</a></li>
 <li class="toctree-l6"><a class="reference internal" href="torch_peft_lora.html"> PEFT LoRA APIs</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_peft_lora.html#user-flow">User flow</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_peft_lora.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_peft_lora.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.AdapterMetaData"><code class="docutils literal notranslate"><span class="pre">AdapterMetaData</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.replace_lora_layers_with_quantizable_layers"><code class="docutils literal notranslate"><span class="pre">peft.replace_lora_layers_with_quantizable_layers()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.track_lora_meta_data"><code class="docutils literal notranslate"><span class="pre">peft.track_lora_meta_data()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.disable_lora_adapters"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.disable_lora_adapters()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.enable_adapter_and_load_weights"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.enable_adapter_and_load_weights()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.export_adapter_weights"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.export_adapter_weights()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.freeze_base_model"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.freeze_base_model()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.freeze_base_model_activation_quantizers"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.freeze_base_model_activation_quantizers()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.freeze_base_model_param_quantizers"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.freeze_base_model_param_quantizers()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.get_fp_lora_layer"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.get_fp_lora_layer()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.get_quantized_lora_layer"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.get_quantized_lora_layer()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.quantize_lora_scale_with_fixed_range"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.quantize_lora_scale_with_fixed_range()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.set_bitwidth_for_lora_adapters"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.set_bitwidth_for_lora_adapters()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 </ul>
 </li>
 </ul>
@@ -370,31 +451,106 @@
 <li class="toctree-l5"><a class="reference internal" href="torch_quantization.html#backwards-compatibility">Backwards Compatibility</a></li>
 <li class="toctree-l5"><a class="reference internal" href="torch_quantization.html#id1">API Reference</a><ul>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/quantized_modules.html">Quantized Modules</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.input_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.input_quantizers</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.output_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.output_quantizers</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.param_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.param_quantizers</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.__quant_init__"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.__quant_init__()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.compute_encodings()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.forward"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.forward()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#configuration">Configuration</a></li>
 <li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#computing-encodings">Computing Encodings</a></li>
 <li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#quantized-module-classes">Quantized Module Classes</a></li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/quantizer.html">Quantizers</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantizer.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantizer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase"><code class="docutils literal notranslate"><span class="pre">QuantizerBase</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.allow_overwrite"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.allow_overwrite()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.compute_encodings()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.get_encoding"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.get_encoding()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.get_legacy_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.get_legacy_encodings()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.is_initialized"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.is_initialized()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.register_quantization_parameter"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.register_quantization_parameter()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.set_legacy_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.set_legacy_encodings()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizeDequantize"><code class="docutils literal notranslate"><span class="pre">QuantizeDequantize</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizeDequantize.forward"><code class="docutils literal notranslate"><span class="pre">QuantizeDequantize.forward()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.Quantize"><code class="docutils literal notranslate"><span class="pre">Quantize</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.Quantize.forward"><code class="docutils literal notranslate"><span class="pre">Quantize.forward()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html">QuantizationMixin</a><ul>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin</span></code></a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.input_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.input_quantizers</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.output_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.output_quantizers</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.param_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.param_quantizers</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.forward"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.forward()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.__quant_init__"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.__quant_init__()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.set_kernel"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.set_kernel()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.set_default_kernel"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.set_default_kernel()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.compute_encodings()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.from_module"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.from_module()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.get_default_kernel"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.get_default_kernel()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.get_kernel"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.get_kernel()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.implements"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.implements()</span></code></a></li>
+</ul>
+</li>
 </ul>
 </li>
-<li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html">QuantizationMixin</a></li>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html">quantization.affine</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#classes">Classes</a></li>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#functions">Functions</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#classes">Classes</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.Quantize"><code class="docutils literal notranslate"><span class="pre">Quantize</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.QuantizeDequantize"><code class="docutils literal notranslate"><span class="pre">QuantizeDequantize</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#functions">Functions</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.quantize"><code class="docutils literal notranslate"><span class="pre">quantize()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.quantize_dequantize"><code class="docutils literal notranslate"><span class="pre">quantize_dequantize()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.dequantize"><code class="docutils literal notranslate"><span class="pre">dequantize()</span></code></a></li>
+</ul>
+</li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html">quantization.float</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html#classes">Classes</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html#classes">Classes</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html#aimet_torch.v2.quantization.float.FloatQuantizeDequantize"><code class="docutils literal notranslate"><span class="pre">FloatQuantizeDequantize</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html#aimet_torch.v2.quantization.float.QuantizeDequantize"><code class="docutils literal notranslate"><span class="pre">QuantizeDequantize</span></code></a></li>
+</ul>
+</li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/encoding_analyzer.html">Encoding Analyzers</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#variants">Variants</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer"><code class="docutils literal notranslate"><span class="pre">EncodingAnalyzer</span></code></a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.compute_encodings"><code class="docutils literal notranslate"><span class="pre">EncodingAnalyzer.compute_encodings()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.reset_stats"><code class="docutils literal notranslate"><span class="pre">EncodingAnalyzer.reset_stats()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.update_stats"><code class="docutils literal notranslate"><span class="pre">EncodingAnalyzer.update_stats()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#variants">Variants</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.MinMaxEncodingAnalyzer"><code class="docutils literal notranslate"><span class="pre">MinMaxEncodingAnalyzer</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.SqnrEncodingAnalyzer"><code class="docutils literal notranslate"><span class="pre">SqnrEncodingAnalyzer</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.PercentileEncodingAnalyzer"><code class="docutils literal notranslate"><span class="pre">PercentileEncodingAnalyzer</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/visualization_tools.html">Visualization Tools</a><ul>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/visualization_tools.html#aimet_torch.v2.visualization_tools.visualize_stats"><code class="docutils literal notranslate"><span class="pre">visualize_stats()</span></code></a></li>
 </ul>
 </li>
-<li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/visualization_tools.html">Visualization Tools</a></li>
 </ul>
 </li>
 </ul>
@@ -403,31 +559,102 @@
 </li>
 <li class="toctree-l3"><a class="reference internal" href="torch_compress.html">PyTorch Model Compression API</a><ul>
 <li class="toctree-l4"><a class="reference internal" href="torch_compress.html#introduction">Introduction</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#top-level-api-for-compression">Top-level API for Compression</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#top-level-api-for-compression">Top-level API for Compression</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.compress.ModelCompressor"><code class="docutils literal notranslate"><span class="pre">ModelCompressor</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.compress.ModelCompressor.compress_model"><code class="docutils literal notranslate"><span class="pre">ModelCompressor.compress_model()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_compress.html#greedy-selection-parameters">Greedy Selection Parameters</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_common.defs.GreedySelectionParameters"><code class="docutils literal notranslate"><span class="pre">GreedySelectionParameters</span></code></a></li>
 </ul>
 </li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#spatial-svd-configuration">Spatial SVD Configuration</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#weight-svd-configuration">Weight SVD Configuration</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#channel-pruning-configuration">Channel Pruning Configuration</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#configuration-definitions">Configuration Definitions</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#spatial-svd-configuration">Spatial SVD Configuration</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.AutoModeParams"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.AutoModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.ManualModeParams"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.ManualModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.Mode"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.Mode.auto"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode.auto</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.Mode.manual"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode.manual</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#weight-svd-configuration">Weight SVD Configuration</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.AutoModeParams"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.AutoModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.ManualModeParams"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.ManualModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.Mode"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.Mode</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.Mode.auto"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.Mode.auto</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.Mode.manual"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.Mode.manual</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#channel-pruning-configuration">Channel Pruning Configuration</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.AutoModeParams"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.AutoModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.ManualModeParams"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.ManualModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.Mode"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.Mode</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.Mode.auto"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.Mode.auto</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.Mode.manual"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.Mode.manual</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#configuration-definitions">Configuration Definitions</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ModuleCompRatioPair"><code class="docutils literal notranslate"><span class="pre">ModuleCompRatioPair</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_compress.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="torch_visualization_compression.html">PyTorch Model Visualization API for Compression</a><ul>
-<li class="toctree-l4"><a class="reference internal" href="torch_visualization_compression.html#top-level-api-compression">Top-level API Compression</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_visualization_compression.html#top-level-api-compression">Top-level API Compression</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_visualization_compression.html#aimet_torch.visualize_serialized_data.VisualizeCompression"><code class="docutils literal notranslate"><span class="pre">VisualizeCompression</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_visualization_compression.html#aimet_torch.visualize_serialized_data.VisualizeCompression.display_eval_scores"><code class="docutils literal notranslate"><span class="pre">VisualizeCompression.display_eval_scores()</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_visualization_compression.html#aimet_torch.visualize_serialized_data.VisualizeCompression.display_comp_ratio_plot"><code class="docutils literal notranslate"><span class="pre">VisualizeCompression.display_comp_ratio_plot()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_visualization_compression.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="torch_visualization_quantization.html">PyTorch Model Visualization API for Quantization</a><ul>
-<li class="toctree-l4"><a class="reference internal" href="torch_visualization_quantization.html#top-level-api-quantization">Top-level API Quantization</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_visualization_quantization.html#top-level-api-quantization">Top-level API Quantization</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_visualization_quantization.html#aimet_torch.visualize_model.visualize_relative_weight_ranges_to_identify_problematic_layers"><code class="docutils literal notranslate"><span class="pre">visualize_relative_weight_ranges_to_identify_problematic_layers()</span></code></a></li>
+<li class="toctree-l5"><a class="reference internal" href="torch_visualization_quantization.html#aimet_torch.visualize_model.visualize_weight_ranges"><code class="docutils literal notranslate"><span class="pre">visualize_weight_ranges()</span></code></a></li>
+<li class="toctree-l5"><a class="reference internal" href="torch_visualization_quantization.html#aimet_torch.visualize_model.visualize_changes_after_optimization"><code class="docutils literal notranslate"><span class="pre">visualize_changes_after_optimization()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_visualization_quantization.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="torch_layer_output_generation.html">PyTorch Debug API</a><ul>
-<li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#top-level-api">Top-level API</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#enum-definition">Enum Definition</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.LayerOutputUtil"><code class="docutils literal notranslate"><span class="pre">LayerOutputUtil</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.LayerOutputUtil.generate_layer_outputs"><code class="docutils literal notranslate"><span class="pre">LayerOutputUtil.generate_layer_outputs()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#enum-definition">Enum Definition</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.NamingScheme"><code class="docutils literal notranslate"><span class="pre">NamingScheme</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.NamingScheme.ONNX"><code class="docutils literal notranslate"><span class="pre">NamingScheme.ONNX</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.NamingScheme.PYTORCH"><code class="docutils literal notranslate"><span class="pre">NamingScheme.PYTORCH</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.NamingScheme.TORCHSCRIPT"><code class="docutils literal notranslate"><span class="pre">NamingScheme.TORCHSCRIPT</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#code-example">Code Example</a></li>
 </ul>
 </li>
@@ -437,27 +664,49 @@
 <li class="toctree-l3"><a class="reference internal" href="keras_quantization.html">TensorFlow Model Quantization API</a><ul>
 <li class="toctree-l4"><a class="reference internal" href="keras_model_guidelines.html"> Model Guidelines</a></li>
 <li class="toctree-l4"><a class="reference internal" href="keras_model_preparer.html"> Model Preparer API</a><ul>
-<li class="toctree-l5"><a class="reference internal" href="keras_model_preparer.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_model_preparer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_model_preparer.html#aimet_tensorflow.keras.model_preparer.prepare_model"><code class="docutils literal notranslate"><span class="pre">prepare_model()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_model_preparer.html#code-examples">Code Examples</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_model_preparer.html#limitations">Limitations</a></li>
 </ul>
 </li>
 <li class="toctree-l4"><a class="reference internal" href="keras_quant_analyzer.html"> Quant Analyzer API</a><ul>
-<li class="toctree-l5"><a class="reference internal" href="keras_quant_analyzer.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_quant_analyzer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_quant_analyzer.html#aimet_tensorflow.keras.quant_analyzer.QuantAnalyzer"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="keras_quant_analyzer.html#aimet_tensorflow.keras.quant_analyzer.QuantAnalyzer.analyze"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.analyze()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_quant_analyzer.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l4"><a class="reference internal" href="keras_quantsim.html"> Quantization Simulation API</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="keras_quantsim.html#user-guide-link">User Guide Link</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_quantsim.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_quantsim.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_quantsim.html#aimet_tensorflow.keras.quantsim.QuantizationSimModel"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="keras_quantsim.html#aimet_tensorflow.keras.quantsim.QuantizationSimModel.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel.compute_encodings()</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="keras_quantsim.html#aimet_tensorflow.keras.quantsim.QuantizationSimModel.export"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel.export()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_quantsim.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l4"><a class="reference internal" href="keras_adaround.html"> Adaptive Rounding API</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#examples-notebook-link">Examples Notebook Link</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#top-level-api">Top-level API</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#adaround-parameters">Adaround Parameters</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_adaround.html#aimet_tensorflow.keras.adaround_weight.Adaround.apply_adaround"><code class="docutils literal notranslate"><span class="pre">apply_adaround()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#adaround-parameters">Adaround Parameters</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_adaround.html#aimet_tensorflow.keras.adaround_weight.AdaroundParameters"><code class="docutils literal notranslate"><span class="pre">AdaroundParameters</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#enum-definition">Enum Definition</a><ul>
 <li class="toctree-l6"><a class="reference internal" href="keras_adaround.html#aimet_common.defs.QuantScheme"><code class="docutils literal notranslate"><span class="pre">QuantScheme</span></code></a><ul>
 <li class="toctree-l7"><a class="reference internal" href="keras_adaround.html#aimet_common.defs.QuantScheme.post_training_percentile"><code class="docutils literal notranslate"><span class="pre">QuantScheme.post_training_percentile</span></code></a></li>
@@ -476,15 +725,34 @@
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#introduction">Introduction</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#cross-layer-equalization-api">Cross Layer Equalization API</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#cross-layer-equalization-api">Cross Layer Equalization API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_cross_layer_equalization.html#aimet_tensorflow.keras.cross_layer_equalization.equalize_model"><code class="docutils literal notranslate"><span class="pre">equalize_model()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#code-example">Code Example</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#primitive-apis">Primitive APIs</a><ul>
 <li class="toctree-l6"><a class="reference internal" href="keras_primitive_apis_cle.html">Primitive APIs for Cross Layer Equalization</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#introduction">Introduction</a></li>
-<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#higher-level-apis-for-cross-layer-equalization">Higher Level APIs for Cross Layer Equalization</a></li>
+<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#higher-level-apis-for-cross-layer-equalization">Higher Level APIs for Cross Layer Equalization</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.batch_norm_fold.fold_all_batch_norms"><code class="docutils literal notranslate"><span class="pre">fold_all_batch_norms()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.CrossLayerScaling.scale_model"><code class="docutils literal notranslate"><span class="pre">scale_model()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.HighBiasFold.bias_fold"><code class="docutils literal notranslate"><span class="pre">bias_fold()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#code-examples-for-higher-level-apis">Code Examples for Higher Level APIs</a></li>
-<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#lower-level-apis-for-cross-layer-equalization">Lower Level APIs for Cross Layer Equalization</a></li>
-<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#custom-datatype-used">Custom Datatype used</a></li>
+<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#lower-level-apis-for-cross-layer-equalization">Lower Level APIs for Cross Layer Equalization</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.batch_norm_fold.fold_given_batch_norms"><code class="docutils literal notranslate"><span class="pre">fold_given_batch_norms()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.CrossLayerScaling.scale_cls_sets"><code class="docutils literal notranslate"><span class="pre">scale_cls_sets()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#id0"><code class="docutils literal notranslate"><span class="pre">bias_fold()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#custom-datatype-used">Custom Datatype used</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.ClsSetInfo"><code class="docutils literal notranslate"><span class="pre">ClsSetInfo</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.ClsSetInfo.ClsSetLayerPairInfo"><code class="docutils literal notranslate"><span class="pre">ClsSetInfo.ClsSetLayerPairInfo</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#code-example-for-lower-level-apis">Code Example for Lower level APIs</a></li>
 <li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#example-helper-methods-to-perform-cle-in-manual-mode">Example helper methods to perform CLE in manual mode</a></li>
 </ul>
@@ -496,7 +764,11 @@
 <li class="toctree-l4"><a class="reference internal" href="keras_batchnorm_re_estimation.html"> BN Re-estimation APIs</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#introduction">Introduction</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#top-level-apis">Top-level APIs</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#top-level-apis">Top-level APIs</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_batchnorm_re_estimation.html#aimet_tensorflow.keras.bn_reestimation.reestimate_bn_stats"><code class="docutils literal notranslate"><span class="pre">reestimate_bn_stats()</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="keras_batchnorm_re_estimation.html#aimet_tensorflow.keras.batch_norm_fold.fold_all_batch_norms_to_scale"><code class="docutils literal notranslate"><span class="pre">fold_all_batch_norms_to_scale()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#code-example">Code Example</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#limitations">Limitations</a></li>
 </ul>
@@ -504,15 +776,39 @@
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="keras_layer_output_generation.html">TensorFlow Debug API</a><ul>
-<li class="toctree-l4"><a class="reference internal" href="keras_layer_output_generation.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l4"><a class="reference internal" href="keras_layer_output_generation.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="keras_layer_output_generation.html#aimet_tensorflow.keras.layer_output_utils.LayerOutputUtil"><code class="docutils literal notranslate"><span class="pre">LayerOutputUtil</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_layer_output_generation.html#aimet_tensorflow.keras.layer_output_utils.LayerOutputUtil.generate_layer_outputs"><code class="docutils literal notranslate"><span class="pre">LayerOutputUtil.generate_layer_outputs()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="keras_layer_output_generation.html#code-example">Code Example</a></li>
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="keras_compression.html">TensorFlow Model Compression API</a><ul>
 <li class="toctree-l4"><a class="reference internal" href="keras_compression.html#introduction">Introduction</a></li>
-<li class="toctree-l4"><a class="reference internal" href="keras_compression.html#top-level-api-for-compression">Top-level API for Compression</a></li>
+<li class="toctree-l4"><a class="reference internal" href="keras_compression.html#top-level-api-for-compression">Top-level API for Compression</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.compress.ModelCompressor"><code class="docutils literal notranslate"><span class="pre">ModelCompressor</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.compress.ModelCompressor.compress_model"><code class="docutils literal notranslate"><span class="pre">ModelCompressor.compress_model()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="keras_compression.html#greedy-selection-parameters">Greedy Selection Parameters</a></li>
-<li class="toctree-l4"><a class="reference internal" href="keras_compression.html#spatial-svd-configuration">Spatial SVD Configuration</a></li>
+<li class="toctree-l4"><a class="reference internal" href="keras_compression.html#spatial-svd-configuration">Spatial SVD Configuration</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.AutoModeParams"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.AutoModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.ManualModeParams"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.ManualModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.Mode"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.Mode.auto"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode.auto</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.Mode.manual"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode.manual</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="keras_compression.html#configuration-definitions">Configuration Definitions</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="keras_compression.html#aimet_common.defs.CostMetric"><code class="docutils literal notranslate"><span class="pre">CostMetric</span></code></a><ul>
 <li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_common.defs.CostMetric.mac"><code class="docutils literal notranslate"><span class="pre">CostMetric.mac</span></code></a></li>
@@ -525,6 +821,7 @@
 <li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_common.defs.CompressionScheme.weight_svd"><code class="docutils literal notranslate"><span class="pre">CompressionScheme.weight_svd</span></code></a></li>
 </ul>
 </li>
+<li class="toctree-l5"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.ModuleCompRatioPair"><code class="docutils literal notranslate"><span class="pre">ModuleCompRatioPair</span></code></a></li>
 </ul>
 </li>
 <li class="toctree-l4"><a class="reference internal" href="keras_compression.html#code-examples">Code Examples</a></li>
diff --git a/releases/1.35.1/api_docs/torch_spconv_custom_onnx_export.html b/releases/1.35.1/api_docs/torch_spconv_custom_onnx_export.html
index 3b8dff0..f7ea33d 100644
--- a/releases/1.35.1/api_docs/torch_spconv_custom_onnx_export.html
+++ b/releases/1.35.1/api_docs/torch_spconv_custom_onnx_export.html
@@ -241,9 +241,15 @@
 <li class="toctree-l4"><a class="reference internal" href="torch_quantization.html#aimet-torch">aimet_torch</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="torch_quantization.html#api-reference">API Reference</a><ul>
 <li class="toctree-l6"><a class="reference internal" href="torch_model_guidelines.html"> Model Guidelines</a></li>
-<li class="toctree-l6"><a class="reference internal" href="torch_architecture_checker.html"> Architecture Checker API</a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_architecture_checker.html"> Architecture Checker API</a><ul>
+<li class="toctree-l7"><a class="reference internal" href="torch_architecture_checker.html#aimet_torch.arch_checker.arch_checker.ArchChecker.check_model_arch"><code class="docutils literal notranslate"><span class="pre">check_model_arch()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l6"><a class="reference internal" href="torch_model_preparer.html"> Model Preparer API</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="torch_model_preparer.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_model_preparer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_model_preparer.html#aimet_torch.model_preparer.prepare_model"><code class="docutils literal notranslate"><span class="pre">prepare_model()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_model_preparer.html#code-examples">Code Examples</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_model_preparer.html#limitations-of-torch-fx-symbolic-trace-api">Limitations of torch.fx symbolic trace API</a></li>
 </ul>
@@ -253,10 +259,23 @@
 <li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.enable_per_layer_mse_loss"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.enable_per_layer_mse_loss()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.analyze"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.analyze()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_common.utils.CallbackFunc"><code class="docutils literal notranslate"><span class="pre">CallbackFunc</span></code></a></li>
 </ul>
 </li>
-<li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#run-specific-utility">Run specific utility</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#run-specific-utility">Run specific utility</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.check_model_sensitivity_to_quantization"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.check_model_sensitivity_to_quantization()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.perform_per_layer_analysis_by_enabling_quant_wrappers"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.perform_per_layer_analysis_by_enabling_quant_wrappers()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.perform_per_layer_analysis_by_disabling_quant_wrappers"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.perform_per_layer_analysis_by_disabling_quant_wrappers()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.export_per_layer_encoding_min_max_range"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.export_per_layer_encoding_min_max_range()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.export_per_layer_stats_histogram"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.export_per_layer_stats_histogram()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quant_analyzer.html#aimet_torch.v1.quant_analyzer.QuantAnalyzer.export_per_layer_mse_loss"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.export_per_layer_mse_loss()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quant_analyzer.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
@@ -264,7 +283,16 @@
 <li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#guidelines">Guidelines</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.QuantizationSimModel"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.QuantizationSimModel.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel.compute_encodings()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.QuantizationSimModel.export"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel.export()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.save_checkpoint"><code class="docutils literal notranslate"><span class="pre">quantsim.save_checkpoint()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_quantsim.html#aimet_torch.v1.quantsim.load_checkpoint"><code class="docutils literal notranslate"><span class="pre">quantsim.load_checkpoint()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_quantsim.html#enum-definition">Enum Definition</a><ul>
 <li class="toctree-l8"><a class="reference internal" href="torch_quantsim.html#aimet_common.defs.QuantScheme"><code class="docutils literal notranslate"><span class="pre">QuantScheme</span></code></a><ul>
 <li class="toctree-l9"><a class="reference internal" href="torch_quantsim.html#aimet_common.defs.QuantScheme.post_training_percentile"><code class="docutils literal notranslate"><span class="pre">QuantScheme.post_training_percentile</span></code></a></li>
@@ -282,8 +310,14 @@
 <li class="toctree-l6"><a class="reference internal" href="torch_adaround.html"> Adaptive Rounding API</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#examples-notebook-link">Examples Notebook Link</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#top-level-api">Top-level API</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#adaround-parameters">Adaround Parameters</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_adaround.html#aimet_torch.v1.adaround.adaround_weight.Adaround.apply_adaround"><code class="docutils literal notranslate"><span class="pre">apply_adaround()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#adaround-parameters">Adaround Parameters</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_adaround.html#aimet_torch.v1.adaround.adaround_weight.AdaroundParameters"><code class="docutils literal notranslate"><span class="pre">AdaroundParameters</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_adaround.html#enum-definition">Enum Definition</a><ul>
 <li class="toctree-l8"><a class="reference internal" href="torch_adaround.html#aimet_common.defs.QuantScheme"><code class="docutils literal notranslate"><span class="pre">QuantScheme</span></code></a><ul>
 <li class="toctree-l9"><a class="reference internal" href="torch_adaround.html#aimet_common.defs.QuantScheme.post_training_percentile"><code class="docutils literal notranslate"><span class="pre">QuantScheme.post_training_percentile</span></code></a></li>
@@ -302,15 +336,31 @@
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#introduction">Introduction</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#cross-layer-equalization-api">Cross Layer Equalization API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#cross-layer-equalization-api">Cross Layer Equalization API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_cross_layer_equalization.html#aimet_torch.cross_layer_equalization.equalize_model"><code class="docutils literal notranslate"><span class="pre">equalize_model()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#code-example">Code Example</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_cross_layer_equalization.html#primitive-apis">Primitive APIs</a><ul>
 <li class="toctree-l8"><a class="reference internal" href="torch_primitive_apis_cle.html">Primitive APIs for Cross Layer Equalization</a><ul>
 <li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#introduction">Introduction</a></li>
-<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#clssetinfo-definition">ClsSetInfo Definition</a></li>
-<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#higher-level-apis-for-cross-layer-equalization">Higher Level APIs for Cross Layer Equalization</a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#clssetinfo-definition">ClsSetInfo Definition</a><ul>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.cross_layer_equalization.ClsSetInfo"><code class="docutils literal notranslate"><span class="pre">ClsSetInfo</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#higher-level-apis-for-cross-layer-equalization">Higher Level APIs for Cross Layer Equalization</a><ul>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.batch_norm_fold.fold_all_batch_norms"><code class="docutils literal notranslate"><span class="pre">fold_all_batch_norms()</span></code></a></li>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.cross_layer_equalization.CrossLayerScaling.scale_model"><code class="docutils literal notranslate"><span class="pre">scale_model()</span></code></a></li>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.cross_layer_equalization.HighBiasFold.bias_fold"><code class="docutils literal notranslate"><span class="pre">bias_fold()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#code-examples-for-higher-level-apis">Code Examples for Higher Level APIs</a></li>
-<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#lower-level-apis-for-cross-layer-equalization">Lower Level APIs for Cross Layer Equalization</a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#lower-level-apis-for-cross-layer-equalization">Lower Level APIs for Cross Layer Equalization</a><ul>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.batch_norm_fold.fold_given_batch_norms"><code class="docutils literal notranslate"><span class="pre">fold_given_batch_norms()</span></code></a></li>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#aimet_torch.cross_layer_equalization.CrossLayerScaling.scale_cls_sets"><code class="docutils literal notranslate"><span class="pre">scale_cls_sets()</span></code></a></li>
+<li class="toctree-l10"><a class="reference internal" href="torch_primitive_apis_cle.html#id0"><code class="docutils literal notranslate"><span class="pre">bias_fold()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l9"><a class="reference internal" href="torch_primitive_apis_cle.html#code-examples-for-lower-level-apis">Code Examples for Lower Level APIs</a></li>
 </ul>
 </li>
@@ -320,7 +370,10 @@
 </li>
 <li class="toctree-l6"><a class="reference internal" href="torch_bias_correction.html"> Bias Correction API</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#user-guide-link">User Guide Link</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#bias-correction-api">Bias Correction API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#bias-correction-api">Bias Correction API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_bias_correction.html#aimet_torch.bias_correction.correct_bias"><code class="docutils literal notranslate"><span class="pre">correct_bias()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#convbninfotype">ConvBnInfoType</a><ul>
 <li class="toctree-l8"><a class="reference internal" href="torch_bias_correction.html#aimet_common.bias_correction.ConvBnInfoType"><code class="docutils literal notranslate"><span class="pre">ConvBnInfoType</span></code></a></li>
 </ul>
@@ -334,7 +387,10 @@
 </li>
 </ul>
 </li>
-<li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#quantization-params">Quantization Params</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#quantization-params">Quantization Params</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_bias_correction.html#aimet_torch.v1.quantsim.QuantParams"><code class="docutils literal notranslate"><span class="pre">QuantParams</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#code-example-1-empirical-bias-correction">Code Example #1 Empirical Bias Correction</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_bias_correction.html#code-example-2-analytical-empirical-bias-correction">Code Example #2 Analytical + Empirical Bias correction</a></li>
 </ul>
@@ -342,21 +398,46 @@
 <li class="toctree-l6"><a class="reference internal" href="torch_auto_quant.html"> AutoQuant API</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#examples-notebook-link">Examples Notebook Link</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_auto_quant.html#aimet_torch.v1.auto_quant.AutoQuant"><code class="docutils literal notranslate"><span class="pre">AutoQuant</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_auto_quant.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="torch_batchnorm_re_estimation.html"> BN Re-estimation APIs</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#introduction">Introduction</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#top-level-apis">Top-level APIs</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#top-level-apis">Top-level APIs</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_batchnorm_re_estimation.html#aimet_torch.bn_reestimation.reestimate_bn_stats"><code class="docutils literal notranslate"><span class="pre">reestimate_bn_stats()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_batchnorm_re_estimation.html#aimet_torch.batch_norm_fold.fold_all_batch_norms_to_scale"><code class="docutils literal notranslate"><span class="pre">fold_all_batch_norms_to_scale()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="torch_batchnorm_re_estimation.html#code-example-bn-reestimation">Code Example - BN-Reestimation</a></li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="torch_multi_gpu.html"> Multi-GPU guidelines</a></li>
 <li class="toctree-l6"><a class="reference internal" href="torch_peft_lora.html"> PEFT LoRA APIs</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="torch_peft_lora.html#user-flow">User flow</a></li>
-<li class="toctree-l7"><a class="reference internal" href="torch_peft_lora.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_peft_lora.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.AdapterMetaData"><code class="docutils literal notranslate"><span class="pre">AdapterMetaData</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.replace_lora_layers_with_quantizable_layers"><code class="docutils literal notranslate"><span class="pre">peft.replace_lora_layers_with_quantizable_layers()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.track_lora_meta_data"><code class="docutils literal notranslate"><span class="pre">peft.track_lora_meta_data()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.disable_lora_adapters"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.disable_lora_adapters()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.enable_adapter_and_load_weights"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.enable_adapter_and_load_weights()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.export_adapter_weights"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.export_adapter_weights()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.freeze_base_model"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.freeze_base_model()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.freeze_base_model_activation_quantizers"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.freeze_base_model_activation_quantizers()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.freeze_base_model_param_quantizers"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.freeze_base_model_param_quantizers()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.get_fp_lora_layer"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.get_fp_lora_layer()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.get_quantized_lora_layer"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.get_quantized_lora_layer()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.quantize_lora_scale_with_fixed_range"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.quantize_lora_scale_with_fixed_range()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="torch_peft_lora.html#aimet_torch.peft.PeftQuantUtils.set_bitwidth_for_lora_adapters"><code class="docutils literal notranslate"><span class="pre">PeftQuantUtils.set_bitwidth_for_lora_adapters()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 </ul>
 </li>
 </ul>
@@ -368,31 +449,106 @@
 <li class="toctree-l5"><a class="reference internal" href="torch_quantization.html#backwards-compatibility">Backwards Compatibility</a></li>
 <li class="toctree-l5"><a class="reference internal" href="torch_quantization.html#id1">API Reference</a><ul>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/quantized_modules.html">Quantized Modules</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.input_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.input_quantizers</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.output_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.output_quantizers</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.param_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.param_quantizers</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.__quant_init__"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.__quant_init__()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.compute_encodings()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantized_modules.html#aimet_torch.v2.nn.QuantizationMixin.forward"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.forward()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#configuration">Configuration</a></li>
 <li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#computing-encodings">Computing Encodings</a></li>
 <li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantized_modules.html#quantized-module-classes">Quantized Module Classes</a></li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/quantizer.html">Quantizers</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantizer.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/quantizer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase"><code class="docutils literal notranslate"><span class="pre">QuantizerBase</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.allow_overwrite"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.allow_overwrite()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.compute_encodings()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.get_encoding"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.get_encoding()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.get_legacy_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.get_legacy_encodings()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.is_initialized"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.is_initialized()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.register_quantization_parameter"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.register_quantization_parameter()</span></code></a></li>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.set_legacy_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizerBase.set_legacy_encodings()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizeDequantize"><code class="docutils literal notranslate"><span class="pre">QuantizeDequantize</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.QuantizeDequantize.forward"><code class="docutils literal notranslate"><span class="pre">QuantizeDequantize.forward()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.Quantize"><code class="docutils literal notranslate"><span class="pre">Quantize</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="../torch_docs/quantizer.html#aimet_torch.v2.quantization.affine.quantizer.Quantize.forward"><code class="docutils literal notranslate"><span class="pre">Quantize.forward()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html">QuantizationMixin</a><ul>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin</span></code></a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.input_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.input_quantizers</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.output_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.output_quantizers</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.param_quantizers"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.param_quantizers</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.forward"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.forward()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.__quant_init__"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.__quant_init__()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.set_kernel"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.set_kernel()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.set_default_kernel"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.set_default_kernel()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.compute_encodings()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.from_module"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.from_module()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.get_default_kernel"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.get_default_kernel()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.get_kernel"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.get_kernel()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html#aimet_torch.v2.nn.QuantizationMixin.implements"><code class="docutils literal notranslate"><span class="pre">QuantizationMixin.implements()</span></code></a></li>
+</ul>
+</li>
 </ul>
 </li>
-<li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/nn.quantization_mixin.html">QuantizationMixin</a></li>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html">quantization.affine</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#classes">Classes</a></li>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#functions">Functions</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#classes">Classes</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.Quantize"><code class="docutils literal notranslate"><span class="pre">Quantize</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.QuantizeDequantize"><code class="docutils literal notranslate"><span class="pre">QuantizeDequantize</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#functions">Functions</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.quantize"><code class="docutils literal notranslate"><span class="pre">quantize()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.quantize_dequantize"><code class="docutils literal notranslate"><span class="pre">quantize_dequantize()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/affine/index.html#aimet_torch.v2.quantization.affine.dequantize"><code class="docutils literal notranslate"><span class="pre">dequantize()</span></code></a></li>
+</ul>
+</li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html">quantization.float</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html#classes">Classes</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html#classes">Classes</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html#aimet_torch.v2.quantization.float.FloatQuantizeDequantize"><code class="docutils literal notranslate"><span class="pre">FloatQuantizeDequantize</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/api/quantization/float/index.html#aimet_torch.v2.quantization.float.QuantizeDequantize"><code class="docutils literal notranslate"><span class="pre">QuantizeDequantize</span></code></a></li>
+</ul>
+</li>
 </ul>
 </li>
 <li class="toctree-l6"><a class="reference internal" href="../torch_docs/encoding_analyzer.html">Encoding Analyzers</a><ul>
-<li class="toctree-l7"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#variants">Variants</a></li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer"><code class="docutils literal notranslate"><span class="pre">EncodingAnalyzer</span></code></a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.compute_encodings"><code class="docutils literal notranslate"><span class="pre">EncodingAnalyzer.compute_encodings()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.reset_stats"><code class="docutils literal notranslate"><span class="pre">EncodingAnalyzer.reset_stats()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.update_stats"><code class="docutils literal notranslate"><span class="pre">EncodingAnalyzer.update_stats()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#variants">Variants</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.MinMaxEncodingAnalyzer"><code class="docutils literal notranslate"><span class="pre">MinMaxEncodingAnalyzer</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.SqnrEncodingAnalyzer"><code class="docutils literal notranslate"><span class="pre">SqnrEncodingAnalyzer</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="../torch_docs/encoding_analyzer.html#aimet_torch.v2.quantization.encoding_analyzer.PercentileEncodingAnalyzer"><code class="docutils literal notranslate"><span class="pre">PercentileEncodingAnalyzer</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/visualization_tools.html">Visualization Tools</a><ul>
+<li class="toctree-l7"><a class="reference internal" href="../torch_docs/api/visualization_tools.html#aimet_torch.v2.visualization_tools.visualize_stats"><code class="docutils literal notranslate"><span class="pre">visualize_stats()</span></code></a></li>
 </ul>
 </li>
-<li class="toctree-l6"><a class="reference internal" href="../torch_docs/api/visualization_tools.html">Visualization Tools</a></li>
 </ul>
 </li>
 </ul>
@@ -401,31 +557,102 @@
 </li>
 <li class="toctree-l3"><a class="reference internal" href="torch_compress.html">PyTorch Model Compression API</a><ul>
 <li class="toctree-l4"><a class="reference internal" href="torch_compress.html#introduction">Introduction</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#top-level-api-for-compression">Top-level API for Compression</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#top-level-api-for-compression">Top-level API for Compression</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.compress.ModelCompressor"><code class="docutils literal notranslate"><span class="pre">ModelCompressor</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.compress.ModelCompressor.compress_model"><code class="docutils literal notranslate"><span class="pre">ModelCompressor.compress_model()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_compress.html#greedy-selection-parameters">Greedy Selection Parameters</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_common.defs.GreedySelectionParameters"><code class="docutils literal notranslate"><span class="pre">GreedySelectionParameters</span></code></a></li>
 </ul>
 </li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#spatial-svd-configuration">Spatial SVD Configuration</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#weight-svd-configuration">Weight SVD Configuration</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#channel-pruning-configuration">Channel Pruning Configuration</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#configuration-definitions">Configuration Definitions</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#spatial-svd-configuration">Spatial SVD Configuration</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.AutoModeParams"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.AutoModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.ManualModeParams"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.ManualModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.Mode"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.Mode.auto"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode.auto</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.SpatialSvdParameters.Mode.manual"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode.manual</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#weight-svd-configuration">Weight SVD Configuration</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.AutoModeParams"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.AutoModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.ManualModeParams"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.ManualModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.Mode"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.Mode</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.Mode.auto"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.Mode.auto</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.WeightSvdParameters.Mode.manual"><code class="docutils literal notranslate"><span class="pre">WeightSvdParameters.Mode.manual</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#channel-pruning-configuration">Channel Pruning Configuration</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.AutoModeParams"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.AutoModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.ManualModeParams"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.ManualModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.Mode"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.Mode</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.Mode.auto"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.Mode.auto</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ChannelPruningParameters.Mode.manual"><code class="docutils literal notranslate"><span class="pre">ChannelPruningParameters.Mode.manual</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l4"><a class="reference internal" href="torch_compress.html#configuration-definitions">Configuration Definitions</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_compress.html#aimet_torch.defs.ModuleCompRatioPair"><code class="docutils literal notranslate"><span class="pre">ModuleCompRatioPair</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_compress.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="torch_visualization_compression.html">PyTorch Model Visualization API for Compression</a><ul>
-<li class="toctree-l4"><a class="reference internal" href="torch_visualization_compression.html#top-level-api-compression">Top-level API Compression</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_visualization_compression.html#top-level-api-compression">Top-level API Compression</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_visualization_compression.html#aimet_torch.visualize_serialized_data.VisualizeCompression"><code class="docutils literal notranslate"><span class="pre">VisualizeCompression</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_visualization_compression.html#aimet_torch.visualize_serialized_data.VisualizeCompression.display_eval_scores"><code class="docutils literal notranslate"><span class="pre">VisualizeCompression.display_eval_scores()</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_visualization_compression.html#aimet_torch.visualize_serialized_data.VisualizeCompression.display_comp_ratio_plot"><code class="docutils literal notranslate"><span class="pre">VisualizeCompression.display_comp_ratio_plot()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_visualization_compression.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="torch_visualization_quantization.html">PyTorch Model Visualization API for Quantization</a><ul>
-<li class="toctree-l4"><a class="reference internal" href="torch_visualization_quantization.html#top-level-api-quantization">Top-level API Quantization</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_visualization_quantization.html#top-level-api-quantization">Top-level API Quantization</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_visualization_quantization.html#aimet_torch.visualize_model.visualize_relative_weight_ranges_to_identify_problematic_layers"><code class="docutils literal notranslate"><span class="pre">visualize_relative_weight_ranges_to_identify_problematic_layers()</span></code></a></li>
+<li class="toctree-l5"><a class="reference internal" href="torch_visualization_quantization.html#aimet_torch.visualize_model.visualize_weight_ranges"><code class="docutils literal notranslate"><span class="pre">visualize_weight_ranges()</span></code></a></li>
+<li class="toctree-l5"><a class="reference internal" href="torch_visualization_quantization.html#aimet_torch.visualize_model.visualize_changes_after_optimization"><code class="docutils literal notranslate"><span class="pre">visualize_changes_after_optimization()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_visualization_quantization.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="torch_layer_output_generation.html">PyTorch Debug API</a><ul>
-<li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#top-level-api">Top-level API</a></li>
-<li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#enum-definition">Enum Definition</a></li>
+<li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.LayerOutputUtil"><code class="docutils literal notranslate"><span class="pre">LayerOutputUtil</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.LayerOutputUtil.generate_layer_outputs"><code class="docutils literal notranslate"><span class="pre">LayerOutputUtil.generate_layer_outputs()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+<li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#enum-definition">Enum Definition</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.NamingScheme"><code class="docutils literal notranslate"><span class="pre">NamingScheme</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.NamingScheme.ONNX"><code class="docutils literal notranslate"><span class="pre">NamingScheme.ONNX</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.NamingScheme.PYTORCH"><code class="docutils literal notranslate"><span class="pre">NamingScheme.PYTORCH</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="torch_layer_output_generation.html#aimet_torch.layer_output_utils.NamingScheme.TORCHSCRIPT"><code class="docutils literal notranslate"><span class="pre">NamingScheme.TORCHSCRIPT</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="torch_layer_output_generation.html#code-example">Code Example</a></li>
 </ul>
 </li>
@@ -435,27 +662,49 @@
 <li class="toctree-l3"><a class="reference internal" href="keras_quantization.html">TensorFlow Model Quantization API</a><ul>
 <li class="toctree-l4"><a class="reference internal" href="keras_model_guidelines.html"> Model Guidelines</a></li>
 <li class="toctree-l4"><a class="reference internal" href="keras_model_preparer.html"> Model Preparer API</a><ul>
-<li class="toctree-l5"><a class="reference internal" href="keras_model_preparer.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_model_preparer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_model_preparer.html#aimet_tensorflow.keras.model_preparer.prepare_model"><code class="docutils literal notranslate"><span class="pre">prepare_model()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_model_preparer.html#code-examples">Code Examples</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_model_preparer.html#limitations">Limitations</a></li>
 </ul>
 </li>
 <li class="toctree-l4"><a class="reference internal" href="keras_quant_analyzer.html"> Quant Analyzer API</a><ul>
-<li class="toctree-l5"><a class="reference internal" href="keras_quant_analyzer.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_quant_analyzer.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_quant_analyzer.html#aimet_tensorflow.keras.quant_analyzer.QuantAnalyzer"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="keras_quant_analyzer.html#aimet_tensorflow.keras.quant_analyzer.QuantAnalyzer.analyze"><code class="docutils literal notranslate"><span class="pre">QuantAnalyzer.analyze()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_quant_analyzer.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l4"><a class="reference internal" href="keras_quantsim.html"> Quantization Simulation API</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="keras_quantsim.html#user-guide-link">User Guide Link</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_quantsim.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_quantsim.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_quantsim.html#aimet_tensorflow.keras.quantsim.QuantizationSimModel"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="keras_quantsim.html#aimet_tensorflow.keras.quantsim.QuantizationSimModel.compute_encodings"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel.compute_encodings()</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="keras_quantsim.html#aimet_tensorflow.keras.quantsim.QuantizationSimModel.export"><code class="docutils literal notranslate"><span class="pre">QuantizationSimModel.export()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_quantsim.html#code-examples">Code Examples</a></li>
 </ul>
 </li>
 <li class="toctree-l4"><a class="reference internal" href="keras_adaround.html"> Adaptive Rounding API</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#examples-notebook-link">Examples Notebook Link</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#top-level-api">Top-level API</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#adaround-parameters">Adaround Parameters</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_adaround.html#aimet_tensorflow.keras.adaround_weight.Adaround.apply_adaround"><code class="docutils literal notranslate"><span class="pre">apply_adaround()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#adaround-parameters">Adaround Parameters</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_adaround.html#aimet_tensorflow.keras.adaround_weight.AdaroundParameters"><code class="docutils literal notranslate"><span class="pre">AdaroundParameters</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_adaround.html#enum-definition">Enum Definition</a><ul>
 <li class="toctree-l6"><a class="reference internal" href="keras_adaround.html#aimet_common.defs.QuantScheme"><code class="docutils literal notranslate"><span class="pre">QuantScheme</span></code></a><ul>
 <li class="toctree-l7"><a class="reference internal" href="keras_adaround.html#aimet_common.defs.QuantScheme.post_training_percentile"><code class="docutils literal notranslate"><span class="pre">QuantScheme.post_training_percentile</span></code></a></li>
@@ -474,15 +723,34 @@
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#user-guide-link">User Guide Link</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#introduction">Introduction</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#cross-layer-equalization-api">Cross Layer Equalization API</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#cross-layer-equalization-api">Cross Layer Equalization API</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_cross_layer_equalization.html#aimet_tensorflow.keras.cross_layer_equalization.equalize_model"><code class="docutils literal notranslate"><span class="pre">equalize_model()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#code-example">Code Example</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_cross_layer_equalization.html#primitive-apis">Primitive APIs</a><ul>
 <li class="toctree-l6"><a class="reference internal" href="keras_primitive_apis_cle.html">Primitive APIs for Cross Layer Equalization</a><ul>
 <li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#introduction">Introduction</a></li>
-<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#higher-level-apis-for-cross-layer-equalization">Higher Level APIs for Cross Layer Equalization</a></li>
+<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#higher-level-apis-for-cross-layer-equalization">Higher Level APIs for Cross Layer Equalization</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.batch_norm_fold.fold_all_batch_norms"><code class="docutils literal notranslate"><span class="pre">fold_all_batch_norms()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.CrossLayerScaling.scale_model"><code class="docutils literal notranslate"><span class="pre">scale_model()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.HighBiasFold.bias_fold"><code class="docutils literal notranslate"><span class="pre">bias_fold()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#code-examples-for-higher-level-apis">Code Examples for Higher Level APIs</a></li>
-<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#lower-level-apis-for-cross-layer-equalization">Lower Level APIs for Cross Layer Equalization</a></li>
-<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#custom-datatype-used">Custom Datatype used</a></li>
+<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#lower-level-apis-for-cross-layer-equalization">Lower Level APIs for Cross Layer Equalization</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.batch_norm_fold.fold_given_batch_norms"><code class="docutils literal notranslate"><span class="pre">fold_given_batch_norms()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.CrossLayerScaling.scale_cls_sets"><code class="docutils literal notranslate"><span class="pre">scale_cls_sets()</span></code></a></li>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#id0"><code class="docutils literal notranslate"><span class="pre">bias_fold()</span></code></a></li>
+</ul>
+</li>
+<li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#custom-datatype-used">Custom Datatype used</a><ul>
+<li class="toctree-l8"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.ClsSetInfo"><code class="docutils literal notranslate"><span class="pre">ClsSetInfo</span></code></a><ul>
+<li class="toctree-l9"><a class="reference internal" href="keras_primitive_apis_cle.html#aimet_tensorflow.keras.cross_layer_equalization.ClsSetInfo.ClsSetLayerPairInfo"><code class="docutils literal notranslate"><span class="pre">ClsSetInfo.ClsSetLayerPairInfo</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#code-example-for-lower-level-apis">Code Example for Lower level APIs</a></li>
 <li class="toctree-l7"><a class="reference internal" href="keras_primitive_apis_cle.html#example-helper-methods-to-perform-cle-in-manual-mode">Example helper methods to perform CLE in manual mode</a></li>
 </ul>
@@ -494,7 +762,11 @@
 <li class="toctree-l4"><a class="reference internal" href="keras_batchnorm_re_estimation.html"> BN Re-estimation APIs</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#examples-notebook-link">Examples Notebook Link</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#introduction">Introduction</a></li>
-<li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#top-level-apis">Top-level APIs</a></li>
+<li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#top-level-apis">Top-level APIs</a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_batchnorm_re_estimation.html#aimet_tensorflow.keras.bn_reestimation.reestimate_bn_stats"><code class="docutils literal notranslate"><span class="pre">reestimate_bn_stats()</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="keras_batchnorm_re_estimation.html#aimet_tensorflow.keras.batch_norm_fold.fold_all_batch_norms_to_scale"><code class="docutils literal notranslate"><span class="pre">fold_all_batch_norms_to_scale()</span></code></a></li>
+</ul>
+</li>
 <li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#code-example">Code Example</a></li>
 <li class="toctree-l5"><a class="reference internal" href="keras_batchnorm_re_estimation.html#limitations">Limitations</a></li>
 </ul>
@@ -502,15 +774,39 @@
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="keras_layer_output_generation.html">TensorFlow Debug API</a><ul>
-<li class="toctree-l4"><a class="reference internal" href="keras_layer_output_generation.html#top-level-api">Top-level API</a></li>
+<li class="toctree-l4"><a class="reference internal" href="keras_layer_output_generation.html#top-level-api">Top-level API</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="keras_layer_output_generation.html#aimet_tensorflow.keras.layer_output_utils.LayerOutputUtil"><code class="docutils literal notranslate"><span class="pre">LayerOutputUtil</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_layer_output_generation.html#aimet_tensorflow.keras.layer_output_utils.LayerOutputUtil.generate_layer_outputs"><code class="docutils literal notranslate"><span class="pre">LayerOutputUtil.generate_layer_outputs()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="keras_layer_output_generation.html#code-example">Code Example</a></li>
 </ul>
 </li>
 <li class="toctree-l3"><a class="reference internal" href="keras_compression.html">TensorFlow Model Compression API</a><ul>
 <li class="toctree-l4"><a class="reference internal" href="keras_compression.html#introduction">Introduction</a></li>
-<li class="toctree-l4"><a class="reference internal" href="keras_compression.html#top-level-api-for-compression">Top-level API for Compression</a></li>
+<li class="toctree-l4"><a class="reference internal" href="keras_compression.html#top-level-api-for-compression">Top-level API for Compression</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.compress.ModelCompressor"><code class="docutils literal notranslate"><span class="pre">ModelCompressor</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.compress.ModelCompressor.compress_model"><code class="docutils literal notranslate"><span class="pre">ModelCompressor.compress_model()</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="keras_compression.html#greedy-selection-parameters">Greedy Selection Parameters</a></li>
-<li class="toctree-l4"><a class="reference internal" href="keras_compression.html#spatial-svd-configuration">Spatial SVD Configuration</a></li>
+<li class="toctree-l4"><a class="reference internal" href="keras_compression.html#spatial-svd-configuration">Spatial SVD Configuration</a><ul>
+<li class="toctree-l5"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters</span></code></a><ul>
+<li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.AutoModeParams"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.AutoModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.ManualModeParams"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.ManualModeParams</span></code></a></li>
+<li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.Mode"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode</span></code></a><ul>
+<li class="toctree-l7"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.Mode.auto"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode.auto</span></code></a></li>
+<li class="toctree-l7"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.SpatialSvdParameters.Mode.manual"><code class="docutils literal notranslate"><span class="pre">SpatialSvdParameters.Mode.manual</span></code></a></li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
 <li class="toctree-l4"><a class="reference internal" href="keras_compression.html#configuration-definitions">Configuration Definitions</a><ul>
 <li class="toctree-l5"><a class="reference internal" href="keras_compression.html#aimet_common.defs.CostMetric"><code class="docutils literal notranslate"><span class="pre">CostMetric</span></code></a><ul>
 <li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_common.defs.CostMetric.mac"><code class="docutils literal notranslate"><span class="pre">CostMetric.mac</span></code></a></li>
@@ -523,6 +819,7 @@
 <li class="toctree-l6"><a class="reference internal" href="keras_compression.html#aimet_common.defs.CompressionScheme.weight_svd"><code class="docutils literal notranslate"><span class="pre">CompressionScheme.weight_svd</span></code></a></li>
 </ul>
 </li>
+<li class="toctree-l5"><a class="reference internal" href="keras_compression.html#aimet_tensorflow.keras.defs.ModuleCompRatioPair"><code class="docutils literal notranslate"><span class="pre">ModuleCompRatioPair</span></code></a></li>
 </ul>
 </li>
 <li class="toctree-l4"><a class="reference internal" href="keras_compression.html#code-examples">Code Examples</a></li>
@@ -673,7 +970,21 @@
 <section id="custom-api-for-the-spconv-modules">
 <h2>Custom API for the spconv modules<a class="headerlink" href="#custom-api-for-the-spconv-modules" title="Permalink to this heading"></a></h2>
 <p><strong>The following api can be used to create a sparse tensor given indices and features in dense form</strong></p>
+<dl class="py class">
+<dt class="sig sig-object py" id="aimet_torch.nn.modules.custom.SparseTensorWrapper">
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">aimet_torch.nn.modules.custom.</span></span><span class="sig-name descname"><span class="pre">SparseTensorWrapper</span></span><a class="reference internal" href="../_modules/aimet_torch/v1/nn/modules/custom.html#SparseTensorWrapper"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#aimet_torch.nn.modules.custom.SparseTensorWrapper" title="Permalink to this definition"></a></dt>
+<dd><p>Custom SparsetensorWrapper class for SparseConvTensor</p>
+<p>Initializes internal Module state, shared by both nn.Module and ScriptModule.</p>
+</dd></dl>
+
 <p><strong>The following api can be used to create a dense tensor given a sparse tensor</strong></p>
+<dl class="py class">
+<dt class="sig sig-object py" id="aimet_torch.nn.modules.custom.ScatterDense">
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">aimet_torch.nn.modules.custom.</span></span><span class="sig-name descname"><span class="pre">ScatterDense</span></span><a class="reference internal" href="../_modules/aimet_torch/v1/nn/modules/custom.html#ScatterDense"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#aimet_torch.nn.modules.custom.ScatterDense" title="Permalink to this definition"></a></dt>
+<dd><p>ScatterDense custom implementation</p>
+<p>Initializes internal Module state, shared by both nn.Module and ScriptModule.</p>
+</dd></dl>
+
 </section>
 <section id="code-example">
 <h2>Code Example<a class="headerlink" href="#code-example" title="Permalink to this heading"></a></h2>
diff --git a/releases/1.35.1/install/index.html b/releases/1.35.1/install/index.html
index e16c583..ceeae0a 100644
--- a/releases/1.35.1/install/index.html
+++ b/releases/1.35.1/install/index.html
@@ -989,25 +989,25 @@ <h2>Release Packages<a class="headerlink" href="#release-packages" title="Permal
 </div>
 <p><strong>PyTorch</strong></p>
 <pre class="literal-block"># Pytorch 2.1 with CUDA 12.x
-python3 -m pip install https://github.com/quic/aimet/releases/download/1.35.1/aimet_torch-1.35.1.cu121-cp310-cp310-manylinux_2_34_x86_64.whl -f https://download.pytorch.org/whl/torch_stable.html
+python3 -m pip install https://github.com/quic/aimet/releases/download/1.35.1/aimet_torch-1.35.1+cu121-cp310-cp310-manylinux_2_34_x86_64.whl -f https://download.pytorch.org/whl/torch_stable.html
 
 # Pytorch 2.1 CPU only
-python3 -m pip install https://github.com/quic/aimet/releases/download/1.35.1/aimet_torch-1.35.1.cpu-cp310-cp310-manylinux_2_34_x86_64.whl -f https://download.pytorch.org/whl/torch_stable.html
+python3 -m pip install https://github.com/quic/aimet/releases/download/1.35.1/aimet_torch-1.35.1+cpu-cp310-cp310-manylinux_2_34_x86_64.whl -f https://download.pytorch.org/whl/torch_stable.html
 
 # Pytorch 1.13 with CUDA 11.x
-python3 -m pip install https://github.com/quic/aimet/releases/download/1.35.1/aimet_torch-1.35.1.cu117-cp310-cp310-manylinux_2_34_x86_64.whl -f https://download.pytorch.org/whl/torch_stable.html</pre>
+python3 -m pip install https://github.com/quic/aimet/releases/download/1.35.1/aimet_torch-1.35.1+cu117-cp310-cp310-manylinux_2_34_x86_64.whl -f https://download.pytorch.org/whl/torch_stable.html</pre>
 <p><strong>TensorFlow</strong></p>
 <pre class="literal-block"># Tensorflow 2.10 GPU with CUDA 11.x
-python3 -m pip install https://github.com/quic/aimet/releases/download/1.35.1/aimet_tensorflow-1.35.1.cu118-cp310-cp310-manylinux_2_34_x86_64.whl
+python3 -m pip install https://github.com/quic/aimet/releases/download/1.35.1/aimet_tensorflow-1.35.1+cu118-cp310-cp310-manylinux_2_34_x86_64.whl
 
 # Tensorflow 2.10 CPU only
-python3 -m pip install https://github.com/quic/aimet/releases/download/1.35.1/aimet_tensorflow-1.35.1.cpu-cp310-cp310-manylinux_2_34_x86_64.whl</pre>
+python3 -m pip install https://github.com/quic/aimet/releases/download/1.35.1/aimet_tensorflow-1.35.1+cpu-cp310-cp310-manylinux_2_34_x86_64.whl</pre>
 <p><strong>ONNX</strong></p>
 <pre class="literal-block"># ONNX 1.16 GPU with CUDA 11.x
-python3 -m pip install https://github.com/quic/aimet/releases/download/1.35.1/aimet_onnx-1.35.1.cu117-cp310-cp310-manylinux_2_34_x86_64.whl -f https://download.pytorch.org/whl/torch_stable.html
+python3 -m pip install https://github.com/quic/aimet/releases/download/1.35.1/aimet_onnx-1.35.1+cu118-cp310-cp310-manylinux_2_34_x86_64.whl -f https://download.pytorch.org/whl/torch_stable.html
 
 # ONNX 1.16 CPU
-python3 -m pip install https://github.com/quic/aimet/releases/download/1.35.1/aimet_onnx-1.35.1.cpu-cp310-cp310-manylinux_2_34_x86_64.whl -f https://download.pytorch.org/whl/torch_stable.html</pre>
+python3 -m pip install https://github.com/quic/aimet/releases/download/1.35.1/aimet_onnx-1.35.1+cpu-cp310-cp310-manylinux_2_34_x86_64.whl -f https://download.pytorch.org/whl/torch_stable.html</pre>
 <p>For older versions, please browse the releases at <a class="reference external" href="https://github.com/quic/aimet/releases">https://github.com/quic/aimet/releases</a> and follow the documentation corresponding to that release to select and install the appropriate package.</p>
 </section>
 <section id="system-requirements">
diff --git a/releases/1.35.1/install/install_docker.html b/releases/1.35.1/install/install_docker.html
index f627b09..5ab4578 100644
--- a/releases/1.35.1/install/install_docker.html
+++ b/releases/1.35.1/install/install_docker.html
@@ -1072,14 +1072,14 @@ <h3>From Release Package<a class="headerlink" href="#from-release-package" title
 </dd>
 </dl>
 <p>Set the package details as follows:</p>
-<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span><span class="c1"># Set the release tag ex. &quot;1.34.0&quot;</span>
+<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span><span class="c1"># Set the release tag ex. &quot;1.35.1&quot;</span>
 <span class="nb">export</span><span class="w"> </span><span class="nv">release_tag</span><span class="o">=</span><span class="s2">&quot;&lt;version release tag&gt;&quot;</span>
 
 <span class="c1"># Construct the download root URL</span>
 <span class="nb">export</span><span class="w"> </span><span class="nv">download_url</span><span class="o">=</span><span class="s2">&quot;https://github.com/quic/aimet/releases/download/</span><span class="si">${</span><span class="nv">release_tag</span><span class="si">}</span><span class="s2">&quot;</span>
 
 <span class="c1"># Set the wheel file name with extension</span>
-<span class="c1"># ex. &quot;aimet_torch-1.34.0.cu121-cp310-cp310-manylinux_2_34_x86_64.whl&quot;</span>
+<span class="c1"># ex. &quot;aimet_torch-1.35.1+cu121-cp310-cp310-manylinux_2_34_x86_64.whl&quot;</span>
 <span class="nb">export</span><span class="w"> </span><span class="nv">wheel_file_name</span><span class="o">=</span><span class="s2">&quot;&lt;wheel file name&gt;&quot;</span>
 
 <span class="c1"># NOTE: Do the following ONLY for the PyTorch and ONNX variant packages!</span>
diff --git a/releases/1.35.1/install/install_host.html b/releases/1.35.1/install/install_host.html
index b25510d..e3419b2 100644
--- a/releases/1.35.1/install/install_host.html
+++ b/releases/1.35.1/install/install_host.html
@@ -1056,14 +1056,14 @@ <h3>From Release Package<a class="headerlink" href="#from-release-package" title
 </dd>
 </dl>
 <p>Set the package details as follows:</p>
-<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span><span class="c1"># Set the release tag ex. &quot;1.34.0&quot;</span>
+<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span><span class="c1"># Set the release tag ex. &quot;1.35.1&quot;</span>
 <span class="nb">export</span><span class="w"> </span><span class="nv">release_tag</span><span class="o">=</span><span class="s2">&quot;&lt;version release tag&gt;&quot;</span>
 
 <span class="c1"># Construct the download root URL</span>
 <span class="nb">export</span><span class="w"> </span><span class="nv">download_url</span><span class="o">=</span><span class="s2">&quot;https://github.com/quic/aimet/releases/download/</span><span class="si">${</span><span class="nv">release_tag</span><span class="si">}</span><span class="s2">&quot;</span>
 
 <span class="c1"># Set the wheel file name with extension</span>
-<span class="c1"># ex. &quot;aimet_torch-1.33.0.cu121-cp310-cp310-manylinux_2_34_x86_64.whl&quot;</span>
+<span class="c1"># ex. &quot;aimet_torch-1.35.1+cu121-cp310-cp310-manylinux_2_34_x86_64.whl&quot;</span>
 <span class="nb">export</span><span class="w"> </span><span class="nv">wheel_file_name</span><span class="o">=</span><span class="s2">&quot;&lt;wheel file name&gt;&quot;</span>
 
 <span class="c1"># NOTE: Do the following ONLY for the PyTorch and ONNX variant packages!</span>
diff --git a/releases/1.35.1/searchindex.js b/releases/1.35.1/searchindex.js
index e2a506a..1ddac88 100644
--- a/releases/1.35.1/searchindex.js
+++ b/releases/1.35.1/searchindex.js
@@ -1 +1 @@
-Search.setIndex({"docnames": ["Examples/onnx/quantization/AMP", "Examples/onnx/quantization/adaround", "Examples/onnx/quantization/cle", "Examples/onnx/quantization/quantsim", "Examples/tensorflow/quantization/keras/KerasAMP", "Examples/tensorflow/quantization/keras/adaround", "Examples/tensorflow/quantization/keras/autoquant", "Examples/tensorflow/quantization/keras/bn_reestimation", "Examples/tensorflow/quantization/keras/keras_transformer_qat", "Examples/tensorflow/quantization/keras/model_preparer", "Examples/tensorflow/quantization/keras/qat", "Examples/tensorflow/quantization/keras/qat_range_learning", "Examples/tensorflow/quantization/keras/quant_analyzer", "Examples/tensorflow/quantization/keras/quantsim_adaround_pcq", "Examples/tensorflow/quantization/keras/quantsim_cle", "Examples/torch/compression/channel_pruning", "Examples/torch/compression/spatial_svd", "Examples/torch/compression/spatial_svd_channel_pruning", "Examples/torch/quantization/AMP", "Examples/torch/quantization/adaround", "Examples/torch/quantization/autoquant", "Examples/torch/quantization/bn_reestimation", "Examples/torch/quantization/cle_bc", "Examples/torch/quantization/qat", "Examples/torch/quantization/qat_range_learning", "Examples/torch/quantization/quant_analyzer", "api_docs/index", "api_docs/keras", "api_docs/keras_adaround", "api_docs/keras_batchnorm_re_estimation", "api_docs/keras_compression", "api_docs/keras_cross_layer_equalization", "api_docs/keras_layer_output_generation", "api_docs/keras_mixed_precision", "api_docs/keras_model_guidelines", "api_docs/keras_model_preparer", "api_docs/keras_primitive_apis_cle", "api_docs/keras_quant_analyzer", "api_docs/keras_quantization", "api_docs/keras_quantsim", "api_docs/onnx", "api_docs/onnx_adaround", "api_docs/onnx_auto_quant", "api_docs/onnx_cross_layer_equalization", "api_docs/onnx_layer_output_generation", "api_docs/onnx_mixed_precision", "api_docs/onnx_quant_analyzer", "api_docs/onnx_quantization", "api_docs/onnx_quantsim", "api_docs/quantization_encoding_specification", "api_docs/torch", "api_docs/torch_adaround", "api_docs/torch_architecture_checker", "api_docs/torch_auto_quant", "api_docs/torch_batchnorm_re_estimation", "api_docs/torch_bias_correction", "api_docs/torch_compress", "api_docs/torch_cross_layer_equalization", "api_docs/torch_layer_output_generation", "api_docs/torch_mixed_precision", "api_docs/torch_model_guidelines", "api_docs/torch_model_preparer", "api_docs/torch_model_validator", "api_docs/torch_multi_gpu", "api_docs/torch_peft_lora", "api_docs/torch_primitive_apis_cle", "api_docs/torch_quant_analyzer", "api_docs/torch_quantization", "api_docs/torch_quantsim", "api_docs/torch_spconv_custom_onnx_export", "api_docs/torch_visualization_compression", "api_docs/torch_visualization_quantization", "api_docs/v2_migrgation_guide", "install/index", "install/install_docker", "install/install_host", "toplevelhidden", "torch_docs/api/nn.quantization_mixin", "torch_docs/api/quantization/affine/index", "torch_docs/api/quantization/float/FloatQuantizeDequantize", "torch_docs/api/quantization/float/index", "torch_docs/api/quantization/tensor", "torch_docs/api/visualization_tools", "torch_docs/blockwise_quantization", "torch_docs/encoding_analyzer", "torch_docs/examples/ptq", "torch_docs/gptvq", "torch_docs/index", "torch_docs/quantized_modules", "torch_docs/quantizer", "torch_docs/tutorials/quickstart_guide", "user_guide/adaround", "user_guide/auto_quant", "user_guide/bn_reestimation", "user_guide/channel_pruning", "user_guide/compression_feature_guidebook", "user_guide/examples", "user_guide/greedy_compression_ratio_selection", "user_guide/index", "user_guide/known_issues", "user_guide/model_compression", "user_guide/model_guidelines", "user_guide/model_quantization", "user_guide/post_training_quant_techniques", "user_guide/quant_analyzer", "user_guide/quantization_aware_training", "user_guide/quantization_configuration", "user_guide/quantization_feature_guidebook", "user_guide/quantization_sim", "user_guide/release_notes", "user_guide/spatial_svd", "user_guide/visualization_compression", "user_guide/visualization_quant", "user_guide/weight_svd", "user_guide/winnowing"], "filenames": ["Examples/onnx/quantization/AMP.ipynb", "Examples/onnx/quantization/adaround.ipynb", "Examples/onnx/quantization/cle.ipynb", "Examples/onnx/quantization/quantsim.ipynb", "Examples/tensorflow/quantization/keras/KerasAMP.ipynb", "Examples/tensorflow/quantization/keras/adaround.ipynb", "Examples/tensorflow/quantization/keras/autoquant.ipynb", "Examples/tensorflow/quantization/keras/bn_reestimation.ipynb", "Examples/tensorflow/quantization/keras/keras_transformer_qat.ipynb", "Examples/tensorflow/quantization/keras/model_preparer.ipynb", "Examples/tensorflow/quantization/keras/qat.ipynb", "Examples/tensorflow/quantization/keras/qat_range_learning.ipynb", "Examples/tensorflow/quantization/keras/quant_analyzer.ipynb", "Examples/tensorflow/quantization/keras/quantsim_adaround_pcq.ipynb", "Examples/tensorflow/quantization/keras/quantsim_cle.ipynb", "Examples/torch/compression/channel_pruning.ipynb", "Examples/torch/compression/spatial_svd.ipynb", "Examples/torch/compression/spatial_svd_channel_pruning.ipynb", "Examples/torch/quantization/AMP.ipynb", "Examples/torch/quantization/adaround.ipynb", "Examples/torch/quantization/autoquant.ipynb", "Examples/torch/quantization/bn_reestimation.ipynb", "Examples/torch/quantization/cle_bc.ipynb", "Examples/torch/quantization/qat.ipynb", "Examples/torch/quantization/qat_range_learning.ipynb", "Examples/torch/quantization/quant_analyzer.ipynb", "api_docs/index.rst", "api_docs/keras.rst", "api_docs/keras_adaround.rst", "api_docs/keras_batchnorm_re_estimation.rst", "api_docs/keras_compression.rst", "api_docs/keras_cross_layer_equalization.rst", "api_docs/keras_layer_output_generation.rst", "api_docs/keras_mixed_precision.rst", "api_docs/keras_model_guidelines.rst", "api_docs/keras_model_preparer.rst", "api_docs/keras_primitive_apis_cle.rst", "api_docs/keras_quant_analyzer.rst", "api_docs/keras_quantization.rst", "api_docs/keras_quantsim.rst", "api_docs/onnx.rst", "api_docs/onnx_adaround.rst", "api_docs/onnx_auto_quant.rst", "api_docs/onnx_cross_layer_equalization.rst", "api_docs/onnx_layer_output_generation.rst", "api_docs/onnx_mixed_precision.rst", "api_docs/onnx_quant_analyzer.rst", "api_docs/onnx_quantization.rst", "api_docs/onnx_quantsim.rst", "api_docs/quantization_encoding_specification.rst", "api_docs/torch.rst", "api_docs/torch_adaround.rst", "api_docs/torch_architecture_checker.rst", "api_docs/torch_auto_quant.rst", "api_docs/torch_batchnorm_re_estimation.rst", "api_docs/torch_bias_correction.rst", "api_docs/torch_compress.rst", "api_docs/torch_cross_layer_equalization.rst", "api_docs/torch_layer_output_generation.rst", "api_docs/torch_mixed_precision.rst", "api_docs/torch_model_guidelines.rst", "api_docs/torch_model_preparer.rst", "api_docs/torch_model_validator.rst", "api_docs/torch_multi_gpu.rst", "api_docs/torch_peft_lora.rst", "api_docs/torch_primitive_apis_cle.rst", "api_docs/torch_quant_analyzer.rst", "api_docs/torch_quantization.rst", "api_docs/torch_quantsim.rst", "api_docs/torch_spconv_custom_onnx_export.rst", "api_docs/torch_visualization_compression.rst", "api_docs/torch_visualization_quantization.rst", "api_docs/v2_migrgation_guide.rst", "install/index.rst", "install/install_docker.rst", "install/install_host.rst", "toplevelhidden.rst", "torch_docs/api/nn.quantization_mixin.rst", "torch_docs/api/quantization/affine/index.rst", "torch_docs/api/quantization/float/FloatQuantizeDequantize.rst", "torch_docs/api/quantization/float/index.rst", "torch_docs/api/quantization/tensor.rst", "torch_docs/api/visualization_tools.rst", "torch_docs/blockwise_quantization.rst", "torch_docs/encoding_analyzer.rst", "torch_docs/examples/ptq.rst", "torch_docs/gptvq.rst", "torch_docs/index.rst", "torch_docs/quantized_modules.rst", "torch_docs/quantizer.rst", "torch_docs/tutorials/quickstart_guide.rst", "user_guide/adaround.rst", "user_guide/auto_quant.rst", "user_guide/bn_reestimation.rst", "user_guide/channel_pruning.rst", "user_guide/compression_feature_guidebook.rst", "user_guide/examples.rst", "user_guide/greedy_compression_ratio_selection.rst", "user_guide/index.rst", "user_guide/known_issues.rst", "user_guide/model_compression.rst", "user_guide/model_guidelines.rst", "user_guide/model_quantization.rst", "user_guide/post_training_quant_techniques.rst", "user_guide/quant_analyzer.rst", "user_guide/quantization_aware_training.rst", "user_guide/quantization_configuration.rst", "user_guide/quantization_feature_guidebook.rst", "user_guide/quantization_sim.rst", "user_guide/release_notes.rst", "user_guide/spatial_svd.rst", "user_guide/visualization_compression.rst", "user_guide/visualization_quant.rst", "user_guide/weight_svd.rst", "user_guide/winnowing.rst"], "titles": ["Automatic Mixed-Precision (AMP)", "Adaptive Rounding (AdaRound)", "Cross-Layer Equalization", "Quantization simulation", "Automatic Mixed-Precision (AMP)", "Adaptive Rounding (AdaRound)", "AutoQuant", "Quantization-Aware Training with BatchNorm Re-estimation", "Quantization-Aware Training with a Keras Transformer Model", "Keras Model Preparer", "Quantization-aware training", "Quantization-Aware training with range learning", "Quant Analyzer", "Quantsim and Adaround - Per Channel Quantization (PCQ)", "Cross-Layer Equalization with QuantSim", "Model compression using channel pruning", "Model compression using spatial SVD", "Model compression using spatial SVD and channel pruning", "Automatic Mixed-Precision (AMP)", "Adaptive Rounding (AdaRound)", "AutoQuant", "Quantization-Aware Training with BatchNorm Re-estimation", "Cross-Layer Equalization and Bias Correction", "Quantization-aware training", "Quantization-aware training with range learning", "Quant Analyzer", "Welcome to AI Model Efficiency Toolkit API Docs!", "AIMET TensorFlow APIs", "AIMET TensorFlow AdaRound API", "AIMET TensorFlow BatchNorm Re-estimation APIs", "AIMET TensorFlow Compression API", "AIMET TensorFlow Cross Layer Equalization APIs", "AIMET TensorFlow Layer Output Generation API", "AIMET TensorFlow Mixed Precision API", "TensorFlow Model Guidelines", "TensorFlow Model Preparer API", "AIMET TensorFlow Cross Layer Equalization Primitive API", "AIMET TensorFlow Quant Analyzer API", "AIMET TensorFlow Quantization APIs", "AIMET TensorFlow Quantization SIM API", "AIMET ONNX APIs", "AIMET ONNX AdaRound API", "AIMET ONNX AutoQuant API", "AIMET ONNX Cross Layer Equalization APIs", "AIMET ONNX Layer Output Generation API", "AIMET ONNX Mixed Precision API", "AIMET ONNX Quant Analyzer API", "AIMET ONNX Quantization APIs", "AIMET ONNX Quantization SIM API", "Encoding Format Specification", "AIMET PyTorch APIs", "AIMET PyTorch AdaRound API", "Architecture Checker API", "AIMET PyTorch AutoQuant API", "AIMET PyTorch BatchNorm Re-estimation APIs", "AIMET PyTorch Bias Correction API", "AIMET PyTorch Compression API", "AIMET PyTorch Cross Layer Equalization APIs", "AIMET PyTorch Layer Output Generation API", "AIMET PyTorch Mixed Precision API", "PyTorch Model Guidelines", "Model Preparer API", "Model Validator Utility", "PyTorch Multi-GPU support", "PEFT LoRA", "AIMET PyTorch Cross Layer Equalization Primitive API", "AIMET PyTorch Quant Analyzer API", "AIMET PyTorch Quantization APIs", "AIMET PyTorch Quantization SIM API", "AIMET Torch SparseConvolution custom onnx export", "AIMET Visualization Compression API", "AIMET Visualization for Quantization API", "Migrate to aimet_torch.v2", "AIMET Installation", "AIMET Installation in Docker", "AIMET Installation and Setup", "&lt;no title&gt;", "QuantizationMixin", "quantization.affine", "FloatQuantizeDequantize", "quantization.float", "quantization.tensor", "Visualization Tools", "Blockwise Quantization", "Encoding Analyzers", "Post-Training Quantization", "GPTVQ", "AIMET: AI Model Efficiency Toolkit Documentation", "Quantized Modules", "Quantizers", "Quickstart Guide", "AIMET AdaRound", "AIMET AutoQuant", "AIMET Batch Norm Re-estimation", "AIMET channel pruning", "AIMET Compression Features Guidebook", "AIMET examples", "AIMET greedy compression ratio selection", "AI Model Efficiency Toolkit User Guide", "AIMET Known Issues", "AIMET model compression", "Model Guidelines for PyTorch", "AIMET model quantization", "AIMET post-training quantization techniques", "AIMET QuantAnalyzer", "AIMET quantization aware training", "Quantization simulation configuration", "AIMET quantization diagnostics", "AIMET quantization simulation", "AIMET Release Notes", "AIMET spatial SVD", "AIMET visualization", "AIMET visualization for quantization", "AIMET weight SVD", "AIMET winnowing"], "terms": {"show": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 29, 31, 41, 45, 51, 52, 53, 54, 57, 59, 62, 64, 66, 68, 71, 83, 86, 87, 90, 93, 97, 98, 103, 107], "work": [0, 1, 3, 4, 5, 6, 7, 8, 10, 11, 12, 15, 16, 17, 18, 19, 20, 21, 23, 24, 25, 26, 33, 39, 41, 48, 51, 62, 63, 68, 83, 96, 100, 103], "code": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 18, 19, 20, 21, 22, 23, 24, 25, 83, 90, 91], "how": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 29, 31, 33, 41, 45, 48, 49, 51, 52, 53, 54, 55, 57, 59, 62, 64, 66, 67, 68, 69, 72, 83, 86, 88, 90, 96, 100, 102, 103, 104, 106, 107, 108, 110, 113], "us": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 18, 19, 20, 21, 22, 23, 24, 25, 26, 28, 29, 30, 31, 32, 33, 34, 35, 37, 38, 39, 41, 42, 43, 44, 45, 46, 48, 49, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 72, 73, 75, 77, 78, 81, 82, 83, 84, 86, 87, 88, 89, 90, 93, 95, 96, 98, 101, 103, 104, 105, 106, 107, 108, 109, 111, 112], "aimet": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 34, 35, 49, 52, 60, 61, 62, 63, 64, 72, 77, 86, 88, 90, 98, 101, 106], "perform": [0, 1, 2, 3, 4, 5, 6, 8, 12, 13, 14, 15, 16, 17, 18, 19, 20, 22, 25, 28, 29, 31, 33, 37, 41, 42, 43, 45, 46, 49, 51, 52, 54, 55, 56, 57, 59, 63, 64, 65, 66, 67, 68, 71, 77, 78, 83, 86, 88, 89, 90, 92, 93, 94, 95, 97, 100, 102, 103, 104, 105, 107], "auto": [0, 4, 15, 16, 17, 18, 26, 30, 31, 36, 42, 43, 45, 48, 49, 56, 57, 59, 65, 70], "techniqu": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 23, 24, 28, 30, 31, 38, 41, 42, 43, 47, 51, 53, 55, 56, 57, 66, 67, 87, 90, 92, 94, 95, 96, 98, 102, 104, 105, 107, 108, 109, 110, 113], "where": [0, 1, 2, 3, 4, 5, 6, 7, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 30, 33, 39, 41, 45, 49, 51, 56, 59, 60, 61, 64, 68, 78, 79, 80, 86, 89, 90, 93, 97, 104, 110, 111, 113, 114], "given": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 30, 31, 33, 36, 39, 42, 43, 45, 48, 49, 51, 53, 54, 56, 57, 59, 65, 68, 69, 77, 82, 83, 84, 88, 92, 97, 100, 103], "target": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 30, 32, 35, 39, 42, 44, 48, 49, 51, 54, 56, 58, 59, 64, 68, 87, 93, 95, 97, 98, 100, 102, 107, 108, 109], "find": [0, 1, 5, 6, 7, 8, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 22, 23, 24, 33, 36, 45, 51, 55, 59, 62, 65, 68, 71, 97, 102, 104, 105, 108], "bit": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 33, 41, 45, 46, 49, 51, 59, 66, 73, 79, 80, 83, 90, 91, 93, 102, 107, 108, 109], "per": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 30, 37, 45, 46, 49, 54, 56, 58, 59, 64, 66, 68, 83, 86, 88, 93, 103, 104, 106, 107, 108, 109, 111], "meet": [0, 4, 18, 42, 53, 59, 73, 92, 95, 97], "while": [0, 1, 2, 3, 4, 5, 8, 10, 11, 13, 14, 15, 16, 17, 18, 19, 22, 23, 24, 30, 51, 56, 64, 83, 88, 91, 97, 101, 105, 107], "try": [0, 1, 2, 3, 4, 13, 15, 16, 17, 18, 30, 52, 56, 70, 92, 94, 95, 100, 102, 107], "optim": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 30, 33, 37, 38, 39, 41, 42, 45, 47, 48, 51, 52, 53, 56, 59, 67, 68, 70, 71, 83, 86, 90, 91, 92, 98, 100, 102, 105, 108, 109, 111], "infer": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 30, 33, 38, 39, 41, 42, 46, 47, 48, 49, 51, 67, 68, 69, 83, 86, 87, 90, 93, 95, 98, 103, 105, 108, 109], "speed": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 30, 51, 56, 64, 91, 100, 103, 105, 109], "As": [0, 2, 4, 7, 8, 10, 11, 13, 14, 15, 16, 17, 18, 21, 22, 23, 24, 60, 68, 77, 83, 86, 92, 95, 97, 103, 104, 108], "sai": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 61, 95], "particular": [0, 4, 18, 83, 102, 106], "desir": [0, 4, 15, 16, 17, 18, 30, 39, 46, 56, 66, 68, 74, 83, 90, 95, 100, 102, 107], "when": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 30, 33, 34, 35, 37, 38, 39, 42, 43, 45, 46, 49, 56, 57, 59, 60, 61, 66, 67, 68, 77, 83, 86, 87, 88, 90, 91, 100, 102, 103, 104, 105, 106, 107, 108, 111, 112, 114], "int8": [0, 1, 2, 3, 4, 13, 18, 19, 22, 23, 24, 51, 81, 105, 108, 112], "The": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 28, 29, 30, 32, 33, 35, 36, 37, 39, 41, 43, 44, 45, 46, 48, 49, 51, 52, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 68, 69, 72, 73, 74, 75, 77, 78, 79, 80, 81, 82, 83, 84, 86, 87, 88, 90, 91, 92, 93, 94, 95, 96, 97, 98, 100, 101, 102, 103, 104, 105, 106, 107, 108, 110, 111, 112, 113, 114], "featur": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 34, 35, 36, 38, 43, 49, 51, 57, 60, 61, 62, 63, 65, 67, 68, 69, 72, 82, 83, 86, 91, 92, 93, 96, 100, 103, 104, 107, 108, 109, 111, 112], "minim": [0, 3, 4, 10, 11, 18, 23, 24, 28, 51, 68, 87, 98, 102, 108], "set": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 30, 33, 35, 36, 41, 42, 45, 46, 48, 49, 51, 53, 56, 59, 61, 62, 64, 65, 66, 68, 72, 75, 77, 82, 83, 86, 88, 89, 91, 95, 96, 97, 100, 101, 103, 104, 105, 106, 107], "need": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 30, 32, 33, 34, 35, 36, 39, 41, 46, 49, 51, 55, 56, 58, 63, 64, 65, 66, 67, 68, 69, 72, 73, 74, 75, 83, 86, 90, 102, 103, 105, 106, 108, 109, 112], "int16": [0, 4, 18], "get": [0, 1, 2, 3, 4, 7, 8, 9, 12, 30, 32, 33, 36, 44, 45, 52, 56, 58, 59, 61, 64, 68, 71, 73, 74, 75, 86, 100, 112], "It": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 18, 19, 22, 23, 24, 25, 30, 31, 33, 35, 36, 37, 41, 42, 43, 44, 45, 46, 48, 49, 51, 56, 61, 65, 66, 68, 90, 93, 94, 97, 105, 114], "should": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 30, 33, 34, 35, 37, 38, 39, 41, 42, 46, 48, 49, 51, 53, 56, 58, 60, 61, 64, 66, 67, 68, 72, 77, 83, 86, 88, 90, 95], "note": [0, 1, 2, 3, 4, 5, 6, 7, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 33, 35, 36, 37, 39, 41, 42, 43, 44, 45, 46, 48, 53, 56, 57, 59, 63, 64, 65, 66, 68, 69, 72, 74, 75, 83, 86, 90, 98, 111], "choos": [0, 4, 15, 16, 17, 18, 48, 68, 71, 83, 94, 95, 100], "higher": [0, 4, 15, 16, 17, 18, 41, 51, 56, 59, 83, 84, 93, 97, 105, 107], "some": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 22, 23, 24, 25, 30, 35, 36, 38, 39, 51, 56, 61, 65, 67, 68, 71, 74, 75, 88, 90, 91, 95, 97, 101, 102, 103, 105, 107, 108, 114], "necessarili": [0, 4, 18], "involv": [0, 4, 18, 33, 45, 59, 72, 84, 90, 102, 107], "trade": [0, 4, 18, 28, 33, 41, 51], "off": [0, 4, 18, 28, 39, 41, 51, 68, 103], "lower": [0, 4, 13, 18, 33, 41, 51, 72, 83, 97, 102, 107], "sec": [0, 4, 13, 18], "vice": [0, 4, 18, 64, 97, 107, 108], "versa": [0, 4, 18, 64, 97, 107, 108], "altern": [0, 4, 15, 16, 17, 18, 75, 83], "can": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 28, 30, 31, 32, 33, 34, 35, 36, 38, 39, 41, 44, 45, 46, 48, 49, 51, 52, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 74, 78, 81, 83, 86, 87, 88, 89, 90, 92, 93, 95, 97, 98, 100, 102, 103, 104, 105, 106, 107, 108, 111, 112, 114], "gener": [0, 4, 8, 18, 20, 26, 33, 39, 45, 48, 49, 52, 59, 64, 69, 77, 78, 83, 86, 89, 90, 96, 100, 102, 104, 105, 106, 107, 108], "pareto": [0, 4, 18, 33, 45, 59], "curv": [0, 4, 18, 33, 45, 59, 97], "v": [0, 4, 12, 18, 25, 28, 33, 41, 45, 51, 59, 74, 83], "op": [0, 1, 2, 3, 5, 7, 8, 10, 11, 13, 14, 15, 17, 18, 19, 20, 21, 22, 23, 24, 28, 30, 33, 36, 39, 41, 42, 45, 48, 51, 52, 59, 62, 68, 90, 106, 108, 109], "guid": [0, 4, 6, 18, 19, 20, 22, 23, 24, 25, 30, 56, 67, 72, 87, 95, 103, 107, 109], "user": [0, 1, 2, 3, 4, 5, 6, 7, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 29, 30, 33, 34, 35, 36, 37, 38, 45, 46, 48, 49, 54, 56, 59, 60, 61, 63, 65, 67, 70, 71, 72, 74, 77, 83, 86, 87, 91, 95, 100, 104, 107, 109], "decid": [0, 1, 2, 3, 4, 5, 13, 15, 16, 17, 18, 19, 22, 23, 24, 25, 91, 111], "right": [0, 4, 6, 8, 18, 20, 77, 78, 79, 80, 88, 89, 114], "oper": [0, 3, 4, 9, 10, 11, 18, 23, 24, 30, 35, 60, 61, 62, 72, 77, 88, 90, 101, 102, 103, 106, 107], "point": [0, 1, 2, 4, 5, 6, 7, 8, 10, 11, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 33, 35, 36, 37, 38, 45, 46, 47, 49, 55, 59, 64, 65, 66, 67, 68, 72, 77, 81, 83, 87, 98, 102, 104, 107, 108, 112], "tradeoff": [0, 4, 18], "specif": [0, 1, 4, 5, 7, 9, 13, 18, 19, 21, 30, 33, 35, 39, 56, 68, 77, 83, 88, 90, 92, 93, 98, 101, 102, 103, 106, 109], "abov": [0, 4, 12, 13, 15, 16, 17, 18, 25, 28, 37, 46, 51, 56, 61, 63, 66, 68, 74, 75, 83, 86, 87, 100, 103, 108, 111, 114], "cover": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 18, 19, 21, 22, 23, 24, 25, 51, 68, 83, 108], "follow": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 30, 31, 32, 33, 34, 35, 36, 38, 39, 43, 44, 46, 47, 48, 49, 51, 52, 53, 54, 55, 56, 57, 58, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 72, 73, 74, 75, 77, 83, 86, 88, 91, 93, 94, 95, 96, 97, 98, 100, 101, 102, 104, 105, 106, 107, 108, 110, 113, 114], "instanti": [0, 12, 13, 18, 21, 25, 60, 63, 64, 83, 86, 90, 111], "": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 28, 30, 31, 33, 34, 35, 36, 37, 39, 41, 42, 45, 46, 48, 49, 51, 54, 55, 56, 59, 61, 65, 66, 68, 69, 71, 75, 77, 83, 87, 88, 89, 90, 94, 95, 97, 99, 100, 102, 103, 104, 105, 107, 108, 112, 114], "fake": [0, 1, 2, 3, 5, 7, 8, 10, 11, 13, 14, 18, 19, 20, 21, 22, 23, 24, 51, 59, 68, 78, 79, 80, 89, 90], "insert": [0, 1, 2, 3, 5, 7, 8, 10, 11, 13, 14, 15, 17, 18, 19, 21, 22, 23, 24, 51, 61, 68, 102, 108], "design": [0, 4, 9, 12, 13, 18, 25, 26, 62, 67, 103], "state": [0, 1, 2, 3, 4, 5, 6, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 22, 23, 24, 25, 33, 69, 90], "art": [0, 1, 2, 3, 4, 5, 6, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 22, 23, 24, 25, 90], "result": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 30, 33, 35, 37, 42, 45, 46, 51, 53, 56, 59, 66, 68, 77, 81, 83, 84, 86, 91, 92, 94, 95, 98, 100, 103, 104, 105, 106, 108], "For": [0, 4, 7, 8, 9, 12, 13, 18, 21, 25, 28, 29, 30, 31, 32, 34, 35, 44, 46, 48, 51, 53, 54, 56, 57, 58, 60, 61, 62, 63, 64, 66, 67, 68, 71, 72, 73, 74, 75, 77, 83, 86, 87, 88, 90, 91, 94, 95, 96, 97, 98, 99, 100, 102, 104, 106, 108], "rel": [0, 1, 2, 3, 4, 5, 6, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 22, 23, 24, 25, 30, 33, 56, 71, 95, 107, 112], "friendli": [0, 1, 2, 3, 4, 5, 6, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 22, 23, 24, 25, 67, 92, 102, 103], "like": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 29, 31, 35, 36, 45, 51, 57, 59, 65, 68, 72, 83, 86, 87, 90, 92, 98, 100, 102, 104, 105, 106], "resnet18": [0, 1, 2, 3, 5, 6, 10, 11, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 51, 53, 54, 57, 65, 66, 68, 70, 71], "also": [0, 1, 2, 3, 4, 5, 6, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 22, 23, 24, 25, 28, 37, 39, 41, 46, 49, 51, 53, 60, 61, 66, 68, 74, 75, 83, 94, 100, 102, 104, 106, 108, 109, 112, 114], "number": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 28, 29, 30, 33, 35, 37, 39, 41, 45, 46, 48, 51, 54, 55, 56, 59, 61, 66, 68, 74, 77, 78, 79, 80, 83, 84, 88, 91, 97, 98, 100, 105, 108, 109, 111, 114], "sampl": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 30, 33, 36, 37, 39, 41, 45, 46, 48, 49, 51, 53, 55, 59, 66, 68, 82, 87, 88, 90, 94, 103, 104, 105, 108], "ar": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 41, 44, 45, 46, 48, 51, 52, 54, 55, 56, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 72, 73, 74, 75, 77, 78, 79, 80, 83, 84, 86, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 100, 101, 102, 103, 104, 105, 106, 107, 108, 111, 112, 114], "deliber": [0, 4, 12, 13, 18, 25], "chosen": [0, 1, 2, 3, 4, 5, 6, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 22, 23, 24, 25, 96], "have": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 35, 43, 46, 49, 51, 52, 57, 58, 61, 62, 66, 68, 71, 72, 75, 77, 82, 83, 90, 100, 103, 104, 107], "execut": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 33, 42, 45, 51, 53, 59, 61, 70, 75, 90, 96, 111], "more": [0, 4, 7, 8, 9, 12, 13, 18, 21, 25, 28, 30, 31, 36, 37, 39, 41, 42, 43, 46, 48, 49, 51, 52, 53, 55, 56, 57, 59, 62, 65, 66, 67, 68, 72, 73, 83, 86, 87, 88, 90, 94, 95, 97, 100, 102, 103, 104, 106, 107, 108, 111], "quickli": [0, 4, 12, 13, 18, 25], "reli": [0, 1, 2, 3, 4, 7, 8, 12, 13, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 72], "imagenet": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 30, 33, 48, 51, 54, 55, 68, 96], "task": [0, 1, 2, 3, 4, 5, 6, 7, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 49, 111, 112], "imag": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 33, 37, 46, 53, 55, 66, 73, 91, 96, 104], "classif": [0, 1, 2, 3, 4, 5, 6, 7, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 35, 100], "If": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 30, 31, 33, 34, 35, 36, 39, 41, 42, 45, 46, 48, 49, 51, 53, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 70, 71, 72, 74, 75, 77, 78, 79, 80, 83, 86, 88, 89, 90, 91, 92, 95, 97, 101, 102, 103, 104, 106, 107, 111, 112, 114], "you": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 30, 51, 56, 61, 63, 67, 68, 74, 75, 77, 86, 91, 92, 95, 96, 98, 100, 101, 102, 104, 105, 106, 107, 108, 111, 112], "alreadi": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 57, 65, 68, 74, 77, 107], "version": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 44, 51, 61, 67, 68, 72, 73, 74, 75, 77, 82, 83, 86, 88, 90, 96, 98, 105], "readili": [0, 4, 7, 12, 13, 18, 21, 25], "avail": [0, 1, 2, 3, 4, 7, 12, 13, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 31, 51, 53, 61, 66, 68, 73, 90, 101, 104, 106, 107], "pleas": [0, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 18, 21, 25, 26, 28, 29, 30, 31, 37, 39, 41, 42, 43, 46, 51, 53, 54, 55, 56, 57, 62, 64, 66, 67, 68, 69, 72, 73, 75, 87, 90, 103], "els": [0, 1, 2, 3, 4, 5, 7, 10, 11, 12, 13, 14, 18, 19, 21, 22, 23, 24, 25, 30, 33, 36, 42, 45, 54, 59, 61, 62, 90, 103], "download": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 73, 74, 75, 90], "from": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 28, 29, 30, 31, 32, 33, 35, 36, 37, 39, 41, 42, 43, 44, 45, 46, 48, 49, 51, 52, 53, 54, 55, 56, 57, 58, 59, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 73, 77, 78, 79, 80, 81, 83, 84, 86, 88, 89, 90, 91, 94, 95, 96, 97, 98, 100, 101, 102, 103, 104, 105, 106, 107, 108, 114], "appropri": [0, 4, 7, 8, 12, 13, 18, 21, 25, 30, 33, 51, 56, 59, 68, 73, 75, 77, 83, 86, 88, 97, 107], "locat": [0, 4, 7, 12, 13, 18, 21, 25], "e": [0, 4, 7, 12, 13, 18, 21, 25, 28, 33, 37, 38, 39, 41, 45, 46, 48, 49, 51, 55, 59, 66, 68, 90, 93], "g": [0, 4, 7, 12, 13, 18, 21, 25, 28, 33, 37, 39, 41, 46, 48, 49, 51, 66, 68, 74, 90, 93], "http": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 61, 73, 74, 75, 96, 103, 109, 111], "net": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 96], "org": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 61, 73, 74, 75, 96, 103], "challeng": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25], "lsvrc": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25], "2012": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25], "index": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 46, 53, 66, 69, 86, 88, 109], "php": [0, 4, 7, 12, 13, 18, 21, 25, 96], "note1": [0, 18, 21, 25], "typic": [0, 1, 5, 6, 7, 8, 10, 11, 13, 15, 17, 18, 19, 20, 21, 22, 23, 24, 25, 35, 51, 68, 77, 83, 88, 90, 95, 102, 104, 105, 108], "ha": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 35, 36, 37, 41, 43, 46, 51, 52, 56, 57, 59, 61, 62, 64, 65, 66, 68, 71, 72, 77, 81, 83, 86, 90, 95, 97, 102, 103, 105, 108, 111, 114], "characterist": [0, 18, 21, 25], "dataload": [0, 1, 2, 3, 4, 5, 6, 7, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 33, 41, 42, 45, 46, 48, 51, 53, 54, 59, 66, 86, 90, 96, 104], "provid": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 30, 33, 35, 36, 37, 38, 41, 45, 46, 47, 48, 49, 51, 52, 53, 59, 62, 64, 66, 67, 68, 70, 72, 74, 75, 77, 79, 80, 83, 86, 87, 90, 91, 95, 96, 97, 100, 102, 103, 104, 106, 107, 108, 111, 112], "subfold": [0, 1, 2, 3, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25], "train": [0, 4, 9, 18, 20, 26, 28, 29, 30, 35, 37, 38, 42, 46, 47, 48, 51, 53, 54, 56, 63, 66, 67, 73, 87, 91, 92, 93, 96, 98, 100, 104, 107, 108, 109], "val": [0, 1, 2, 3, 10, 11, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25], "valid": [0, 4, 7, 8, 10, 11, 12, 13, 18, 20, 21, 25, 30, 33, 37, 45, 46, 48, 51, 55, 56, 59, 66, 67, 68, 83, 92, 102, 109], "see": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 28, 29, 30, 31, 35, 39, 41, 42, 43, 51, 53, 54, 55, 56, 57, 66, 67, 68, 73, 78, 88, 89, 90, 91, 92, 93, 94, 96, 98, 100, 102, 104, 106, 107, 108, 111, 112], "descript": [0, 1, 2, 3, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 88, 91, 101], "detail": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 51, 61, 67, 68, 73, 74, 75, 88, 97, 107, 108, 111, 112], "A": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 29, 30, 33, 36, 37, 39, 41, 42, 45, 46, 48, 51, 52, 53, 54, 55, 56, 57, 59, 63, 64, 65, 66, 68, 70, 71, 83, 91, 95, 97, 100, 102, 104, 105, 108], "subdirectori": [0, 1, 2, 3, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25], "class": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 30, 32, 33, 34, 35, 36, 37, 39, 41, 42, 44, 45, 46, 48, 51, 52, 53, 55, 56, 58, 59, 60, 61, 62, 64, 65, 66, 68, 69, 70, 72, 77, 79, 83, 84, 86, 89, 90], "file": [0, 1, 2, 3, 6, 8, 12, 13, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 30, 33, 37, 39, 41, 42, 45, 46, 48, 51, 52, 53, 55, 56, 59, 64, 66, 68, 70, 73, 74, 75, 83, 86, 90, 102, 104, 105, 108, 109, 112], "each": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 28, 30, 33, 35, 36, 41, 45, 46, 48, 49, 51, 52, 55, 56, 59, 62, 65, 66, 68, 70, 71, 74, 75, 77, 82, 83, 88, 89, 90, 93, 94, 95, 97, 100, 102, 103, 104, 105, 106, 107, 108, 112], "note2": [0, 18, 21, 25], "To": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 30, 31, 33, 35, 39, 41, 42, 43, 45, 51, 53, 55, 56, 57, 59, 64, 66, 68, 72, 73, 77, 86, 88, 90, 93, 96, 97, 101, 102, 104, 106, 107, 108, 111, 112], "up": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 30, 35, 37, 39, 41, 46, 48, 51, 56, 64, 66, 68, 75, 83, 91, 96, 100, 106, 114], "mai": [0, 2, 4, 7, 8, 12, 13, 14, 18, 21, 22, 25, 35, 42, 45, 49, 51, 53, 59, 61, 64, 68, 73, 74, 75, 77, 81, 82, 83, 86, 88, 91, 100, 102, 103, 104], "reduc": [0, 1, 2, 3, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 51, 64, 83, 86, 88, 100, 102, 103, 105, 107, 109, 114], "subset": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 36, 37, 46, 66, 83, 91, 93, 104, 114], "entir": [0, 1, 2, 3, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 37, 46, 56, 64, 66, 83, 90, 100], "ilsvrc2012": [0, 1, 2, 3, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25], "1000": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 33, 37, 46, 48, 51, 53, 55, 56, 66, 68, 90, 91, 103, 104], "50": [0, 1, 2, 3, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 30, 45, 56, 59, 95], "But": [0, 7, 8, 12, 13, 18, 21, 25, 51, 61, 68, 100], "purpos": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 51, 68, 83], "could": [0, 1, 2, 3, 5, 7, 10, 11, 12, 13, 14, 18, 19, 21, 22, 23, 24, 25, 28, 37, 39, 41, 46, 48, 49, 51, 60, 66, 68, 72, 90, 114], "perhap": [0, 7, 12, 13, 18, 21, 25], "exercis": [0, 7, 12, 13, 18, 21, 25], "left": [0, 1, 2, 3, 5, 7, 8, 10, 11, 12, 13, 14, 18, 19, 21, 22, 23, 24, 25, 78, 79, 80, 89, 97, 114], "upto": [0, 7, 12, 13, 18, 21, 25, 33], "reader": [0, 7, 12, 13, 18, 21, 25], "necessari": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 18, 19, 20, 21, 22, 23, 24, 25, 37, 46, 51, 53, 56, 66, 68, 81, 83, 90, 96, 111], "edit": [0, 1, 2, 3, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 48, 49, 51, 68], "cell": [0, 1, 2, 3, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25], "below": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 31, 32, 33, 34, 35, 36, 43, 44, 49, 51, 57, 58, 60, 64, 67, 72, 74, 75, 77, 78, 83, 86, 88, 89, 90, 93, 94, 96, 97, 100, 102, 103, 104, 106, 107, 108, 111], "specifi": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 30, 33, 39, 41, 45, 46, 49, 51, 56, 59, 66, 68, 71, 74, 75, 78, 79, 80, 83, 89, 90, 92, 94, 95, 97, 100, 106, 108, 111], "directori": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 30, 32, 33, 37, 42, 44, 45, 46, 48, 53, 56, 58, 59, 64, 66, 71, 96], "save": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 30, 32, 33, 36, 37, 39, 41, 42, 44, 45, 46, 48, 51, 53, 56, 58, 59, 64, 65, 66, 68, 71, 82, 86, 90, 108, 112], "dataset_dir": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 30, 33], "path": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 30, 32, 33, 37, 39, 41, 42, 44, 45, 46, 48, 51, 53, 55, 56, 58, 59, 61, 64, 66, 68, 69, 70, 75, 82, 86, 96], "replac": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 36, 48, 51, 54, 55, 61, 64, 65, 67, 68, 72, 74, 83, 88, 90, 103, 108], "real": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 53, 81, 111], "loop": [0, 1, 2, 3, 5, 6, 7, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 61, 90, 107], "doe": [0, 1, 2, 3, 5, 6, 7, 9, 10, 11, 12, 13, 14, 15, 16, 17, 19, 20, 21, 22, 23, 24, 25, 28, 35, 37, 43, 46, 56, 57, 59, 60, 61, 66, 72, 77, 90, 94, 97, 99, 102, 107, 108], "ani": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 30, 33, 34, 35, 36, 37, 38, 39, 45, 46, 51, 54, 56, 59, 60, 61, 62, 65, 66, 67, 68, 69, 72, 74, 77, 83, 86, 90, 106, 109], "limit": [0, 1, 2, 3, 5, 6, 7, 8, 12, 13, 14, 15, 16, 17, 19, 21, 22, 23, 24, 25, 72, 99], "written": [0, 1, 2, 3, 4, 5, 6, 7, 8, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 101, 102], "Not": [0, 7, 12, 13, 21, 25, 46, 63, 64, 66, 91, 97], "realli": [0, 7, 12, 13, 21, 25], "we": [0, 1, 4, 5, 6, 7, 8, 9, 12, 13, 15, 17, 18, 19, 20, 21, 25, 29, 30, 32, 33, 35, 41, 44, 45, 46, 51, 52, 54, 55, 58, 59, 61, 62, 64, 66, 68, 71, 72, 74, 75, 83, 86, 88, 90, 91, 95, 100, 102, 103, 107], "later": [0, 7, 8, 12, 13, 21, 25, 68, 73, 86, 90], "modifi": [0, 1, 2, 3, 5, 6, 7, 8, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 36, 39, 44, 61, 64, 65, 68, 74, 75, 102, 108, 109, 114], "quantizationsim": [0, 1, 2, 3, 5, 6, 8, 10, 11, 12, 13, 14, 15, 16, 17, 19, 21, 22, 23, 24, 25, 51, 63], "session": [0, 1, 2, 3, 28, 30, 42, 44, 45, 46, 48, 70], "act": [0, 45, 46, 59, 66], "regular": [0, 8, 28, 39, 41, 51, 68, 77, 88, 91, 102, 108], "onnxruntim": [0, 1, 2, 3, 42, 44, 46], "howev": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 22, 23, 24, 25, 34, 35, 51, 56, 68, 72, 102, 103], "recommend": [0, 1, 2, 3, 4, 5, 6, 9, 13, 19, 20, 30, 35, 37, 41, 42, 43, 45, 46, 48, 51, 52, 56, 66, 73, 83, 91, 93, 95, 102, 107], "onli": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 30, 32, 33, 34, 39, 41, 44, 45, 46, 48, 51, 52, 55, 58, 59, 60, 61, 63, 65, 66, 68, 69, 73, 74, 75, 78, 81, 82, 83, 88, 90, 93, 99, 100, 102, 104, 105, 106, 109, 111, 114], "quantizationsimmodel": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 18, 19, 20, 21, 22, 23, 24, 25, 28, 29, 32, 33, 36, 39, 41, 42, 44, 45, 46, 48, 51, 54, 58, 59, 64, 66, 67, 68, 69, 77, 82, 83, 86, 87, 90, 91, 93], "regist": [0, 77, 89], "requir": [0, 1, 4, 9, 12, 15, 16, 17, 18, 19, 22, 23, 24, 25, 28, 29, 30, 31, 33, 35, 36, 37, 39, 41, 43, 45, 46, 48, 49, 51, 54, 55, 56, 57, 58, 59, 60, 61, 64, 65, 66, 68, 70, 71, 74, 75, 77, 83, 86, 90, 93, 95, 100, 102, 103, 106, 107, 111], "custom": [0, 6, 8, 20, 35, 39, 41, 48, 49, 61, 67, 77, 88, 107, 108], "import": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 39, 41, 42, 43, 44, 45, 46, 48, 51, 52, 53, 54, 55, 56, 57, 58, 59, 61, 62, 64, 65, 66, 67, 68, 69, 70, 71, 75, 77, 78, 79, 80, 81, 83, 84, 86, 87, 88, 89, 90, 93, 94], "torch": [0, 1, 2, 3, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 51, 52, 53, 54, 56, 58, 59, 60, 62, 63, 64, 65, 66, 68, 70, 71, 72, 73, 74, 77, 78, 79, 80, 81, 83, 84, 86, 87, 88, 89, 90, 96, 101, 109], "ort": [0, 1, 2, 3, 42], "common": [0, 1, 2, 3, 5, 6, 7, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 64, 68, 72, 74, 83, 107, 112], "image_net_config": [0, 1, 2, 3, 5, 6, 7, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25], "util": [0, 1, 2, 3, 5, 6, 7, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 35, 36, 37, 39, 44, 52, 53, 64, 65, 68, 70, 72, 83, 90, 93, 102], "image_net_evalu": [0, 1, 2, 3, 5, 6, 7, 13, 14, 15, 16, 17, 19, 21, 22, 23, 24, 25], "imagenetevalu": [0, 1, 2, 3, 5, 6, 7, 13, 14, 15, 16, 17, 19, 21, 22, 23, 24, 25], "image_net_data_load": [0, 1, 2, 3, 15, 17, 19, 21, 22, 23, 24, 25], "imagenetdataload": [0, 1, 2, 3, 12, 15, 17, 19, 21, 22, 23, 24, 25], "imagenetdatapipelin": [0, 1, 2, 3, 5, 6, 7, 12, 13, 14, 15, 16, 17, 19, 21, 22, 23, 24, 25, 51, 54, 55, 68], "staticmethod": [0, 1, 2, 3, 5, 6, 7, 12, 13, 14, 15, 16, 17, 19, 21, 22, 23, 24, 25, 61], "def": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 30, 31, 33, 34, 35, 36, 37, 39, 41, 42, 43, 45, 46, 48, 51, 52, 53, 54, 55, 56, 57, 59, 60, 61, 62, 65, 66, 68, 69, 70, 71, 72, 77, 86, 90], "get_val_dataload": [0, 1, 2, 3, 15, 17, 18, 19, 21, 22, 23, 24, 25, 51, 55, 68], "data": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 29, 30, 33, 36, 37, 39, 41, 42, 45, 46, 48, 51, 53, 54, 55, 56, 59, 61, 63, 64, 66, 68, 70, 72, 81, 82, 83, 84, 86, 87, 90, 91, 93, 99, 103, 104, 105, 107, 108], "return": [0, 1, 2, 3, 4, 5, 6, 7, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 41, 42, 44, 45, 46, 48, 51, 52, 53, 54, 55, 56, 58, 59, 60, 61, 62, 64, 65, 66, 68, 69, 70, 71, 77, 81, 82, 83, 84, 86, 87, 89, 90, 92, 97, 98, 104, 108], "data_load": [0, 1, 2, 3, 5, 6, 7, 13, 14, 15, 17, 18, 19, 20, 21, 22, 23, 24, 25, 41, 42, 45, 48, 51, 53, 55, 56, 59, 68, 82, 86, 87, 90], "image_s": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 30, 33, 53], "batch_siz": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 29, 30, 33, 37, 41, 42, 46, 48, 51, 53, 56, 66, 68, 90], "is_train": [0, 1, 2, 3, 4, 15, 17, 19, 21, 22, 23, 24, 25, 33], "fals": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 13, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 30, 33, 35, 39, 42, 44, 45, 48, 49, 52, 53, 55, 56, 59, 61, 62, 64, 68, 69, 72, 77, 78, 81, 83, 84, 86, 88, 89, 90, 101, 106], "num_work": [0, 1, 2, 3, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25], "sess": [0, 1, 2, 3, 30], "inferencesess": [0, 1, 2, 3, 42, 44, 46], "float": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 30, 33, 37, 39, 41, 42, 45, 46, 48, 49, 51, 53, 55, 56, 59, 66, 67, 68, 77, 79, 81, 83, 84, 87, 102, 104, 107, 108, 112], "its": [0, 1, 2, 3, 5, 6, 7, 9, 13, 14, 15, 16, 17, 19, 21, 22, 23, 24, 25, 30, 33, 35, 45, 46, 59, 77, 81, 86, 87, 88, 90, 94, 96, 98, 104, 108, 114], "top": [0, 1, 2, 3, 4, 5, 6, 7, 8, 13, 14, 15, 16, 17, 19, 21, 22, 23, 24, 25, 77, 94, 111], "param": [0, 1, 2, 3, 5, 6, 7, 13, 14, 15, 16, 17, 19, 21, 22, 23, 24, 25, 28, 30, 31, 33, 36, 37, 39, 41, 42, 45, 46, 48, 51, 53, 56, 59, 64, 66, 68, 69, 70, 77, 83, 88, 89, 106], "iter": [0, 1, 2, 3, 4, 5, 6, 7, 13, 14, 15, 16, 17, 19, 21, 22, 23, 24, 25, 28, 30, 33, 37, 41, 42, 46, 51, 53, 56, 66, 90, 91, 103], "none": [0, 1, 2, 3, 4, 5, 6, 7, 8, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 30, 32, 33, 35, 36, 37, 39, 41, 42, 44, 45, 46, 48, 51, 52, 53, 54, 55, 56, 57, 58, 59, 61, 64, 65, 66, 68, 70, 71, 72, 77, 78, 79, 80, 82, 83, 86, 88, 90, 111], "go": [0, 4, 7, 8, 12, 13, 18, 21, 25, 35, 51, 54, 68, 74, 75, 86, 90], "load": [0, 1, 2, 3, 8, 32, 33, 36, 39, 44, 45, 51, 54, 55, 56, 58, 59, 61, 62, 64, 68, 69, 86, 100], "pretrain": [0, 1, 2, 3, 4, 5, 10, 11, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 33, 51, 53, 54, 57, 65, 66, 68, 70, 71, 86, 105, 108], "torchvis": [0, 1, 2, 3, 5, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 51, 53, 54, 57, 65, 66, 68, 70, 71, 90], "similarli": [0, 4, 12, 13, 18, 21, 25, 51, 68, 83, 86, 107], "instead": [0, 1, 2, 3, 4, 5, 6, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 30, 34, 51, 60, 61, 62, 68, 83, 86, 102, 103, 114], "input_shap": [0, 1, 2, 3, 4, 5, 9, 13, 14, 15, 16, 17, 18, 19, 22, 23, 24, 31, 33, 34, 37, 42, 46, 48, 51, 53, 55, 56, 57, 61, 65, 66, 68, 70, 90], "224": [0, 1, 2, 3, 4, 7, 10, 11, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 30, 31, 37, 39, 42, 45, 46, 48, 51, 53, 55, 57, 58, 65, 66, 68, 70, 71], "shape": [0, 1, 2, 3, 7, 8, 9, 13, 18, 19, 21, 22, 23, 24, 25, 33, 34, 35, 52, 56, 57, 61, 62, 64, 65, 69, 72, 78, 79, 80, 81, 83, 84, 88, 89, 90, 104], "channel": [0, 1, 2, 3, 14, 16, 18, 19, 21, 22, 23, 24, 25, 30, 46, 49, 52, 54, 64, 66, 71, 83, 86, 88, 93, 95, 96, 97, 99, 100, 103, 104, 106, 107, 108, 109, 110, 112, 113, 114], "x": [0, 1, 2, 3, 4, 5, 8, 9, 12, 13, 18, 19, 21, 22, 23, 24, 25, 30, 33, 34, 35, 39, 52, 60, 61, 62, 73, 79, 80, 81, 88, 90, 95, 101, 104], "height": [0, 1, 2, 3, 8, 18, 19, 21, 22, 23, 24, 25, 110, 113, 114], "width": [0, 1, 2, 3, 13, 18, 19, 21, 22, 23, 24, 25, 46, 49, 66, 91, 107, 108, 110, 113, 114], "dummy_input": [0, 1, 2, 3, 18, 19, 20, 21, 22, 23, 24, 25, 29, 32, 42, 44, 45, 46, 48, 51, 52, 53, 57, 58, 59, 60, 64, 65, 66, 68, 69, 82, 83, 86, 90], "randn": [0, 1, 2, 3, 20, 39, 42, 46, 48, 51, 53, 59, 61, 62, 66, 68, 69, 77, 78, 81, 84, 88, 89], "filenam": [0, 1, 2, 3, 28, 39, 41, 48, 51, 64, 68, 86], "resnet": [0, 1, 2, 3, 4, 5, 6, 10, 11, 12, 13, 14, 30, 33, 95], "18": [0, 1, 2, 3], "pt_model": [0, 1, 2, 3], "true": [0, 1, 2, 3, 4, 5, 7, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 30, 33, 36, 39, 41, 42, 45, 48, 49, 51, 52, 53, 54, 55, 56, 57, 59, 61, 62, 64, 65, 66, 68, 69, 70, 71, 72, 77, 78, 79, 80, 81, 83, 84, 88, 89, 90, 101, 106], "export": [0, 1, 2, 3, 4, 5, 8, 10, 11, 13, 14, 18, 19, 20, 22, 23, 24, 32, 33, 37, 39, 44, 45, 46, 48, 49, 51, 54, 58, 59, 60, 64, 66, 68, 72, 74, 75, 86, 87, 93, 96, 98, 100, 101, 102, 105, 108, 109], "eval": [0, 1, 2, 3, 4, 7, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 30, 33, 37, 42, 45, 46, 51, 53, 55, 56, 57, 59, 61, 63, 65, 66, 68, 70, 71, 90, 97, 100, 111], "trainingmod": [0, 3], "export_param": [0, 1, 2, 3], "do_constant_fold": [0, 1, 2, 3], "input_nam": [0, 1, 2, 3, 68], "input": [0, 1, 2, 3, 5, 7, 8, 9, 10, 11, 12, 13, 14, 18, 21, 25, 30, 32, 33, 34, 35, 37, 42, 44, 45, 46, 48, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 68, 69, 72, 77, 78, 79, 80, 82, 83, 84, 86, 88, 89, 90, 94, 97, 100, 104, 106, 108, 110, 113, 114], "output_nam": [0, 1, 2, 3, 68], "output": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 29, 30, 33, 34, 35, 37, 42, 45, 46, 48, 49, 51, 52, 53, 55, 59, 60, 61, 62, 64, 66, 67, 68, 69, 71, 72, 77, 78, 83, 88, 89, 90, 94, 100, 103, 104, 106, 108, 109, 110, 113, 114], "dynamic_ax": [0, 1, 2, 3], "0": [0, 1, 2, 3, 5, 6, 8, 9, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 29, 30, 35, 39, 41, 42, 44, 45, 48, 51, 52, 53, 55, 56, 59, 61, 62, 64, 65, 68, 69, 70, 72, 73, 74, 75, 77, 78, 79, 80, 81, 83, 84, 86, 88, 89, 90, 91, 95, 97, 101, 106], "load_model": [0, 1, 2, 3, 32], "befor": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 32, 34, 35, 36, 38, 41, 42, 43, 44, 45, 46, 48, 51, 53, 58, 65, 67, 68, 71, 72, 77, 82, 88, 90, 91, 92, 93, 100, 102, 104, 105, 108, 112], "onnxsim": [0, 1, 2, 3, 41, 42, 43, 44, 45, 46, 48], "_": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 18, 19, 20, 22, 23, 24, 25, 28, 32, 33, 35, 36, 37, 41, 42, 43, 44, 45, 46, 48, 53, 58, 66, 77, 78, 82, 87, 88, 89, 90, 102], "except": [0, 1, 2, 3, 9, 12, 25, 35, 83], "print": [0, 1, 2, 3, 7, 8, 9, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 30, 33, 42, 45, 51, 52, 53, 56, 59, 61, 62, 68, 72, 75, 77, 78, 88, 90, 104], "fail": [0, 1, 2, 3, 52, 61, 62, 92, 101, 102], "proceed": [0, 1, 2, 3], "unsimplifi": [0, 1, 2, 3], "whether": [0, 1, 2, 3, 5, 13, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 32, 38, 44, 58, 61, 62, 67, 91, 97, 105], "cpu": [0, 1, 2, 3, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 51, 53, 54, 57, 58, 61, 65, 68, 69, 71, 73, 74, 90, 102, 109], "cuda": [0, 1, 2, 3, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 41, 42, 44, 48, 53, 54, 55, 56, 59, 66, 68, 70, 73, 74, 75, 90], "devic": [0, 1, 2, 3, 7, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 32, 41, 42, 44, 48, 51, 53, 54, 55, 58, 59, 61, 64, 65, 68, 70, 71, 86, 87, 90, 108], "your": [0, 1, 2, 3, 5, 6, 7, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 42, 48, 51, 54, 55, 61, 62, 68, 72, 73, 74, 75, 77, 87, 91, 92, 95, 96, 100, 101, 102, 105, 108, 111], "environ": [0, 4, 6, 7, 10, 11, 18, 25, 33, 73, 96], "chang": [0, 1, 2, 3, 4, 7, 8, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 33, 38, 45, 49, 51, 53, 59, 60, 61, 64, 67, 68, 71, 82, 83, 86, 90, 91, 100, 104, 105, 106, 108, 112, 114], "logic": [0, 1, 2, 3, 15, 16, 17, 18, 19, 22, 23, 24, 25, 33, 45, 59, 77, 88, 109], "forc": [0, 1, 2, 3, 15, 16, 17, 18, 19, 22, 23, 24, 25], "placement": [0, 1, 2, 3, 15, 16, 17, 18, 19, 22, 23, 24, 25, 106], "cudnn_conv_algo_search": [0, 1, 2, 3], "fix": [0, 1, 2, 3, 49, 62, 87, 98, 102, 107, 108, 109], "default": [0, 1, 2, 3, 4, 5, 6, 7, 8, 12, 13, 15, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 30, 33, 35, 37, 39, 41, 42, 45, 46, 48, 51, 53, 55, 56, 59, 61, 66, 68, 74, 75, 77, 78, 82, 86, 88, 89, 91, 97, 100, 106, 108, 109, 111], "avoid": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 18, 19, 22, 23, 24, 25, 34, 39, 46, 51, 60, 66, 68, 91, 95], "everi": [0, 1, 2, 3, 4, 7, 8, 10, 11, 12, 13, 15, 16, 17, 18, 21, 23, 24, 25, 28, 32, 37, 41, 44, 46, 51, 58, 66, 68, 90, 97, 100, 105, 112], "cudaexecutionprovid": [0, 1, 2, 3], "get_available_provid": [0, 1, 2, 3], "cpuexecutionprovid": [0, 1, 2, 3], "use_cuda": [0, 1, 2, 3, 4, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 30, 41, 42, 44, 48, 51, 54, 56, 68], "let": [0, 4, 7, 8, 13, 18, 51, 61, 68, 90], "determin": [0, 8, 18, 20, 28, 30, 37, 39, 41, 46, 48, 49, 51, 56, 66, 68, 79, 80, 83, 88, 90, 92, 102, 103, 104, 112], "32": [0, 1, 2, 4, 5, 6, 8, 9, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 22, 23, 24, 28, 33, 34, 35, 37, 42, 49, 51, 52, 61, 62, 68, 74, 75, 78, 86, 89, 107], "routin": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 51, 68], "serializetostr": [0, 1, 2, 3, 44], "batchnorm": [0, 1, 2, 3, 5, 10, 11, 13, 14, 18, 19, 22, 23, 24, 31, 35, 36, 38, 42, 43, 52, 53, 55, 57, 65, 71, 92, 103, 114], "bn": [0, 1, 2, 3, 5, 7, 10, 11, 13, 14, 18, 19, 22, 23, 24, 29, 36, 55, 65, 67, 102, 104, 109], "These": [0, 2, 6, 8, 13, 18, 20, 22, 28, 39, 41, 42, 48, 53, 67, 68, 72, 75, 88, 90, 92, 93, 94, 95, 101, 102, 103, 104, 107, 108], "adjac": [0, 1, 2, 3, 5, 10, 11, 13, 14, 18, 19, 22, 23, 24, 90, 106], "convolut": [0, 1, 2, 3, 5, 9, 10, 11, 13, 14, 15, 17, 18, 19, 22, 23, 24, 30, 35, 36, 52, 83, 90, 93, 94, 95, 100, 107, 110, 113, 114], "cannot": [0, 1, 2, 3, 5, 10, 11, 13, 14, 18, 19, 22, 23, 24, 52, 61, 62, 78, 89], "thei": [0, 1, 2, 3, 5, 8, 9, 10, 11, 12, 13, 14, 18, 19, 22, 23, 24, 25, 34, 36, 61, 65, 67, 83, 107, 111], "why": [0, 13, 18, 107], "do": [0, 1, 2, 3, 4, 5, 6, 7, 9, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 29, 33, 35, 39, 41, 51, 61, 63, 64, 71, 74, 75, 90, 100, 104, 107, 108], "On": [0, 13, 18, 49, 73], "runtim": [0, 1, 2, 3, 5, 10, 11, 13, 14, 18, 19, 22, 23, 24, 39, 48, 49, 51, 56, 68, 69, 77, 83, 86, 87, 90, 95, 98, 100, 102, 104, 106, 108, 109], "tflite": [0, 13, 18], "snapdragon": [0, 13, 18], "neural": [0, 6, 13, 18, 20, 87, 90, 92, 95, 98, 100, 102, 105, 107, 108, 113], "process": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 13, 14, 18, 19, 22, 23, 24, 30, 32, 44, 51, 58, 68, 70, 83, 84, 87, 90, 92, 94, 97, 98, 100, 103, 108], "sdk": [0, 13, 18, 87, 90, 98], "etc": [0, 4, 7, 8, 13, 18, 49, 51, 68, 74, 95, 102], "practic": [0, 4, 6, 7, 8, 12, 13, 15, 16, 17, 18, 20, 25, 51, 68, 90, 100], "so": [0, 1, 4, 5, 7, 8, 9, 10, 11, 12, 13, 15, 16, 17, 18, 19, 21, 23, 24, 25, 28, 29, 37, 39, 41, 46, 48, 51, 56, 61, 62, 63, 66, 68, 72, 75, 88, 97, 101, 104], "speedup": [0, 13, 18], "sinc": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 18, 19, 22, 23, 24, 25, 48, 51, 64, 68, 83, 93, 95, 108], "unnecessari": [0, 13, 18, 90, 114], "now": [0, 1, 2, 3, 4, 7, 8, 9, 10, 11, 13, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 30, 35, 51, 61, 62, 68, 69, 86, 90, 109], "perspect": [0, 13, 18], "mathemat": [0, 13, 18, 60], "equival": [0, 13, 18, 19, 22, 23, 24, 25, 51, 59, 60, 67, 68, 77, 78, 79, 80, 83, 90], "produc": [0, 12, 13, 18, 25, 42, 49, 53, 61, 81, 82, 83, 84, 97, 104], "same": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 13, 15, 16, 17, 18, 19, 21, 22, 23, 24, 28, 32, 35, 44, 51, 53, 58, 61, 62, 64, 66, 68, 69, 72, 77, 81, 83, 88, 89, 93, 103, 106, 112], "increas": [0, 13, 18, 30, 56, 71, 83, 97, 103], "rang": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 13, 14, 18, 19, 20, 21, 22, 23, 35, 37, 46, 51, 53, 54, 61, 66, 68, 71, 78, 82, 84, 90, 91, 93, 96, 97, 102, 103, 104, 105, 107, 108, 109, 112], "tensor": [0, 2, 9, 12, 13, 14, 18, 22, 23, 24, 25, 28, 32, 35, 38, 39, 45, 47, 48, 49, 51, 52, 53, 56, 57, 58, 59, 60, 61, 64, 65, 66, 67, 68, 69, 77, 78, 79, 80, 83, 84, 86, 88, 89, 90, 91, 94, 101, 102, 104, 106, 107, 108, 109], "valu": [0, 1, 2, 4, 5, 6, 7, 8, 9, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 25, 28, 30, 33, 36, 37, 41, 45, 46, 49, 51, 55, 56, 58, 59, 61, 64, 65, 66, 68, 77, 78, 79, 80, 81, 82, 83, 84, 86, 89, 90, 91, 94, 95, 97, 100, 102, 103, 104, 105, 106, 108, 110, 112, 113], "weight": [0, 1, 2, 3, 4, 5, 6, 9, 10, 11, 12, 13, 14, 18, 19, 20, 22, 23, 24, 25, 28, 30, 33, 35, 36, 37, 38, 39, 41, 45, 46, 47, 49, 51, 55, 59, 62, 64, 65, 66, 67, 68, 71, 72, 77, 82, 83, 84, 86, 88, 90, 91, 93, 95, 100, 102, 103, 104, 105, 106, 107, 108, 112], "And": [0, 13, 18, 36, 65], "neg": [0, 7, 8, 13, 18, 78, 83], "impact": [0, 13, 18, 90, 97, 107], "especi": [0, 13, 18, 73, 102, 105, 107], "want": [0, 4, 7, 8, 12, 13, 18, 25, 32, 33, 36, 39, 44, 45, 48, 51, 58, 59, 61, 65, 67, 68, 74, 77], "behavior": [0, 13, 18, 19, 22, 23, 24, 61, 72, 88, 90, 98], "here": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 15, 17, 18, 19, 21, 22, 23, 24, 25, 28, 29, 30, 31, 41, 51, 53, 54, 57, 61, 64, 66, 68, 69, 72, 86, 90, 102, 105, 106], "place": [0, 1, 2, 3, 5, 6, 7, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 33, 39, 43, 45, 51, 55, 57, 59, 65, 68, 83, 86, 106], "aimet_onnx": [0, 1, 2, 3, 41, 42, 43, 44, 45, 46, 48, 73, 75], "batch_norm_fold": [0, 1, 2, 3, 4, 5, 7, 10, 11, 13, 14, 18, 19, 21, 22, 23, 24, 29, 36, 54, 65, 71, 90], "fold_all_batch_norms_to_weight": [0, 1, 2, 3], "basic": [0, 4, 7, 8, 18, 21, 51, 68, 75, 87, 90], "mean": [0, 4, 7, 8, 9, 12, 13, 15, 16, 17, 18, 20, 21, 22, 25, 38, 51, 54, 68, 71, 88, 90, 104, 106, 108], "graph": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 13, 14, 15, 17, 18, 19, 21, 22, 23, 24, 25, 30, 35, 49, 51, 52, 61, 68, 70, 86, 101, 102, 108, 111], "configur": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 14, 18, 19, 21, 22, 23, 24, 28, 37, 41, 42, 46, 48, 49, 51, 53, 55, 64, 66, 68, 83, 86, 90, 99, 109], "them": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 18, 19, 21, 22, 23, 24, 25, 35, 39, 42, 46, 51, 61, 62, 64, 66, 68, 72, 88, 90, 100], "few": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 51, 68, 90, 95], "explain": [0, 4, 7, 8, 12, 18, 21, 25, 51, 68, 94, 100, 103, 108], "quant_schem": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 18, 19, 21, 22, 23, 24, 25, 28, 37, 39, 42, 46, 48, 49, 51, 53, 55, 66, 68, 69, 82, 86], "quantschem": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 18, 19, 21, 22, 23, 24, 25, 28, 37, 39, 41, 42, 46, 48, 51, 53, 54, 55, 66, 68, 69, 72, 82, 86, 92], "post_training_tf_enhanc": [0, 1, 2, 3, 4, 7, 8, 12, 18, 19, 21, 22, 23, 25, 28, 37, 39, 41, 42, 46, 48, 49, 51, 53, 55, 66, 68], "support": [0, 4, 7, 8, 9, 18, 21, 23, 24, 26, 28, 30, 31, 33, 34, 35, 37, 39, 41, 45, 46, 48, 51, 55, 56, 59, 60, 61, 66, 67, 68, 69, 73, 77, 83, 86, 94, 95, 98, 99, 100, 101, 102, 103, 106, 107, 108, 109, 113], "option": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 30, 33, 36, 37, 39, 41, 42, 45, 46, 48, 51, 52, 53, 54, 55, 56, 59, 61, 64, 65, 66, 68, 71, 75, 77, 78, 83, 86, 87, 89, 90, 91, 104, 106, 108], "tf_enhanc": [0, 4, 7, 8, 18, 21, 39, 55], "tf": [0, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 18, 21, 25, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 39, 45, 46, 48, 55, 66, 74, 104, 108, 109], "quant": [0, 1, 4, 5, 7, 8, 10, 11, 13, 14, 18, 19, 20, 21, 22, 23, 24, 28, 38, 39, 41, 42, 45, 48, 51, 55, 59, 67, 68, 93], "scheme": [0, 4, 7, 8, 12, 15, 16, 17, 18, 21, 25, 28, 30, 37, 39, 41, 42, 46, 48, 51, 53, 55, 56, 58, 66, 68, 83, 84, 92, 93, 100, 104], "enum": [0, 4, 7, 8, 18, 21, 30, 33, 41, 45, 55, 56, 59], "post_training_tf": [0, 4, 5, 7, 8, 10, 13, 14, 18, 21, 22, 28, 37, 39, 41, 46, 48, 49, 51, 55, 66, 68, 69, 82, 86], "default_output_bw": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 18, 19, 21, 22, 23, 24, 25, 28, 37, 39, 45, 48, 51, 59, 66, 68, 86, 90], "8": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 16, 17, 18, 19, 21, 22, 23, 24, 25, 28, 33, 36, 37, 39, 41, 42, 45, 46, 48, 49, 51, 53, 55, 56, 59, 61, 62, 64, 66, 68, 70, 72, 73, 75, 77, 78, 79, 80, 81, 83, 84, 86, 88, 89, 90, 102, 107, 114], "essenti": [0, 4, 7, 8, 18, 21, 83, 87], "ask": [0, 4, 7, 8, 12, 18, 21, 25, 77], "all": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 18, 19, 21, 22, 23, 24, 25, 29, 31, 33, 34, 35, 36, 39, 41, 45, 46, 48, 49, 51, 54, 55, 56, 59, 61, 62, 64, 65, 66, 67, 68, 71, 72, 73, 74, 77, 82, 83, 86, 88, 90, 94, 97, 100, 103, 104, 106, 107], "activ": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 18, 19, 21, 22, 23, 24, 25, 33, 34, 35, 36, 37, 39, 45, 46, 48, 49, 51, 52, 55, 59, 60, 61, 64, 65, 66, 68, 69, 82, 83, 86, 88, 90, 102, 104, 105, 106, 107, 108], "integ": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 18, 19, 21, 22, 23, 24, 25, 28, 37, 39, 41, 46, 48, 49, 66, 68, 78, 83, 91, 102, 104], "default_param_bw": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 18, 19, 21, 22, 23, 24, 25, 28, 37, 39, 41, 45, 46, 48, 51, 59, 66, 68, 86, 90], "There": [0, 1, 4, 5, 7, 8, 12, 13, 14, 18, 19, 21, 22, 23, 24, 25, 58, 62, 68, 72, 73, 101, 103, 105, 112], "other": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 36, 60, 61, 65, 67, 68, 69, 72, 73, 83, 86, 97, 99, 102, 104, 107, 108, 109], "check": [0, 4, 7, 8, 12, 18, 21, 25, 32, 35, 37, 38, 44, 46, 52, 58, 60, 61, 62, 66, 67, 68, 92, 102, 105, 107], "document": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 14, 18, 19, 20, 21, 22, 23, 24, 25, 26, 33, 64, 70, 73, 75, 98, 109, 111], "refer": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 45, 49, 51, 55, 58, 59, 64, 68, 72, 83, 86, 88, 91, 96, 108], "aimet_common": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114], "quantsim": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 18, 19, 21, 22, 23, 24, 28, 32, 39, 41, 44, 45, 46, 48, 51, 53, 54, 55, 58, 59, 64, 66, 67, 68, 69, 72, 82, 83, 86, 87, 96, 102, 105, 106, 109], "default_activation_bw": [0, 1, 2, 3, 41, 46, 48], "even": [0, 4, 7, 8, 13, 18, 51, 68, 77], "though": [0, 4, 7, 8, 13, 18, 51, 68, 77, 83, 106], "ad": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 13, 14, 15, 16, 17, 18, 19, 22, 23, 24, 48, 49, 51, 62, 64, 68, 69, 90, 99, 106, 109], "node": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 13, 14, 18, 19, 22, 23, 24, 39, 51, 52, 59, 60, 61, 68, 90, 105, 108], "readi": [0, 1, 2, 3, 4, 7, 8, 10, 11, 13, 15, 16, 17, 18, 19, 22, 23, 24, 25, 39, 51, 68, 90, 107], "yet": [0, 4, 7, 8, 13, 18, 51, 68], "scale": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 18, 19, 20, 22, 23, 24, 25, 29, 31, 36, 43, 49, 51, 54, 57, 64, 65, 68, 77, 78, 79, 80, 81, 83, 86, 89, 93, 102, 103, 104, 105, 108], "offset": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 18, 19, 20, 22, 23, 24, 25, 37, 46, 49, 51, 66, 68, 77, 78, 83, 84, 86, 89, 102, 104, 105, 108], "pass": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 28, 30, 32, 33, 35, 36, 37, 39, 41, 42, 44, 45, 46, 48, 51, 52, 54, 55, 56, 58, 59, 60, 61, 62, 63, 64, 65, 66, 68, 72, 77, 83, 86, 87, 88, 90, 98, 101, 103, 104, 105, 107, 108, 109, 111], "unlabel": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 17, 18, 19, 20, 22, 23, 24, 25, 42, 46, 48, 51, 53, 66, 68, 91, 102, 104], "through": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 18, 19, 21, 22, 23, 24, 25, 35, 45, 51, 55, 59, 61, 66, 68, 71, 72, 86, 88, 90, 103, 104, 108], "collect": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 13, 14, 18, 19, 22, 23, 24, 42, 46, 51, 53, 66, 68, 82, 83, 97, 104], "statist": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 13, 14, 15, 16, 17, 18, 19, 22, 23, 24, 29, 30, 37, 38, 46, 51, 54, 56, 66, 67, 68, 71, 78, 79, 80, 82, 84, 88, 89, 90, 93, 102, 104, 112], "which": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 28, 30, 32, 33, 35, 36, 38, 41, 44, 45, 46, 49, 51, 52, 55, 56, 58, 59, 61, 62, 64, 65, 67, 68, 71, 74, 75, 77, 78, 81, 83, 84, 86, 87, 88, 89, 90, 93, 95, 97, 100, 102, 103, 104, 106, 108, 109, 111, 114], "calcul": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 22, 23, 24, 25, 28, 33, 39, 42, 45, 48, 51, 53, 59, 65, 68, 84, 88, 97, 103, 104, 105, 108], "sometim": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 13, 14, 18, 19, 22, 23, 24, 51, 68, 94, 100, 103, 104], "calibr": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 18, 19, 22, 23, 24, 25, 37, 41, 46, 48, 51, 66, 68, 78, 82, 83, 84, 86, 87, 88, 89, 90, 102, 104, 105, 107, 108], "simpli": [0, 4, 7, 8, 13, 18, 21, 28, 37, 39, 41, 46, 48, 51, 61, 66, 68], "benefici": [0, 4, 7, 8, 12, 13, 18, 25, 51, 68, 104], "forward": [0, 3, 4, 7, 8, 9, 10, 11, 12, 18, 19, 21, 22, 23, 24, 25, 33, 35, 37, 39, 45, 46, 48, 51, 52, 54, 59, 60, 61, 62, 63, 65, 66, 68, 69, 74, 77, 78, 88, 89, 90, 101, 104, 107, 109], "well": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 18, 19, 20, 22, 23, 24, 25, 33, 46, 51, 52, 62, 64, 66, 68, 81, 83, 86, 100, 103, 104], "distribut": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 18, 19, 22, 23, 24, 25, 30, 51, 56, 68, 103, 107, 108], "doesn": [0, 1, 2, 3, 5, 6, 14, 15, 16, 17, 18, 19, 22, 23, 24, 63, 77, 105], "t": [0, 4, 7, 8, 12, 13, 18, 21, 25, 33, 45, 51, 59, 61, 63, 64, 67, 68, 74, 77, 91, 104, 105], "look": [0, 4, 7, 8, 9, 12, 13, 18, 25, 35, 45, 51, 59, 68, 90, 92], "definit": [0, 4, 7, 8, 12, 13, 18, 19, 22, 23, 24, 25, 34, 38, 60, 61, 64, 67, 72, 77, 90, 102], "extrem": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 18, 19, 22, 23, 24, 25, 51, 68, 108], "bias": [0, 2, 14, 18, 22, 102], "origin": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 30, 32, 33, 35, 44, 56, 58, 61, 68, 72, 77, 88, 90, 94, 95, 97, 102, 103, 104, 108, 111], "consist": [0, 18, 58, 72, 83, 97, 108], "dark": [0, 1, 2, 3, 4, 5, 10, 11, 12, 13, 14, 18, 19, 22, 23, 24, 25, 51, 68], "light": [0, 1, 2, 3, 4, 5, 10, 11, 12, 13, 14, 18, 19, 22, 23, 24, 25, 51, 68], "mani": [0, 4, 7, 8, 12, 13, 15, 16, 17, 18, 25, 61, 91, 95, 103], "differ": [0, 4, 7, 8, 13, 15, 16, 17, 18, 23, 24, 30, 51, 53, 56, 61, 64, 66, 68, 69, 72, 74, 75, 83, 94, 97, 100, 102, 103, 105, 107, 108], "wai": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 18, 19, 22, 23, 24, 25, 30, 56, 58, 68, 72, 73, 83, 90, 101], "just": [0, 4, 7, 8, 12, 13, 18, 23, 24, 25, 51, 68, 108, 114], "pass_calibration_data": [0, 1, 2, 3, 5, 10, 11, 12, 13, 14, 18, 19, 21, 22, 23, 24, 25, 41, 48, 51, 68], "get_input": [0, 1, 2, 3], "name": [0, 1, 2, 3, 7, 9, 12, 25, 30, 32, 33, 35, 41, 44, 45, 46, 49, 55, 58, 59, 64, 66, 68, 74, 75, 77, 82, 86, 88, 89, 103, 108, 109, 111], "batch_cntr": [0, 1, 2, 3, 5, 10, 11, 13, 14, 19, 21, 22, 23, 24, 25, 42], "input_data": [0, 1, 2, 3, 18, 19, 21, 22, 23, 24, 25, 28, 42, 48, 51, 68], "target_data": [0, 1, 2, 3, 18, 19, 21, 22, 23, 24, 25, 51, 68], "inputs_batch": [0, 1, 2, 3, 18, 19, 21, 22, 23, 24, 25, 51, 68], "numpi": [0, 1, 2, 3, 9, 28, 30, 33, 37, 39, 42, 45, 46, 48], "break": [0, 1, 2, 3, 4, 5, 10, 11, 13, 14, 19, 21, 22, 23, 24, 25, 30, 33, 42, 48, 51, 68, 90], "subsequ": [0, 2, 13, 14, 18, 51, 68, 81, 86, 101, 103, 106], "compute_encod": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 13, 14, 18, 19, 21, 22, 23, 24, 28, 39, 45, 48, 51, 59, 68, 69, 72, 77, 78, 79, 80, 81, 82, 84, 86, 87, 88, 89, 90], "forward_pass_callback": [0, 1, 2, 3, 5, 10, 11, 12, 13, 14, 18, 19, 21, 22, 23, 24, 25, 28, 33, 37, 39, 41, 45, 46, 48, 59, 66, 68], "forward_pass_callback_arg": [0, 1, 2, 3, 4, 5, 7, 10, 11, 13, 14, 18, 19, 21, 22, 23, 24, 39, 41, 45, 48, 51, 59, 68], "10000": [0, 1, 5, 13, 18, 19, 28, 51, 91], "initi": [0, 1, 5, 11, 12, 13, 18, 19, 23, 24, 25, 28, 44, 51, 68, 69, 77, 78, 79, 80, 88, 89, 91, 105, 108], "phase": [0, 4, 18, 33, 45, 59, 100], "compris": [0, 4, 18, 97], "sensit": [0, 2, 4, 14, 18, 22, 33, 37, 38, 45, 46, 47, 59, 66, 67, 97, 102, 104, 107, 108, 109], "greedili": [0, 4, 18], "select": [0, 4, 18, 28, 42, 51, 68, 71, 73, 74, 75, 92, 95, 104, 108, 111, 114], "bitwidth": [0, 1, 4, 5, 13, 18, 19, 28, 33, 37, 39, 41, 42, 45, 46, 48, 49, 51, 53, 55, 59, 64, 66, 68, 72, 78, 79, 80, 81, 83, 86, 88, 89, 90, 93, 102, 107, 108], "base": [0, 1, 4, 5, 6, 7, 13, 18, 19, 20, 21, 28, 29, 41, 45, 46, 48, 51, 59, 64, 66, 68, 69, 72, 74, 77, 78, 79, 80, 83, 84, 88, 89, 94, 95, 97, 102, 111], "three": [0, 15, 16, 17, 18, 31, 61, 92, 95, 112], "eval_callback_for_phase1": [0, 18, 33, 45, 59], "eval_callback_for_phase2": [0, 18, 33, 45, 59], "callbackfunc": [0, 4, 12, 18, 25, 37, 46, 66], "object": [0, 6, 7, 12, 18, 19, 20, 22, 23, 24, 25, 28, 32, 33, 37, 39, 41, 42, 44, 45, 46, 48, 53, 56, 58, 59, 64, 66, 68, 77, 81, 82, 83, 86, 88, 89, 90, 93, 102, 105, 108], "In": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 30, 34, 35, 37, 38, 42, 46, 49, 51, 52, 53, 56, 59, 60, 61, 62, 66, 67, 68, 72, 77, 83, 88, 90, 91, 95, 97, 100, 102, 103, 105, 106, 108, 111, 112, 114], "reus": [0, 18, 34, 60, 61, 62], "previou": [0, 4, 18, 22, 30, 33, 36, 45, 56, 59, 65, 67, 90, 95, 107], "snippet": [0, 18, 49, 61, 83, 86], "func_callback_arg": [0, 18, 33, 45, 46, 59, 66], "measur": [0, 15, 16, 17, 18, 30, 33, 45, 46, 56, 59, 66], "score": [0, 1, 2, 3, 4, 6, 7, 20, 21, 30, 33, 42, 45, 46, 51, 53, 56, 59, 66, 70, 97, 100, 111], "respecit": [0, 18], "both": [0, 4, 11, 17, 18, 23, 24, 35, 49, 51, 61, 66, 68, 69, 72, 73, 78, 83, 86, 87, 88, 100, 102, 103, 105, 106, 107, 108, 110, 111, 114], "qualiti": [0, 18], "slightli": [0, 18], "goal": [0, 18, 37, 42, 46, 53, 66, 92], "rough": [0, 18], "wherea": [0, 18, 59, 90, 108], "callbak": [0, 18], "impli": [0, 18, 45, 59], "flexibl": [0, 18], "than": [0, 1, 5, 7, 8, 18, 19, 21, 29, 30, 36, 41, 49, 51, 52, 56, 59, 61, 62, 65, 68, 72, 83, 86, 90, 95, 99, 105, 106], "smaller": [0, 13, 18, 33, 41, 45, 51, 52, 59, 98, 107, 110, 113], "indirect": [0, 18], "sqnr": [0, 4, 18, 45, 59, 84, 108], "between": [0, 13, 18, 28, 30, 36, 41, 45, 46, 51, 53, 56, 58, 59, 65, 66, 68, 72, 75, 83, 88, 103, 104, 106, 108], "faster": [0, 6, 7, 13, 18, 20, 33, 84, 98], "correl": [0, 18], "metric": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 22, 23, 24, 25, 30, 37, 39, 51, 56, 68, 104, 108], "aimet_torch": [0, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 51, 52, 53, 54, 55, 56, 57, 58, 59, 61, 62, 64, 65, 66, 68, 69, 70, 71, 73, 74, 75, 77, 78, 79, 80, 81, 82, 83, 84, 86, 87, 88, 89, 90, 101], "mixed_precision_algo": [0, 4, 18, 45, 59], "evalcallbackfactori": [0, 18, 45, 59], "forward_one_batch": [0, 18], "label": [0, 4, 5, 6, 7, 10, 11, 13, 18, 20, 30, 33, 37, 46, 51, 53, 66, 68, 104, 105], "eval_callback_factori": [0, 18], "forward_fn": [0, 1, 7, 18, 21, 41, 45, 51, 54, 59, 86], "small": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 18, 19, 20, 22, 23, 24, 25, 51, 68, 93, 98, 102], "hand": [0, 18, 102], "miou": [0, 18], "full": [0, 1, 2, 3, 4, 5, 7, 10, 11, 14, 18, 19, 21, 22, 23, 24, 30, 33, 34, 38, 60, 67, 88], "appli": [0, 7, 8, 15, 16, 17, 18, 20, 21, 28, 30, 31, 36, 38, 41, 42, 43, 45, 46, 51, 53, 55, 56, 62, 65, 67, 69, 71, 73, 77, 78, 83, 86, 88, 89, 90, 91, 92, 93, 96, 100, 102, 103, 105, 106, 107, 108, 109, 111, 112], "dummi": [0, 12, 18, 25, 28, 39, 41, 42, 46, 48, 51, 52, 53, 57, 58, 59, 65, 66, 68, 86, 104], "one": [0, 1, 2, 3, 4, 5, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 22, 23, 24, 25, 36, 49, 51, 52, 59, 61, 62, 64, 65, 68, 74, 83, 86, 90, 94, 96, 100, 105, 109, 110, 111, 113], "tupl": [0, 4, 12, 18, 25, 28, 29, 30, 32, 33, 36, 37, 39, 41, 42, 44, 45, 46, 48, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 65, 66, 68, 78, 83, 84, 86, 89], "expect": [0, 7, 15, 16, 17, 18, 21, 30, 34, 36, 37, 39, 41, 45, 46, 48, 51, 52, 56, 59, 61, 62, 66, 68, 82, 84, 86, 90, 100, 102, 104], "group": [0, 18, 36, 74, 83, 106, 108], "list": [0, 4, 7, 9, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 29, 30, 31, 32, 33, 35, 36, 41, 42, 44, 45, 48, 51, 54, 55, 56, 57, 58, 59, 61, 65, 66, 68, 71, 78, 83, 86, 88, 89, 97, 99, 101, 106], "modul": [0, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 30, 33, 34, 41, 45, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 71, 73, 77, 82, 83, 86, 87, 90, 102, 109, 114], "therefor": [0, 4, 7, 8, 9, 18, 33, 45, 59, 64, 90, 95, 103], "might": [0, 1, 4, 5, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 22, 23, 24, 25, 33, 45, 49, 51, 59, 68, 91, 104, 107], "front": [0, 4, 18, 33, 45, 59], "candid": [0, 4, 18, 30, 31, 33, 42, 45, 56, 59, 97, 100], "possibl": [0, 4, 6, 9, 18, 20, 33, 34, 35, 39, 42, 45, 48, 53, 59, 60, 62, 68, 83, 90, 97, 104, 106, 107], "suppos": [0, 4, 18, 33, 45, 59], "combin": [0, 4, 18, 33, 45, 55, 59, 61, 83, 92, 95, 100, 102, 103], "type": [0, 4, 6, 7, 9, 12, 15, 16, 17, 18, 20, 23, 24, 28, 29, 30, 31, 33, 36, 37, 39, 41, 42, 45, 46, 48, 51, 52, 53, 54, 55, 56, 59, 61, 64, 65, 66, 68, 71, 72, 77, 81, 82, 83, 86, 88, 89, 100, 102, 104, 106, 108, 111], "int": [0, 4, 6, 7, 12, 15, 16, 17, 18, 20, 28, 29, 30, 33, 37, 39, 41, 42, 44, 45, 46, 48, 49, 51, 53, 54, 55, 56, 59, 64, 66, 68, 69, 72, 78, 79, 80, 83, 84, 89], "16": [0, 4, 7, 18, 22, 28, 30, 33, 39, 45, 48, 49, 51, 59, 61, 64, 68, 69, 73, 77, 78, 79, 80, 83, 84, 86, 88, 89], "quantizationdatatyp": [0, 4, 18, 33, 39, 45, 48, 59, 68, 72], "allowed_accuracy_drop": [0, 4, 6, 18, 20, 33, 42, 45, 53, 59], "maximum": [0, 4, 5, 6, 7, 12, 13, 14, 18, 25, 28, 33, 42, 45, 51, 59, 68, 78, 79, 80, 84], "allow": [0, 4, 6, 8, 18, 20, 30, 32, 33, 35, 38, 39, 42, 44, 45, 47, 49, 56, 58, 59, 60, 61, 67, 68, 81, 83, 92, 100, 107, 108, 109, 111], "drop": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 33, 42, 45, 59, 67, 68, 88, 92, 95, 100, 103, 104, 105, 107, 108], "plot": [0, 4, 12, 18, 25, 33, 45, 59, 71, 82, 104], "till": [0, 4, 18, 33, 45, 59], "met": [0, 4, 18, 33, 45, 59], "complet": [0, 4, 15, 16, 17, 18, 30, 33, 45, 59, 90, 93, 107], "pick": [0, 4, 18, 30, 33, 35, 36, 45, 56, 59, 95, 97], "results_dir": [0, 4, 12, 18, 25, 33, 37, 42, 45, 46, 53, 59, 66, 71], "cach": [0, 4, 18, 33, 42, 45, 53, 59, 75], "intermedi": [0, 4, 18, 32, 33, 44, 45, 52, 58, 59, 68, 108], "clean_start": [0, 4, 18, 33, 45, 59], "inform": [0, 4, 18, 21, 33, 36, 45, 49, 55, 59, 62, 65, 67, 72, 81, 86, 102], "delet": [0, 4, 18, 33, 45, 59, 104], "prior": [0, 4, 18, 19, 22, 23, 24, 33, 45, 59], "start": [0, 4, 7, 8, 9, 10, 11, 12, 13, 15, 16, 17, 18, 21, 23, 24, 25, 28, 30, 33, 35, 41, 45, 51, 56, 59, 61, 62, 68, 78, 90, 91, 95, 96, 106, 108], "analysi": [0, 4, 8, 15, 16, 17, 18, 30, 33, 37, 45, 46, 56, 59, 66, 100, 107], "applic": [0, 1, 4, 5, 6, 10, 11, 12, 13, 14, 18, 19, 22, 30, 31, 33, 36, 37, 39, 45, 49, 59, 65, 101], "respons": [0, 4, 18, 33, 45, 59, 100], "flag": [0, 4, 18, 33, 36, 42, 45, 53, 59, 61, 68, 72, 82, 89], "anyth": [0, 4, 12, 18, 25, 33, 45, 59], "compar": [0, 4, 7, 8, 9, 12, 18, 21, 25, 33, 45, 52, 59, 61, 71, 83, 86, 90, 102, 104, 105, 112], "use_all_amp_candid": [0, 18, 45, 59], "supported_kernel": [0, 18, 45, 59], "field": [0, 18, 45, 49, 59], "config": [0, 13, 18, 39, 45, 46, 59, 66, 106, 109], "under": [0, 18, 31, 33, 45, 59, 72, 82, 83, 86, 104, 106], "op_typ": [0, 7, 18, 45, 59, 106], "section": [0, 7, 18, 20, 45, 52, 59, 62, 74, 75, 83, 93, 102, 108], "ignor": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 22, 23, 24, 25, 30, 45, 51, 55, 56, 59, 61, 68, 90], "continu": [0, 18, 35, 45, 59, 62, 68, 102, 103, 105, 107], "amp_search_algo": [0, 18, 33, 45, 59], "ampsearchalgo": [0, 18, 33, 45, 59], "search": [0, 7, 8, 10, 11, 15, 16, 17, 18, 21, 23, 24, 26, 28, 33, 42, 45, 51, 59, 68, 84, 105, 106], "binari": [0, 18, 33, 45, 59], "interpol": [0, 18, 33, 97], "bruteforc": [0, 18, 33], "phase1_optim": [0, 18, 33, 45, 59], "implement": [0, 18, 32, 37, 39, 42, 44, 46, 53, 58, 66, 68, 69, 77, 101, 102, 107], "either": [0, 5, 13, 15, 16, 17, 18, 26, 30, 36, 51, 56, 60, 64, 83, 91, 114], "optmiz": [0, 18], "phase1": [0, 18, 33, 45, 59], "001": [0, 18, 39], "p": [0, 18, 74, 84], "store": [0, 4, 18, 28, 39, 41, 51, 64, 68, 81, 83, 86], "final": [0, 4, 7, 8, 12, 18, 21, 25, 30, 35, 45, 56, 59, 62, 70, 75, 83, 94, 95, 97, 105, 107], "after": [0, 1, 2, 4, 5, 7, 8, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 28, 29, 36, 42, 46, 51, 53, 54, 61, 62, 65, 66, 68, 71, 77, 84, 86, 88, 90, 91, 92, 93, 95, 96, 100, 102, 107, 111, 112], "multipli": [0, 18, 88, 95, 100], "mac": [0, 15, 16, 17, 18, 30, 56, 70, 95, 100, 110, 113], "therebi": [0, 18], "lesser": [0, 18], "re": [0, 9, 18, 33, 38, 45, 59, 67, 90, 96, 102], "mixed_precis": [0, 4, 18, 33, 45, 59], "choose_mixed_precis": [0, 4, 18, 33, 45, 59], "pareto_front_list": [0, 18, 45, 59], "next": [0, 2, 4, 7, 8, 13, 18, 21, 36, 51, 64, 65, 68, 74, 90, 105, 107, 108], "step": [0, 2, 3, 4, 6, 7, 8, 12, 13, 18, 21, 25, 33, 36, 42, 46, 51, 53, 54, 61, 64, 66, 68, 78, 84, 86, 87, 90, 91, 92, 93, 94, 95, 96, 97, 100, 102, 103, 105, 107], "would": [0, 4, 7, 12, 13, 18, 21, 25, 30, 31, 35, 51, 57, 68, 72, 83, 84, 106, 109], "actual": [0, 4, 7, 9, 18, 21, 32, 37, 42, 44, 46, 51, 53, 58, 63, 66, 68, 83], "take": [0, 4, 6, 7, 9, 12, 13, 14, 15, 16, 17, 18, 21, 25, 33, 36, 45, 51, 56, 59, 65, 68, 77, 83, 90, 97, 100, 102, 103, 105, 107, 114], "o": [0, 1, 4, 5, 6, 7, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 33, 56], "makedir": [0, 1, 4, 5, 7, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24], "exist_ok": [0, 1, 4, 5, 7, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24], "filename_prefix": [0, 1, 4, 5, 7, 13, 14, 18, 19, 20, 21, 22, 23, 24, 28, 33, 39, 41, 48, 51, 64, 68], "resnet18_mixed_precis": [0, 18], "hope": [0, 4, 7, 8, 13, 18, 21], "wa": [0, 1, 4, 5, 7, 8, 9, 13, 15, 17, 18, 19, 21, 30, 32, 44, 49, 51, 56, 58, 64, 81, 100], "understand": [0, 4, 7, 8, 9, 12, 13, 18, 21, 25, 72, 102, 112], "qat": [0, 3, 8, 13, 18, 28, 29, 41, 48, 51, 54, 63, 67, 86, 90, 91, 93, 96, 98, 102, 107, 108, 109], "learn": [0, 1, 2, 3, 5, 6, 7, 8, 9, 10, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 28, 29, 30, 31, 39, 41, 42, 43, 51, 53, 54, 55, 56, 57, 66, 68, 72, 93, 96, 100, 102, 105, 108, 109], "addit": [0, 7, 8, 9, 12, 13, 18, 21, 25, 49, 68, 73, 77, 83, 86, 102, 105, 106, 109], "resourc": [0, 7, 8, 9, 13, 18, 21], "doc": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 61, 64, 104], "know": [0, 7, 8, 13, 18, 21, 77], "thi": [1, 2, 3, 5, 6, 7, 8, 9, 10, 11, 14, 15, 16, 17, 19, 20, 22, 23, 24, 26, 28, 30, 31, 32, 33, 34, 35, 36, 37, 39, 41, 42, 43, 44, 45, 46, 48, 49, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 68, 69, 71, 72, 73, 74, 75, 77, 78, 79, 80, 81, 82, 83, 84, 86, 88, 89, 90, 91, 92, 94, 95, 97, 98, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 111, 114], "notebook": [1, 2, 3, 5, 6, 7, 8, 9, 10, 11, 14, 15, 16, 17, 19, 20, 22, 23, 24], "contain": [1, 2, 3, 5, 6, 10, 11, 12, 14, 15, 16, 17, 19, 20, 22, 23, 24, 25, 33, 36, 45, 46, 49, 52, 56, 59, 61, 62, 66, 73, 77, 81, 82, 86, 88, 90, 102, 104, 105, 106, 108], "nearest": [1, 4, 5, 8, 10, 11, 13, 14, 19, 22, 37, 39, 42, 48, 53, 55, 68, 91], "achiev": [1, 5, 13, 19, 30, 56, 74, 83, 91, 95], "i": [1, 2, 3, 5, 6, 7, 8, 9, 10, 11, 14, 15, 16, 17, 19, 20, 22, 23, 24, 26, 28, 30, 31, 33, 34, 35, 36, 37, 38, 39, 41, 42, 43, 44, 45, 46, 48, 49, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 77, 78, 79, 80, 82, 83, 84, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 97, 98, 100, 101, 102, 103, 104, 105, 106, 107, 108, 110, 111, 112, 113, 114], "loss": [1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 13, 14, 19, 22, 23, 24, 28, 37, 39, 41, 46, 51, 66, 68, 81, 87, 90, 91, 98, 100, 102, 104, 108], "function": [1, 2, 4, 5, 8, 12, 13, 14, 15, 16, 17, 19, 21, 22, 23, 24, 25, 28, 29, 30, 31, 33, 34, 35, 36, 37, 38, 39, 41, 42, 43, 45, 46, 47, 48, 51, 52, 53, 54, 55, 56, 57, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 72, 77, 81, 82, 83, 88, 90, 91, 97, 100, 101, 104, 108, 109, 111, 112], "closer": [1, 5, 13, 19, 91], "farther": [1, 5, 19], "high": [1, 2, 3, 5, 10, 11, 14, 15, 16, 17, 19, 22, 23, 24, 31, 33, 36, 43, 45, 57, 59, 65, 72, 87, 91, 95, 97, 98, 103, 109, 112], "level": [1, 3, 4, 5, 8, 10, 11, 15, 16, 17, 19, 23, 24, 31, 43, 57, 72, 87, 95, 97, 98, 102, 107, 111], "simuat": [1, 2, 5, 10, 11, 13, 14, 19, 22, 23, 24], "post": [1, 2, 3, 5, 6, 7, 8, 10, 11, 13, 14, 15, 16, 17, 19, 20, 21, 22, 23, 24, 38, 42, 47, 48, 49, 53, 67, 87, 90, 91, 92, 98, 100, 105, 108, 109], "finetun": [1, 2, 5, 6, 7, 13, 14, 15, 16, 17, 19, 21, 23, 24, 48, 68], "paramet": [1, 2, 3, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 19, 20, 21, 22, 23, 24, 25, 29, 32, 33, 35, 36, 37, 38, 39, 42, 43, 44, 45, 46, 47, 48, 49, 52, 53, 54, 55, 57, 58, 59, 61, 62, 64, 65, 66, 67, 68, 70, 71, 72, 77, 78, 79, 80, 81, 82, 83, 84, 88, 89, 90, 93, 94, 100, 101, 102, 103, 104, 105, 106, 112], "fine": [1, 2, 3, 5, 6, 8, 10, 11, 14, 19, 20, 22, 23, 24, 26, 30, 39, 56, 64, 68, 87, 95, 98, 102, 105, 108], "tune": [1, 2, 3, 5, 6, 8, 10, 11, 14, 19, 20, 22, 23, 24, 26, 30, 39, 56, 64, 68, 87, 95, 98, 102, 105, 108], "epoch": [1, 2, 3, 5, 6, 7, 8, 10, 11, 14, 15, 16, 17, 19, 20, 21, 22, 23, 24, 39, 54, 56, 68, 90, 98, 100, 105], "improv": [1, 2, 3, 5, 6, 7, 8, 10, 11, 14, 15, 16, 17, 19, 20, 21, 22, 23, 24, 26, 51, 68, 83, 90, 95, 100, 102, 105, 107, 112], "otherwis": [1, 2, 3, 5, 6, 10, 11, 14, 15, 16, 17, 19, 20, 22, 23, 24, 42, 48, 62, 64, 68, 74, 75, 78, 83, 89, 107], "One": [1, 2, 3, 4, 12, 15, 16, 17, 18, 19, 20, 22, 23, 24, 25, 37, 39, 90], "run": [1, 2, 3, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 19, 21, 22, 23, 24, 25, 30, 32, 33, 35, 37, 38, 39, 41, 42, 44, 45, 48, 49, 52, 53, 54, 56, 58, 59, 61, 62, 68, 72, 74, 75, 78, 83, 88, 89, 93, 98, 100, 102, 103, 104, 108, 109, 111], "two": [1, 2, 3, 4, 5, 6, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 19, 20, 22, 23, 24, 25, 30, 33, 35, 36, 56, 59, 61, 62, 65, 72, 73, 83, 90, 97, 98, 100, 102, 103, 104, 105, 108, 110, 112, 113], "thing": [1, 2, 3, 5, 6, 13, 14, 15, 16, 17, 19, 22, 23, 24], "put": [1, 2, 3, 5, 6, 7, 12, 13, 14, 15, 16, 17, 19, 21, 22, 23, 24, 25, 59, 102], "still": [1, 2, 3, 5, 6, 7, 12, 13, 14, 15, 16, 17, 19, 21, 22, 23, 24, 25, 34, 67, 83, 102, 107], "interfac": [1, 2, 3, 5, 6, 7, 12, 13, 14, 15, 16, 17, 19, 21, 22, 23, 24, 25, 67, 73], "method": [1, 2, 3, 5, 6, 7, 8, 9, 12, 13, 14, 15, 16, 17, 19, 21, 22, 23, 24, 25, 32, 33, 39, 42, 44, 55, 58, 59, 61, 68, 72, 77, 83, 86, 88, 90, 97, 100, 102, 107, 108], "abl": [1, 2, 3, 5, 6, 7, 9, 12, 13, 14, 15, 16, 17, 19, 21, 22, 23, 24, 25, 35, 46, 61, 62, 66, 81, 90], "exist": [1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 19, 21, 22, 23, 24, 25, 45, 51, 59, 68, 74, 77, 83, 88, 108], "degrad": [1, 2, 3, 5, 10, 11, 14, 19, 22, 23, 24], "platform": [1, 2, 3, 5, 10, 11, 14, 19, 22, 23, 24, 73, 91, 102, 108], "call": [1, 2, 3, 5, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 19, 22, 23, 24, 25, 29, 30, 31, 33, 34, 35, 36, 42, 45, 46, 49, 51, 56, 57, 59, 61, 65, 66, 68, 77, 79, 80, 81, 83, 88, 90, 102, 104, 106, 108, 109, 110, 113], "kei": [1, 2, 3, 5, 9, 10, 11, 14, 15, 16, 17, 19, 22, 23, 24, 36, 49, 65], "precis": [1, 2, 3, 5, 7, 8, 10, 11, 12, 13, 14, 19, 21, 22, 23, 24, 25, 49, 51, 78, 79, 80, 87, 89, 102], "api": [1, 2, 3, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 19, 20, 21, 22, 23, 24, 25, 34, 60, 63, 72, 74, 82, 90, 96, 98, 101, 102, 106, 109, 111], "explan": [1, 2, 3, 5, 10, 11, 14, 19, 22, 23, 24], "copi": [1, 18, 19, 22, 23, 24, 35, 39, 68, 71, 96, 108], "deepcopi": [1, 71], "must": [1, 2, 3, 5, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 19, 22, 23, 24, 25, 35, 51, 83, 86, 88, 92, 93, 95, 98, 99, 102, 104, 106, 114], "comput": [1, 2, 3, 5, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 19, 22, 23, 24, 25, 28, 30, 32, 33, 37, 39, 41, 42, 44, 45, 46, 48, 49, 51, 53, 56, 58, 59, 63, 64, 66, 68, 69, 73, 75, 77, 79, 80, 83, 84, 86, 90, 91, 100, 101, 103, 104, 108, 111, 114], "encod": [1, 2, 3, 5, 6, 7, 8, 10, 11, 13, 14, 19, 20, 22, 23, 24, 28, 32, 33, 37, 39, 41, 42, 44, 45, 46, 48, 51, 53, 54, 58, 59, 63, 64, 66, 67, 68, 69, 72, 77, 78, 81, 83, 86, 87, 89, 90, 91, 93, 102, 104, 105, 109], "write": [1, 2, 3, 5, 10, 11, 14, 19, 22, 23, 24, 41, 48, 51, 68, 83, 86], "loader": [1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 15, 17, 19, 21, 22, 23, 24, 25, 33, 37, 41, 45, 46, 48, 51, 54, 55, 59, 66, 68, 90, 91], "extract": [1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 19, 22, 23, 24, 25, 51, 68, 103], "regard": [1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 19, 22, 23, 24, 25, 33, 45, 51, 59, 68], "veri": [1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 19, 20, 22, 23, 24, 25, 51, 68, 69, 95, 100, 104, 112], "percentag": [1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 19, 22, 23, 24, 25, 51, 68], "1m": [1, 2, 3, 4, 5, 10, 11, 12, 13, 14, 19, 22, 23, 24, 25, 51, 68], "500": [1, 2, 3, 4, 5, 10, 11, 12, 13, 14, 19, 20, 22, 23, 24, 25, 33, 42, 51, 56, 68, 90, 91, 103, 104], "suffic": [1, 2, 3, 5, 10, 11, 14, 19, 22, 23, 24], "reason": [1, 2, 3, 5, 10, 11, 14, 19, 22, 23, 24, 62], "scenario": [1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 19, 22, 23, 24, 25, 51, 68, 93, 114], "That": [1, 2, 3, 5, 10, 11, 14, 19, 22, 23, 24, 114], "pictur": [1, 2, 3, 4, 5, 10, 11, 12, 13, 14, 19, 22, 23, 24, 25, 51, 68, 87], "captur": [1, 2, 3, 4, 5, 10, 11, 12, 13, 14, 19, 22, 23, 24, 25, 32, 44, 51, 58, 61, 68], "night": [1, 2, 3, 4, 5, 10, 11, 12, 13, 14, 19, 22, 23, 24, 25, 51, 68], "skew": [1, 2, 3, 5, 10, 11, 14, 19, 22, 23, 24], "5": [1, 2, 3, 4, 5, 8, 10, 11, 13, 14, 15, 16, 17, 19, 22, 23, 24, 30, 41, 42, 45, 53, 54, 56, 59, 61, 64, 68, 69, 70, 72, 73, 78, 79, 80, 83, 88, 89, 95, 105, 107], "comparison": [1, 2, 3, 19, 22, 23, 24, 32, 44, 58], "order": [1, 7, 8, 9, 10, 11, 12, 15, 16, 17, 19, 21, 23, 24, 25, 34, 36, 38, 60, 62, 65, 67, 68, 74, 75, 77, 83, 88, 90, 93, 94, 102, 105, 106], "vector": [1, 5, 13, 19, 51, 86], "num_batch": [1, 2, 5, 6, 7, 12, 13, 19, 20, 21, 22, 25, 28, 37, 41, 42, 46, 51, 53, 54, 66], "2000": [1, 5, 6, 13, 19, 20, 22, 41, 42, 51, 53, 78, 81], "size": [1, 5, 6, 7, 8, 9, 13, 19, 33, 35, 39, 46, 48, 51, 52, 53, 62, 66, 68, 77, 78, 83, 86, 88, 89, 91, 101, 110, 113], "default_num_iter": [1, 5, 13, 19, 20, 28, 41, 51], "strongli": [1, 5, 13, 19, 35, 51, 61], "least": [1, 5, 19, 59], "adaround_weight": [1, 5, 6, 13, 19, 20, 28, 41, 42, 51, 53, 67, 72], "adaroundparamet": [1, 5, 6, 13, 19, 20, 28, 41, 42, 51, 53, 67], "satisfi": [1, 6, 20, 61, 83, 90, 92], "signatur": [1, 15, 16, 17, 28, 30, 37, 42, 46, 56, 66, 77, 78], "deriv": [1, 4, 18, 49, 78, 89, 108], "form": [1, 12, 25, 35, 69], "arrai": [1, 83], "__init__": [1, 9, 20, 34, 35, 42, 52, 53, 56, 60, 61, 62, 69, 77, 88, 90], "self": [1, 9, 20, 34, 35, 52, 53, 56, 60, 61, 62, 69, 77, 81, 90], "_torch_data_load": 1, "_iter": 1, "__iter__": 1, "__next__": 1, "__len__": [1, 20, 46, 53, 66], "len": [1, 4, 8, 18, 20, 30, 33, 41, 42, 51, 53, 61], "ada_model": [1, 5, 13, 19], "apply_adaround": [1, 5, 13, 19, 28, 41, 51], "default_quant_schem": [1, 5, 13, 19, 28, 41, 51], "about": [1, 2, 3, 4, 5, 6, 9, 10, 11, 14, 15, 16, 17, 19, 20, 21, 22, 23, 24, 28, 30, 31, 36, 39, 41, 42, 43, 49, 51, 53, 55, 56, 57, 65, 66, 67, 68, 81, 90, 98, 104], "biwidth": [1, 5, 13, 19], "freez": [1, 5, 13, 19, 28, 51, 64, 72, 91], "set_and_freeze_param_encod": [1, 5, 13, 19, 28, 41, 51], "dure": [1, 3, 5, 7, 10, 11, 12, 13, 14, 15, 16, 17, 19, 21, 23, 24, 25, 28, 29, 30, 33, 35, 41, 42, 45, 51, 56, 59, 68, 70, 77, 82, 86, 88, 90, 91, 98, 100, 102, 105, 106, 108, 111, 112], "intern": [1, 5, 8, 9, 13, 19, 35, 42, 48, 51, 53, 68, 69, 72, 84, 100, 103, 106], "maintain": [1, 5, 19, 42, 97, 100], "alter": [1, 5, 13, 19, 51], "negat": [1, 5, 19], "encoding_path": [1, 5, 6, 13, 19, 20, 28, 42, 51, 53], "join": [1, 5, 10, 11, 13, 18, 19, 20, 56, 70], "littl": [1, 5, 10, 11, 14, 15, 16, 17, 19, 22, 23, 24, 100], "gain": [1, 5, 10, 11, 13, 14, 15, 16, 17, 19, 22, 23, 24, 94, 95, 100], "experi": [1, 5, 10, 11, 14, 15, 16, 17, 19, 22, 23, 24, 30, 56, 83, 100], "hyper": [1, 5, 7, 8, 10, 11, 14, 15, 16, 17, 19, 21, 22, 23, 24, 68, 105], "better": [1, 5, 10, 11, 13, 14, 15, 16, 17, 19, 21, 22, 23, 24, 52, 71, 83, 91, 92, 100, 102, 103, 105], "updat": [1, 3, 5, 9, 10, 11, 13, 14, 19, 20, 22, 23, 24, 49, 51, 52, 68, 70, 72, 75, 84, 89, 96, 102, 103, 105, 108, 109, 111], "without": [1, 5, 6, 8, 10, 11, 13, 14, 19, 20, 22, 23, 24, 39, 51, 64, 68, 79, 80, 81, 82, 83, 86, 92, 102, 105, 108, 114], "resnet18_after_adaround": 1, "bia": [2, 7, 14, 31, 36, 43, 52, 57, 61, 62, 64, 65, 67, 69, 72, 77, 79, 80, 88, 90, 91, 94, 102, 103, 106, 107, 109], "correct": [2, 13, 14, 20, 25, 36, 51, 53, 65, 67, 75, 90, 91, 102, 103, 107], "bc": [2, 91], "help": [2, 12, 14, 22, 25, 52, 62, 64, 68, 71, 91, 97, 100, 102, 103, 104, 105, 107, 112], "recov": [2, 14, 15, 16, 17, 22, 87, 98, 107, 108], "oppos": [2, 14, 22], "conv": [2, 7, 14, 22, 28, 29, 36, 41, 51, 54, 55, 61, 65, 71, 83, 99, 106, 109, 110, 113, 114], "immedi": [2, 6, 14, 20, 22], "consecut": [2, 14, 22, 36, 64, 65, 102, 103], "five": [2, 22], "sake": [2, 22, 32, 44, 58], "procedur": [2, 14, 15, 17, 22, 97, 111], "cl": [2, 14, 22, 36, 65, 77, 109], "skip": [2, 14, 22, 31, 33, 41, 51, 53, 55, 74, 94], "absorpt": [2, 14, 22], "hba": [2, 14, 22], "again": [2, 13, 14, 15, 16, 17, 22, 104, 105], "cross_layer_equ": [2, 14, 22, 31, 36, 43, 57, 65, 71, 72, 101], "equalize_model": [2, 14, 22, 31, 43, 57, 71, 72, 101], "free": [2, 7, 8, 14, 21, 22, 68, 74, 103], "iccv": [2, 14, 22, 100, 103], "2019": [2, 14, 22, 103], "add": [3, 7, 10, 11, 15, 16, 17, 23, 24, 34, 35, 39, 49, 60, 61, 62, 64, 68, 74, 77, 88, 90, 106, 108, 109, 114], "ml": [3, 8, 10, 11, 23, 24, 26, 68, 100, 102, 103], "standard": [3, 8, 10, 11, 23, 24, 33, 61, 68, 71, 79, 80, 88], "acceler": [3, 8, 10, 11, 23, 24, 56, 68, 73, 87, 98, 100], "min": [3, 10, 11, 13, 37, 46, 49, 64, 66, 71, 72, 78, 82, 84, 89, 90, 104, 108], "max": [3, 10, 11, 13, 37, 46, 49, 64, 66, 71, 72, 78, 79, 80, 82, 84, 89, 90, 100, 103, 104, 108], "onc": [3, 8, 10, 11, 15, 16, 17, 22, 23, 24, 34, 60, 62, 64, 68, 77, 93, 94, 100, 104, 105, 108], "effect": [3, 8, 10, 11, 23, 24, 28, 29, 39, 41, 51, 54, 64, 68, 83, 88, 90, 93, 102, 104, 108], "keep": [3, 10, 61, 68, 106], "constant": [3, 10, 23, 24, 42, 53, 61, 68, 97, 102], "4": [3, 8, 12, 15, 16, 17, 20, 25, 28, 29, 36, 37, 41, 42, 45, 46, 51, 53, 54, 55, 56, 61, 64, 65, 66, 68, 69, 72, 78, 81, 83, 90, 93, 97, 102, 107, 114], "layer": [4, 8, 15, 16, 17, 28, 29, 30, 33, 34, 35, 37, 38, 39, 41, 42, 46, 47, 48, 51, 52, 53, 54, 55, 56, 60, 62, 63, 64, 66, 67, 68, 69, 70, 71, 77, 82, 83, 86, 88, 90, 91, 92, 93, 94, 95, 96, 99, 101, 102, 104, 106, 107, 108, 109, 110, 111, 112, 113, 114], "an": [4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 29, 30, 31, 33, 34, 35, 37, 39, 41, 42, 45, 46, 48, 49, 51, 53, 54, 55, 56, 57, 59, 60, 61, 62, 66, 68, 69, 72, 73, 77, 81, 82, 83, 87, 88, 89, 90, 91, 92, 94, 95, 97, 98, 100, 101, 102, 104, 105, 106, 107, 108, 112, 114], "resnet50": [4, 5, 6, 10, 11, 12, 13, 14, 30, 31, 33, 36, 37, 39], "disabl": [4, 15, 17, 37, 45, 46, 64, 66, 68, 72, 88, 97, 100, 104, 106, 108], "log": [4, 7, 8, 10, 11, 28, 33, 62, 104], "info": [4, 36, 52, 55, 62, 65, 90, 109], "verbos": 4, "displai": [4, 8, 96, 104, 111, 112], "erorr": 4, "tensorflow": [4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 25, 26, 73, 74, 93, 96, 98, 99, 102, 106, 108, 109], "messag": 4, "error": [4, 33, 35, 42, 53, 61, 77, 92, 102, 104, 105, 107, 108], "critic": 4, "tf_cpp_min_log_level": [4, 6, 7, 10, 11, 33], "compat": [4, 7, 8, 33, 49, 60, 73, 83, 90], "v1": [4, 18, 19, 20, 21, 22, 23, 24, 25, 33, 51, 53, 55, 58, 59, 66, 67, 68, 69, 72], "set_verbos": [4, 33], "evlauat": 4, "kera": [4, 5, 6, 10, 11, 12, 13, 14, 26, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 91, 93, 96, 98, 102, 103, 104, 106, 108, 109], "preprocess_input": [4, 5, 10, 11, 13, 14, 30, 33], "decode_predict": [4, 30, 33], "center_crop": [4, 33], "img_height": 4, "256": [4, 18, 33, 37, 46, 66, 86, 90, 104], "img_width": 4, "crop_length": 4, "start_x": 4, "start_i": 4, "cropped_imag": 4, "get_eval_func": [4, 30, 33], "num_iter": [4, 30, 33], "50000": [4, 30, 33], "debug": [4, 26, 27, 28, 32, 40, 44, 49, 50, 58, 72, 90, 107], "get_top5_acc": 4, "func_wrapp": [4, 30, 33], "validation_d": [4, 30, 33], "preprocess": [4, 5, 8, 10, 11, 13, 30, 33], "image_dataset_from_directori": [4, 5, 10, 11, 13, 30, 33], "label_mod": [4, 5, 10, 11, 13, 30, 33], "categor": [4, 5, 10, 11, 13, 30, 33], "shuffl": [4, 5, 10, 11, 13, 30, 33, 56, 90], "top1": [4, 20, 30, 33], "top5": 4, "total": [4, 9, 30, 33, 90, 97, 108], "img": [4, 30, 33], "pred": [4, 18, 30, 33, 42], "predict": [4, 12, 30, 32, 33, 37, 53], "np": [4, 9, 28, 30, 33, 35, 37, 39, 42, 45, 46, 48], "class_nam": [4, 9, 30, 33], "cnt": [4, 30, 33], "sum": [4, 18, 20, 30, 33, 53, 90], "b": [4, 30, 33, 54, 64, 77, 78, 89], "zip": [4, 30, 33, 37], "str": [4, 9, 28, 30, 32, 33, 37, 39, 41, 42, 44, 45, 46, 48, 51, 53, 55, 58, 59, 60, 61, 64, 66, 68, 71, 82, 86], "eval_func": [4, 12, 30, 33, 70], "aimet_tensorflow": [4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 28, 29, 30, 31, 32, 33, 35, 36, 37, 39, 73, 75], "fold_all_batch_norm": [4, 5, 10, 11, 13, 14, 18, 19, 22, 23, 24, 33, 36, 65, 71, 90], "get_model": [4, 33, 34], "include_top": [4, 5, 13, 14, 33], "input_tensor": [4, 5, 13, 14, 33, 35, 48, 59, 61, 84], "pool": [4, 5, 7, 13, 14, 33], "batch": [4, 6, 7, 15, 16, 17, 21, 28, 29, 30, 32, 33, 36, 37, 41, 44, 45, 46, 48, 51, 52, 54, 58, 59, 65, 66, 68, 91, 102, 103, 104], "norm": [4, 14, 33, 36, 52, 54, 65, 91, 102, 103, 104], "fold": [4, 29, 31, 33, 36, 42, 43, 52, 53, 54, 57, 65, 67, 71, 88, 91, 92, 93, 102, 103, 104, 109], "acccuraci": 4, "fp32_acccuraci": 4, "sim": [4, 7, 8, 13, 20, 28, 29, 33, 41, 42, 45, 46, 51, 53, 54, 55, 59, 63, 64, 66, 72, 82, 83, 86, 87, 90, 105, 108], "rounding_mod": [4, 5, 8, 10, 11, 13, 14, 37, 39, 42, 48, 53, 68], "solut": [4, 18, 97, 105, 107], "less": [4, 18, 52, 83, 84, 94, 97, 106], "convert": [4, 18, 34, 35, 36, 45, 59, 61, 69, 81, 90, 92, 102, 112], "overhead": [4, 15, 17, 18], "fairli": [4, 7, 8, 12, 13, 25, 51, 68], "simpl": [4, 7, 8, 12, 13, 25, 28, 37, 46, 51, 56, 61, 66, 68, 90], "don": [4, 7, 8, 12, 13, 25, 51, 61, 64, 68, 77, 91, 104], "pointer": [4, 7, 8, 12, 13, 25, 51, 68], "done": [4, 9, 13, 21, 34, 74, 78, 89, 100, 106, 108], "defin": [4, 9, 12, 13, 15, 16, 17, 19, 22, 23, 24, 25, 28, 33, 34, 35, 37, 38, 42, 45, 46, 49, 51, 53, 56, 59, 60, 61, 62, 66, 67, 68, 77, 83, 88, 90, 102, 104, 106, 108], "separ": [4, 28, 35, 36, 39, 41, 51, 61, 62, 65, 68, 72, 86, 93, 104, 107, 109], "larg": [4, 64, 95, 105, 110, 113], "enough": [4, 15, 16, 17, 52], "meaning": 4, "give": [4, 8, 12, 13, 15, 16, 17, 25, 33, 51, 68, 69, 100], "ideal": [4, 12, 13, 25, 51, 68], "opt": [4, 86], "01": [4, 6, 20, 28, 41, 42, 51, 53, 78, 91], "discuss": [4, 15, 16, 17, 90, 95, 96, 108], "eval_callback_phase1": 4, "eval_callback_phase2": 4, "forward_pass_call_back": [4, 33, 45, 59], "greedymixedprecisionalgo": [4, 18, 33, 59], "enabl": [4, 11, 13, 15, 17, 18, 24, 26, 30, 33, 37, 45, 46, 54, 56, 59, 64, 66, 72, 73, 74, 83, 87, 93, 98, 102, 104, 106, 108, 109, 111], "enable_convert_op_reduct": [4, 18, 33, 59], "acuraci": [4, 33], "time": [4, 6, 12, 20, 22, 25, 30, 36, 49, 56, 61, 62, 73, 83, 86, 90, 92, 100, 101, 105, 106, 111], "wrapper": [4, 8, 18, 19, 22, 23, 24, 28, 33, 37, 46, 56, 66], "callback": [4, 6, 8, 10, 11, 12, 15, 16, 17, 25, 30, 33, 37, 39, 42, 45, 46, 48, 53, 56, 59, 66, 68, 104, 108], "get_data_loader_wrapp": [4, 33], "dataloader_wrapp": [4, 33], "map": [4, 5, 6, 7, 9, 13, 33, 37, 39, 49, 62, 64, 77, 78, 81, 83, 88, 97, 104, 106], "lambda": [4, 5, 6, 7, 8, 9, 13, 33, 37, 59, 83], "y": [4, 5, 12, 13, 25, 33, 39, 61, 74, 75, 90, 104], "data_loader_wrapp": [4, 33], "choose_fast_mixed_precis": [4, 33], "resnet50_after_amp": 4, "pytorch": [5, 6, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 52, 61, 62, 69, 71, 73, 74, 77, 86, 88, 91, 92, 93, 96, 98, 103, 104, 106, 108, 109], "image_net_dataset": [5, 6, 7, 12, 13, 14], "imagenetdataset": [5, 6, 7, 12, 13, 14], "get_val_dataset": [5, 6, 7, 12, 13, 14], "10": [5, 6, 7, 8, 9, 10, 11, 13, 14, 15, 16, 17, 21, 23, 24, 28, 30, 34, 35, 36, 39, 54, 56, 61, 62, 64, 68, 69, 70, 73, 74, 75, 77, 78, 81, 83, 84, 88, 89, 90, 97, 100, 105], "new": [5, 9, 10, 11, 13, 14, 18, 25, 34, 35, 36, 45, 49, 51, 59, 60, 61, 64, 68, 72, 74, 78, 83, 86, 87, 89, 90, 102, 109], "rest": [5, 10, 11, 13, 14, 107], "progbar": [5, 10, 11, 13, 14], "sim_model": [5, 10, 11, 12, 13, 14, 19, 21, 22, 23, 24, 25, 51, 68], "tf_dataset": [5, 13, 14], "progbar_stat_upd": [5, 10, 11, 13, 14], "equal": [5, 9, 38, 42, 47, 53, 55, 63, 67, 71, 81, 83, 91, 92, 95, 96, 97, 101, 102, 104, 107, 108, 112], "data_set": [5, 13, 28], "ada_round_data": [5, 13], "image_width": [5, 13], "image_height": [5, 13], "resnet50_after_adaround": 5, "offer": [6, 20, 46, 66, 92], "suit": [6, 20, 92], "network": [6, 8, 9, 13, 20, 35, 88, 90, 92, 95, 97, 100, 102, 105, 107, 108, 111, 113], "quantiz": [6, 9, 15, 16, 17, 20, 26, 27, 28, 29, 32, 35, 37, 40, 41, 42, 44, 46, 49, 50, 51, 53, 54, 58, 60, 61, 63, 64, 66, 77, 79, 82, 84, 86, 87, 91, 92, 93, 95, 96, 98, 100, 104, 109, 111], "ptq": [6, 20, 42, 53, 98, 102, 104, 105], "success": [6, 20], "sequenc": [6, 8, 20, 52, 91, 92, 93, 101, 106], "consum": [6, 20, 49, 92, 100], "non": [6, 20, 52, 61, 108, 111], "expert": [6, 20], "effort": [6, 20, 42, 53, 92], "analyz": [6, 20, 30, 38, 47, 56, 67, 78, 87, 88, 89, 92, 94, 101, 104, 111, 112], "automat": [6, 20, 30, 36, 56, 65, 74, 75, 83, 95, 100, 102, 104, 109], "variou": [6, 12, 20, 25, 30, 45, 56, 59, 100, 102, 107, 108, 109, 112], "best": [6, 13, 20, 42, 53, 92, 95, 100, 102, 108], "heurist": [6, 20], "toler": [6, 20, 92, 95], "cumul": [6, 20], "until": [6, 20, 42, 53, 78, 89, 92], "evalu": [6, 8, 20, 28, 30, 33, 37, 39, 42, 45, 46, 48, 51, 53, 56, 59, 66, 68, 70, 90, 92, 96, 97, 100, 102, 104, 105, 108, 111], "creat": [6, 8, 12, 15, 16, 17, 20, 25, 28, 30, 33, 35, 36, 37, 39, 42, 44, 45, 46, 48, 51, 53, 54, 56, 59, 61, 63, 64, 65, 66, 68, 69, 71, 77, 82, 84, 86, 87, 88, 90, 91, 93, 96, 100, 101, 102, 105, 108], "auto_qu": [6, 20, 42, 53], "eval_dataset_s": [6, 7, 20, 42, 53], "5000": [6, 20, 42, 45, 53, 59], "been": [6, 7, 8, 13, 20, 35, 51, 62, 71, 77, 81, 82, 83, 86, 108, 114], "calibration_dataset_s": [6, 20, 42, 53], "20": [6, 7, 8, 9, 10, 11, 21, 23, 24, 28, 30, 35, 41, 49, 51, 68, 73, 91, 105], "eval_dataset": [6, 7, 37, 53], "unlabeled_dataset": [6, 7, 12, 37, 53], "prepar": [6, 29, 34, 37, 38, 42, 46, 51, 53, 60, 64, 66, 67, 68, 69, 92, 102, 109], "eval_callback": [6, 7, 12, 15, 16, 17, 20, 25, 30, 33, 37, 42, 46, 53, 56, 66, 70], "compil": [6, 7, 8, 10, 11, 12, 37, 39, 41, 48], "dictionari": [6, 7, 9, 30, 46, 56, 66, 68, 70, 97, 100, 106], "argument": [6, 7, 12, 25, 28, 32, 33, 37, 39, 41, 44, 45, 46, 48, 51, 58, 59, 61, 66, 68, 77, 79, 80, 83], "num_sampl": [6, 7, 18, 20, 37, 45, 53, 59], "whole": [6, 7, 83, 108], "sampled_dataset": [6, 7, 12], "adam": [6, 7, 8, 10, 11, 12, 37, 39, 90], "categoricalcrossentropi": [6, 7, 12, 37], "categoricalaccuraci": [6, 7, 12, 37], "acc": [6, 7, 8, 12, 37], "unlabeleddatasetwrapp": [6, 20, 53], "indic": [6, 13, 18, 20, 30, 36, 49, 53, 56, 69, 88, 95, 114], "seri": [6, 20, 68], "reach": [6, 20, 92], "furhter": [6, 20], "adaround": [6, 20, 42, 47, 53, 67, 72, 87, 92, 96, 102, 107, 109], "predefin": [6, 20], "were": [6, 13, 20, 32, 36, 44, 49, 51, 58, 64, 65, 68, 75, 86, 95, 106, 114], "empir": [6, 20, 103], "adaround_dataset_s": [6, 20, 42, 53], "adaround_dataset": 6, "adaround_param": [6, 20, 42, 53], "set_adaround_param": [6, 20, 42, 53], "correspond": [6, 13, 20, 28, 29, 32, 36, 41, 44, 45, 46, 51, 54, 58, 59, 64, 65, 66, 68, 73, 74, 75, 83, 86, 88, 94, 104, 108, 114], "counter": [7, 21, 38, 39, 68], "potenti": [7, 21, 36, 38, 52, 101, 111, 112], "instabl": [7, 21, 38], "varianc": [7, 21, 38, 103], "recalcul": [7, 21, 29], "By": [7, 18, 19, 21, 22, 23, 24, 29, 30, 35, 56, 64, 88, 91, 100, 108], "aim": [7, 15, 16, 17, 21, 29], "make": [7, 8, 9, 13, 21, 29, 34, 36, 38, 60, 63, 67, 83, 88, 101, 102], "our": [7, 8, 21, 29, 46, 64, 66, 73, 75, 90], "stabl": [7, 21, 29, 61, 69, 91], "rather": [7, 21, 29, 61, 106], "noisi": [7, 21, 29], "6": [7, 8, 9, 10, 11, 17, 19, 22, 23, 24, 28, 35, 42, 51, 53, 61, 64, 68, 78, 83, 84, 86, 105, 107], "simul": [7, 8, 15, 16, 17, 25, 32, 38, 39, 44, 47, 48, 49, 51, 55, 58, 60, 63, 64, 67, 68, 79, 80, 83, 86, 87, 88, 90, 98, 102, 105, 109], "7": [7, 16, 17, 19, 21, 22, 23, 24, 36, 53, 54, 64, 68, 74, 75, 78, 79, 80, 90, 107, 114], "dir": [7, 12, 13, 14, 48, 69, 75], "accuraci": [7, 8, 12, 20, 21, 25, 26, 28, 30, 32, 33, 39, 41, 42, 44, 45, 51, 53, 56, 58, 59, 64, 68, 83, 87, 90, 91, 92, 95, 97, 98, 100, 102, 103, 104, 105, 107, 108, 109, 112, 114], "helper": [7, 21, 33, 53, 59], "train_dataset_s": 7, "re_estimation_dataset_s": 7, "train_dataset": 7, "re_estimation_dataset": 7, "current": [7, 8, 9, 18, 25, 30, 33, 35, 39, 52, 56, 59, 62, 63, 77, 99, 113], "built": [7, 8, 45, 59, 73, 74, 77, 88], "sequenti": [7, 8, 9, 34, 35, 72, 106, 107], "subclass": [7, 8, 34, 35, 77, 84], "incompat": [7, 8, 90], "backend": [7, 28], "clear_sess": [7, 28], "conv2d": [7, 8, 13, 35, 36, 49, 52, 61, 62, 65, 72, 77, 83, 88, 90, 94, 100, 109, 114], "conv1": [7, 15, 16, 17, 35, 52, 56, 60, 61, 62, 65, 70, 90], "fuse": [7, 106, 108], "relu": [7, 8, 9, 34, 35, 36, 49, 52, 55, 60, 61, 62, 65, 69, 72, 88, 90, 103, 106, 114], "maxpooling2d": 7, "conv2": [7, 35, 49, 56, 60, 61, 65, 83, 90], "flatten": [7, 61, 88], "dens": [7, 8, 9, 34, 35, 36, 69], "functional_model": [7, 8, 9], "fp32": [7, 8, 25, 32, 33, 37, 44, 45, 46, 58, 59, 64, 66, 91, 98, 103, 104, 105, 107, 108], "baselin": [7, 8, 20, 33, 45, 59, 90, 97, 100, 105], "loss_fn": [7, 90], "fit": [7, 8, 10, 11, 21, 30, 39, 56, 68, 97], "test": [7, 8, 9, 37, 46, 52, 54, 66, 69, 75], "training_range_learning_with_tf_init": [7, 11, 21, 24, 28, 51, 68], "json": [7, 12, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114], "default_config_per_channel": 7, "is_output_quant": [7, 106], "is_quant": [7, 106], "is_symmetr": [7, 49, 84, 106], "strict_symmetr": [7, 106], "unsigned_symmetr": [7, 106], "per_channel_quant": [7, 13, 49, 88, 106], "squeez": [7, 18], "pad": [7, 35, 52, 61, 62, 90], "supergroup": [7, 106, 109], "op_list": [7, 106], "clip": [7, 84, 106, 108], "gemm": [7, 106], "model_input": [7, 62, 106], "is_input_quant": [7, 106], "model_output": [7, 106], "open": 7, "tmp": [7, 12, 25, 37, 42, 46, 53, 66, 90], "w": [7, 33, 45, 46, 59, 66, 74, 114], "f": [7, 20, 42, 53, 61, 62, 73, 74, 75, 90], "dump": 7, "qsim": [7, 29, 69], "config_fil": [7, 12, 13, 25, 28, 37, 39, 42, 46, 48, 53, 55, 66, 68], "posit": [7, 8, 9, 35, 78], "15": [7, 8, 10, 11, 21, 23, 24, 68, 78, 100, 105], "job": [7, 8, 10, 11, 15, 16, 17, 21, 23, 24, 68], "good": [7, 8, 10, 11, 15, 16, 17, 21, 23, 24, 35, 64, 67, 68, 90, 91, 100], "rate": [7, 8, 9, 10, 11, 15, 16, 17, 21, 23, 24, 35, 68, 100, 105], "end": [7, 8, 10, 11, 15, 16, 17, 21, 23, 24, 28, 29, 31, 33, 51, 53, 54, 57, 61, 62, 66, 68, 78, 89, 90, 100], "factor": [7, 8, 10, 11, 15, 16, 17, 21, 23, 24, 36, 65, 68, 83, 84, 95, 100, 103], "feel": [7, 8, 21, 68, 74], "quantized_callback": [7, 8, 10, 11], "tensorboard": [7, 8, 10, 11], "log_dir": [7, 8, 10, 11], "histori": [7, 8, 10, 11], "validation_data": [7, 8, 10, 11], "reestimate_bn_stat": [7, 21, 29, 54], "reestim": [7, 29], "100": [7, 21, 29, 33, 45, 53, 54, 59, 72, 84, 86, 90], "adapt": [7, 13, 21, 38, 54, 64, 67, 87, 90, 91, 96, 102, 104, 109], "yield": [7, 21, 45, 46, 51, 54, 59, 66, 95, 107, 108], "directli": [7, 21, 29, 42, 46, 63, 66, 72, 104, 108], "bn_reestim": [7, 21, 29, 54], "far": [7, 21, 91], "first": [7, 8, 9, 12, 13, 15, 16, 17, 21, 25, 30, 35, 38, 51, 61, 67, 69, 88, 90, 100, 102, 105, 107], "effici": [7, 21, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114], "fold_all_batch_norms_to_scal": [7, 21, 29, 54], "mnist_after_bn_re_estimation_qat_range_learn": 7, "exampl": [8, 9, 20, 34, 52, 60, 62, 63, 64, 77, 78, 79, 80, 81, 82, 83, 84, 88, 89, 90, 91, 95, 98, 102, 104, 106, 107, 108, 109, 114], "pipelin": [8, 10, 11, 32, 44, 53, 54, 58, 68, 102, 105, 107, 108], "1": [8, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 50, 51, 52, 53, 54, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 91, 92, 93, 94, 95, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 110, 111, 112, 113, 114], "dataset": [8, 28, 29, 30, 33, 37, 42, 45, 46, 48, 51, 53, 54, 55, 59, 66, 68, 90, 96, 102, 103, 108], "2": [8, 28, 30, 35, 36, 39, 41, 42, 45, 48, 51, 52, 53, 54, 56, 58, 59, 61, 62, 64, 65, 66, 68, 69, 72, 73, 74, 77, 78, 79, 80, 81, 83, 84, 86, 89, 91, 95, 97, 102, 107, 108], "3": [8, 28, 30, 31, 33, 36, 37, 39, 42, 43, 45, 46, 48, 51, 52, 53, 54, 55, 56, 57, 58, 59, 61, 62, 64, 65, 66, 68, 69, 70, 71, 72, 73, 78, 81, 83, 84, 90, 95, 102, 105, 107], "imdb": 8, "sentiment": 8, "vocab_s": [8, 9, 35], "20000": [8, 9, 35], "consid": [8, 15, 17, 52, 107, 110, 113], "20k": 8, "word": [8, 83], "maxlen": [8, 9, 35], "200": [8, 9, 20, 35, 72], "movi": 8, "review": 8, "x_train": [8, 29], "y_train": 8, "x_val": 8, "y_val": 8, "load_data": 8, "num_word": 8, "pad_sequ": 8, "embed_dim": [8, 9, 35], "embed": [8, 9, 35, 61, 68, 88, 100, 107], "token": [8, 9, 35, 107], "num_head": [8, 9, 35], "attent": [8, 9, 35], "head": [8, 9, 35], "ff_dim": [8, 9, 35], "hidden": [8, 9, 35], "feed": [8, 9, 35, 108], "insid": [8, 9, 30, 35, 61, 74, 77, 88, 90], "delta": [8, 9, 35, 37, 46, 66, 84, 108], "input_dim": [8, 9, 35], "output_dim": [8, 9, 35], "block": [8, 53, 72, 78, 83, 86, 89], "multiheadattent": [8, 9, 35, 109], "key_dim": [8, 9, 35], "dropout": [8, 9, 35, 88], "layernorm": [8, 9, 35, 88], "epsilon": [8, 9, 35], "1e": [8, 9, 35, 52, 64, 90, 105], "globalaveragepooling1d": [8, 9, 35], "softmax": [8, 9, 18, 35, 88, 90], "functional_callback": 8, "histogram_freq": 8, "sparse_categorical_crossentropi": 8, "128": [8, 10, 11, 45, 59, 61, 81, 83, 90], "wrap": [8, 12, 25, 61, 72], "visual": [8, 12, 25, 26, 30, 50, 56, 67, 74, 100, 102, 103, 104, 107, 109], "multi": [8, 67, 109], "encount": [8, 77, 90], "access": [8, 18, 19, 22, 23, 24, 67, 72, 74], "within": [8, 77, 81, 88, 95, 104, 108], "granular": [8, 15, 16, 17, 30, 56, 83, 100, 107, 108, 112], "mha": [8, 109], "accur": [8, 90], "clone_lay": 8, "u": [8, 13, 51, 74], "clone": [8, 96], "diagram": [8, 93, 98, 108], "m": [8, 73, 74, 75, 87, 96], "convert_to_pb": [8, 39], "inspect": [8, 100], "1024": [8, 48, 51, 68, 91, 101], "artifact": [8, 32, 44, 48, 58, 74, 90], "3000": [8, 81], "model_after_qat": [8, 10, 11], "anoth": [8, 64, 68, 113, 114], "most": [8, 83, 90, 106], "case": [8, 9, 12, 25, 37, 42, 46, 49, 53, 60, 61, 62, 64, 66, 72, 75, 78, 83, 88, 90, 97, 103, 106], "complex": [8, 28, 37, 39, 41, 46, 48, 66, 68], "around": [8, 13, 37, 46, 48, 51, 66, 68], "elementari": 8, "logdir": 8, "summari": [8, 71, 100], "vanilla": 8, "becaus": [9, 21, 35, 61, 69, 102], "tool": [9, 37, 66, 67, 87, 90, 103, 112, 114], "sequanti": 9, "build": [9, 35, 72], "dicuss": 9, "text": [9, 35, 78, 89], "transform": [9, 18, 19, 20, 22, 23, 24, 25, 35, 51, 53, 61, 68, 83, 86, 90, 109], "found": [9, 36, 65, 69, 72, 83, 105, 108], "tokenandpositionembed": [9, 35], "transformerblock": [9, 35], "super": [9, 35, 52, 61, 62, 69, 77, 90], "att": [9, 35], "ffn": [9, 35], "layernorm1": [9, 35], "layernorm2": [9, 35], "dropout1": [9, 35], "dropout2": [9, 35], "kwarg": [9, 35, 77, 78, 81, 88, 89], "attn_output": [9, 35], "out1": [9, 35], "ffn_output": [9, 35], "token_emb": [9, 35], "pos_emb": [9, 35], "With": [9, 12, 25, 81, 102, 105], "those": [9, 46, 66, 106], "random": [9, 20, 28, 33, 35, 37, 39, 42, 45, 46, 48, 53, 69, 94, 104], "random_input": [9, 35], "embedding_lay": [9, 35], "transformer_block": [9, 35], "token_and_position_embed": 9, "symmetr": [9, 48, 49, 64, 72, 77, 78, 81, 83, 84, 88, 89, 90, 106, 108], "model_prepar": [9, 18, 19, 21, 22, 23, 24, 25, 35, 37, 51, 54, 61, 66, 68, 69, 72, 90], "prepare_model": [9, 18, 19, 21, 22, 23, 24, 25, 35, 37, 51, 54, 61, 66, 68, 69, 72, 90], "input_lay": [9, 35], "begin": [9, 35, 52, 61, 62, 78, 89, 106], "unwrap": 9, "ident": [9, 34, 60, 90], "present": [9, 21, 26, 52, 58, 62, 64, 72, 83, 86, 90, 103], "get_weight": 9, "represent": [9, 49, 79, 80, 81], "reorder": 9, "get_original_models_weights_in_functional_model_ord": 9, "original_model": [9, 35], "ndarrai": [9, 33, 36, 42, 44, 45, 46, 48, 65], "arg": [9, 68, 77, 78, 81, 83, 86, 88, 89], "quick": [9, 13, 15, 17], "lookup": 9, "remov": [9, 29, 54, 61, 72, 74, 90, 94, 98, 108, 114], "match": [9, 28, 32, 37, 44, 46, 56, 58, 66, 68, 83, 94, 100, 104, 106, 107, 108, 114], "original_model_weight": 9, "pop": 9, "out": [9, 35, 37, 38, 39, 46, 47, 61, 64, 66, 67, 68, 78, 79, 80, 89], "weight_nam": 9, "functional_model_weight_ord": 9, "enumer": [9, 28, 30, 51, 56, 58, 68, 90], "sort": 9, "weights_in_correct_ord": 9, "item": [9, 12, 25, 42, 102], "weight_info": 9, "assert": [9, 18, 61, 72, 90], "count_param": 9, "output_shap": 9, "textclassif": 9, "what": [9, 90, 111], "architectur": [9, 67], "model_weights_in_correct_ord": 9, "assert_array_equ": 9, "modelprepar": [9, 18, 19, 22, 23, 24, 25, 29, 35, 51, 61, 68, 90], "arthmet": [9, 35], "experss": [9, 35], "tfoplambda": [9, 35], "ressembl": 9, "conv_1": [9, 35, 83], "conv_2": [9, 35], "becuas": [9, 35, 44], "rais": [9, 35, 77], "hopefulli": 9, "reflect": [10, 11, 23, 24, 102, 108], "imagenet_dir": [10, 11], "assign": [10, 11, 49, 64, 77, 78, 88, 89], "dataset_train": [10, 11], "dataset_valid": [10, 11], "respect": [10, 11, 34, 71, 88, 104], "categorical_crossentropi": [10, 11, 39], "finish": [10, 11, 23, 24], "against": [10, 11, 13, 21, 23, 24, 37, 46, 66, 71, 94], "Of": [10, 11, 13, 15, 16, 17, 23, 24, 83], "cours": [10, 11, 13, 15, 16, 17, 23, 24], "instal": [10, 11, 14, 20, 22, 23, 24, 87, 96, 98, 109, 111], "jointli": [11, 23, 24], "trainabl": [11, 24, 102], "showcas": [12, 25], "analys": [12, 25, 104], "respond": [12, 25], "repres": [12, 25, 28, 30, 33, 35, 37, 39, 41, 45, 46, 48, 49, 56, 59, 60, 64, 66, 68, 79, 80, 81, 88, 89, 90, 97, 103, 104, 105, 108], "second": [12, 25, 35, 51, 69, 83, 88, 106], "singl": [12, 13, 25, 28, 37, 45, 46, 56, 59, 61, 63, 66, 83, 91, 97, 100, 103], "val_dataset": 12, "shown": [12, 25, 36, 60, 63, 64, 72, 103, 104, 107, 114], "itself": [12, 21, 25, 44, 100, 108, 110], "amount": [12, 25, 33], "exactli": [12, 25, 77, 88, 108], "multipl": [12, 25, 30, 52, 56, 57, 58, 61, 62, 65, 68, 70, 75, 83, 88, 98, 100, 109], "demonstr": [12, 25, 33, 90, 96], "quant_analyz": [12, 25, 37, 46, 66, 67, 72], "enable_per_layer_mse_loss": [12, 25, 37, 46, 66], "choic": [12, 13, 25, 37, 49, 100, 108], "enhanc": [12, 25, 37, 46, 48, 64, 66, 104, 108], "track": [12, 25, 64, 84, 104], "minimum": [12, 25, 28, 51, 61, 68, 71, 73, 78, 84], "histogram": [12, 25, 37, 46, 66, 71, 84, 102, 104, 108, 109], "seen": [12, 25, 103, 104], "html": [12, 25, 46, 61, 66, 73, 74, 75, 82, 104, 109, 112], "folder": [12, 25, 71, 104], "structur": [12, 17, 25, 49, 61, 77, 88, 100], "per_layer_quant_en": [12, 25, 104], "per_layer_quant_dis": [12, 25, 104], "min_max_rang": [12, 25, 104], "activations_pdf": [12, 25, 104], "name_": [12, 25, 46, 66], "index_0": [12, 25], "index_1": [12, 25], "index_n": [12, 25], "weights_pdf": [12, 25, 104], "layer1": [12, 25, 36, 65], "param_name_": [12, 25, 46, 66], "channel_index_0": [12, 25], "channel_index_1": [12, 25], "channel_index_n": [12, 25], "layer2": [12, 25, 36, 65], "layern": [12, 25], "per_layer_mse_loss": [12, 25, 104], "axi": [12, 25, 49, 104], "associ": [12, 25, 28, 36, 42, 45, 53, 59, 62, 77, 88, 102], "sub": [12, 25, 52, 75, 108], "illustr": [13, 15, 16, 17, 68, 91, 94, 97, 102, 108, 110, 111, 113, 114], "round": [13, 28, 30, 37, 38, 39, 42, 47, 48, 53, 55, 56, 67, 68, 86, 87, 91, 96, 102, 104, 108], "awai": 13, "low": [13, 15, 17, 22, 67, 87, 91, 93, 100, 102, 103], "basi": [13, 49, 83], "2d": [13, 83, 94, 100, 114], "imagin": 13, "64": [13, 34, 35, 37, 46, 48, 51, 66, 68, 73, 78, 83, 84, 89, 91], "filter": [13, 35], "kernel": [13, 67, 77, 83, 94, 110, 113], "28": [13, 56, 59, 81], "entireti": [13, 35], "matrix": 13, "contrast": [13, 35, 72], "repeat": [13, 64, 90, 94], "uniqu": 13, "attribut": [13, 33, 35, 59, 61, 64, 72, 77, 88, 104], "conv2d_lay": 13, "kernel_s": [13, 35, 52, 61, 62, 69, 90], "snpe": [13, 14], "qnn": [13, 14], "describ": [13, 39, 49, 51, 61, 68, 72, 83, 96, 100, 101, 102, 103, 106, 107, 108, 111], "style": 13, "ensur": [13, 58, 74, 88, 97, 102, 107], "mismatch": 13, "togeth": [13, 83], "pcq_quantsim_config": 13, "tell": 13, "saw": 13, "fashion": [13, 83], "did": [13, 103], "translat": [13, 51], "down": [13, 49, 51], "fo": [13, 51], "r": [13, 33, 45, 46, 51, 59, 64, 66], "NOT": [13, 51], "frozen": [13, 51], "depend": [13, 61, 72, 74, 75, 81, 95, 96, 102, 106, 109], "observ": [13, 21, 71, 77, 84, 88, 89, 90, 100, 103, 104, 108], "slight": 13, "plai": 13, "resnet50_pcq_adaround": 13, "invok": [13, 28, 30, 36, 38, 41, 46, 48, 51, 56, 66, 67, 68, 77, 88, 100, 102, 111, 112], "lead": [14, 22, 37, 46, 66, 83, 91, 93, 103, 107], "shift": [14, 22, 67, 103], "adjust": [14, 22, 28, 51, 52, 68, 82, 83, 91, 93, 94, 95, 102, 103, 107], "aimet_cl": 14, "cle_applied_model": [14, 31], "resnet50_after_cl": 14, "arxiv": [14, 103], "ab": [14, 103], "1906": [14, 103], "04721": [14, 103], "memori": [15, 16, 17, 30, 56, 64, 84, 95, 100, 110, 113, 114], "restor": [15, 16, 17, 68, 107], "image_net_train": [15, 16, 17, 21, 22, 23, 24], "imagenettrain": [15, 16, 17, 21, 22, 23, 24], "nn": [15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 51, 52, 53, 56, 60, 61, 62, 63, 65, 66, 68, 69, 72, 77, 78, 82, 83, 87, 88, 89, 90, 101, 109], "bool": [15, 16, 17, 19, 21, 22, 23, 24, 25, 30, 33, 36, 39, 41, 42, 45, 48, 53, 55, 56, 59, 61, 64, 65, 68, 78, 83, 84, 89], "gpu": [15, 16, 17, 19, 21, 22, 23, 24, 25, 56, 58, 67, 69, 73, 74, 102, 109], "learning_r": [15, 16, 17, 21, 23, 24, 54, 68], "learning_rate_schedul": [15, 16, 17, 21, 23, 24, 54, 68], "schedul": [15, 16, 17, 21, 23, 24, 105], "trainer": [15, 16, 17, 21, 23, 24, 30, 56, 96], "max_epoch": [15, 16, 17, 21, 23, 24], "is_avail": [15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 54, 90], "target_comp_ratio": [15, 16, 17, 30, 56, 70], "ratio": [15, 16, 17, 30, 56, 70, 94, 95], "9": [15, 16, 17, 18, 19, 22, 23, 24, 25, 30, 33, 45, 51, 59, 61, 64, 68, 69, 75, 78, 81], "num_comp_ratio_candid": [15, 16, 17, 30, 56, 70], "tri": [15, 16, 17, 100, 102], "caus": [15, 16, 17, 35, 100, 101, 102, 106, 107], "33": [15, 16, 17, 75, 78, 89], "66": [15, 16, 17, 78, 89, 95], "00": [15, 16, 17, 78], "longer": [15, 16, 17, 72, 102, 105], "compromis": [15, 16, 17], "modules_to_ignor": [15, 16, 17, 30, 56, 66, 70, 99], "mode": [15, 16, 17, 30, 31, 39, 42, 43, 48, 53, 55, 56, 57, 61, 63, 65, 68, 70, 84, 89, 101, 102, 106], "much": [15, 16, 17, 114], "manual": [15, 16, 17, 30, 49, 56, 65, 72, 78, 89, 92, 100], "reconstruct": [15, 17, 28, 41, 51], "num_reconstruction_sampl": [15, 17, 56], "too": [15, 17, 83], "allow_custom_downsample_op": [15, 17, 56], "downsampl": [15, 17], "cost": [15, 17, 30, 56, 83, 97, 100, 105], "suggest": [15, 17, 39, 68, 97, 100, 103], "function_nam": [15, 16, 17], "eval_iter": [15, 16, 17, 30, 56, 70], "invoc": [15, 16, 17], "compress_schem": [15, 16, 17, 30, 56, 70], "cost_metr": [15, 16, 17, 30, 56, 70], "reduct": [15, 16, 17, 95, 102], "decim": [15, 16, 17, 30, 56, 70], "greedyselectionparamet": [15, 16, 17, 30, 56, 70], "channelpruningparamet": [15, 17, 56], "compressionschem": [15, 16, 17, 30, 56, 70], "costmetr": [15, 16, 17, 30, 56, 70], "greedy_param": [15, 16, 17, 30, 56, 70], "auto_param": [15, 16, 17, 30, 56, 70], "automodeparam": [15, 16, 17, 30, 56, 70], "greedy_select_param": [15, 16, 17, 30, 56], "channel_prun": [15, 17, 30, 56], "modelcompressor": [15, 16, 17, 30, 56, 70], "compress_model": [15, 16, 17, 30, 56, 70, 111], "relev": [15, 16, 17], "compressed_model": [15, 16, 30, 56], "comp_stat": [15, 16], "fall": [15, 16, 17, 97, 106], "sharpli": [15, 16, 17], "15e": [15, 17], "finetuned_model": [15, 16], "singular": [16, 17, 100, 110, 113], "decomposit": [16, 17, 100, 110, 113], "prune": [16, 30, 95, 96, 97, 99, 100, 109, 114], "spatialsvdparamet": [16, 17, 30, 56, 70], "spatial_svd": [16, 17, 30, 56, 70], "5e": [16, 17, 21, 23, 24, 54, 68], "ssvd_compressed_model": 17, "ssvd_comp_stat": 17, "ssvd_finetuned_model": 17, "further": [17, 26, 61, 72, 78, 81, 83, 89, 90, 91, 94, 98, 100], "ssvd_cp_compressed_model": 17, "cp_comp_stat": 17, "11": [17, 36, 49, 64, 73, 74, 75, 78, 81], "ssvd_cp_finetuned_model": 17, "imagefold": [18, 20], "tqdm": [18, 20], "root": [18, 20, 74, 75, 90], "compos": [18, 20, 53], "resiz": 18, "centercrop": [18, 20], "totensor": [18, 20, 53, 90], "images_mean": 18, "std": [18, 20], "images_std": 18, "manual_se": 18, "randperm": 18, "tolist": 18, "pin_memori": [18, 61], "evaluate_accuraci": 18, "top1_accuraci": 18, "dim": [18, 53, 69, 83, 90], "no_grad": [18, 19, 20, 22, 23, 24, 25, 51, 62, 68], "logit": [18, 20], "topk": [18, 20, 42], "certain": [18, 19, 22, 23, 24, 25, 51, 60, 61, 66, 68, 83, 100, 101, 106], "guidelin": [18, 19, 22, 23, 24, 25, 38, 41, 48, 51, 61, 67, 90, 102, 105], "autom": [18, 19, 22, 23, 24, 25, 38, 51, 60, 61, 67, 68, 102], "compli": [18, 19, 22, 23, 24, 25, 51, 68], "rand": [18, 19, 21, 22, 23, 24, 25, 28, 37, 45, 52, 58, 62], "modif": [18, 19, 22, 23, 24], "made": [18, 19, 22, 23, 24, 61, 106], "overrid": [18, 19, 22, 23, 24, 61, 68], "300": 18, "verifi": [19, 22, 23, 24, 35, 61], "resnet18_after_cle_bc": [19, 20, 22], "val_transform": 20, "normal": [20, 36, 52, 69, 104], "485": 20, "456": 20, "406": 20, "229": 20, "225": 20, "imagenet_dataset": 20, "_create_sampled_data_load": [20, 53], "subsetrandomsampl": [20, 53], "in_eval_mod": 20, "get_devic": 20, "_dataset": [20, 53], "k": 20, "view_a": 20, "__getitem__": [20, 53], "unlabeled_imagenet_dataset": 20, "unlabeled_imagenet_data_load": 20, "initial_accuraci": [20, 42, 53], "run_infer": [20, 42, 53], "adaround_data_load": [20, 42, 53], "optimized_accuraci": [20, 42, 53], "batchnrom": 21, "focu": 21, "unlik": [21, 79, 80], "script": 21, "didn": [21, 67], "statatist": 21, "finetuned_accuraci": [21, 23, 24], "train_load": [21, 54, 56, 90], "images_dir": 21, "finetuned_accuracy_bn_reestim": 21, "resnet18_after_qat": [21, 23, 24], "reload": 22, "techiqu": 22, "num_quant_sampl": [22, 55], "num_bias_correct_sampl": [22, 55], "quantparam": [22, 55], "bias_correct": [22, 55], "correct_bia": [22, 55], "bc_param": 22, "weight_bw": [22, 55], "act_bw": [22, 55], "round_mod": [22, 55], "held": [23, 24, 77, 88, 90], "Then": [23, 24, 28, 46, 51, 66, 68, 100], "matter": [25, 77], "softwar": [26, 98], "compress": [26, 27, 50, 87, 94, 96, 98, 109, 110, 112, 113, 114], "dramat": 26, "lost": [26, 87, 98, 108], "due": [26, 35, 62, 67, 83, 103], "At": [26, 95, 111], "onnx": [26, 49, 58, 60, 68, 73, 74, 87, 91, 92, 96, 98, 101, 102, 103, 104, 106, 108], "framework": [26, 48, 98, 102, 106, 108], "link": [26, 73, 75, 93, 96, 103, 104], "codebas": 26, "sphinx": 26, "page": [26, 69, 74, 75, 95, 108, 109], "qualcomm": [26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114], "innov": [26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114], "center": [26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114], "inc": [26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114], "quantsim_config": [26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114], "default_config": [26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114], "35": [26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114], "model": [27, 28, 29, 30, 31, 32, 33, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 88, 89, 91, 92, 93, 94, 95, 96, 97, 99, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114], "ai": [27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114], "toolkit": [27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114], "linear": [28, 29, 36, 41, 51, 54, 61, 62, 64, 65, 71, 72, 77, 83, 88, 90, 93, 94], "format": [28, 33, 34, 36, 39, 41, 46, 51, 64, 66, 68, 83, 86, 89, 92, 99], "prefix": [28, 39, 41, 51, 64, 68, 86, 88], "31": [28, 37, 41, 46, 51, 52, 55, 66, 68, 74, 75], "default_reg_param": [28, 41, 51], "default_beta_rang": [28, 41, 51], "default_warm_start": [28, 41, 51], "sourc": [28, 29, 30, 31, 32, 33, 35, 36, 37, 39, 41, 42, 43, 44, 45, 46, 48, 51, 53, 54, 55, 56, 57, 58, 59, 61, 64, 65, 66, 68, 69, 70, 71, 74, 75, 77, 78, 79, 80, 81, 82, 83, 84, 86, 88, 89, 107], "datasetv2": [28, 29], "stop": [28, 41, 51, 92], "beta": [28, 41, 51, 91], "anneal": [28, 41, 51], "start_beta": [28, 41, 51], "end_beta": [28, 41, 51], "warm": [28, 41, 51, 91], "period": [28, 41, 51, 91], "zero": [28, 41, 51, 64, 86, 108, 109], "post_training_percentil": [28, 51, 68], "percentil": [28, 51, 68, 84], "absolut": [28, 45, 51, 56, 59, 68, 78, 89], "nois": [28, 51, 67, 68, 84, 90, 102, 103, 104, 105, 106], "training_range_learning_with_tf_enhanced_init": [28, 51, 68], "aimetlogg": 28, "test_model": 28, "keras_model": 28, "dummy_forward_pass": [28, 69], "intend": [28, 37, 46, 49, 56, 66, 90, 96], "Or": [28, 37, 39, 41, 46, 48, 58, 61, 66, 68, 100], "someth": [28, 37, 39, 41, 46, 48, 66, 68, 100], "apply_adaround_exampl": [28, 41], "set_level_for_all_area": 28, "dataset_s": 28, "possible_batch": 28, "from_tensor_slic": [28, 29, 37], "w4a8": 28, "param_bw": [28, 42, 51, 53, 64], "output_bw": [28, 42, 51, 53, 64], "adarounded_model": [28, 51], "adarounded_sess": 28, "grid": [28, 51, 83], "awar": [29, 38, 54, 63, 77, 91, 93, 96, 98, 100, 102, 107, 108], "bn_re_estimation_dataset": 29, "bn_num_batch": 29, "handl": [29, 42, 53, 54, 83], "undo": [29, 54], "upon": [29, 54, 77, 88, 90], "batch_norm": [29, 36, 54, 65], "qcquantizewrapp": [29, 54], "pair": [29, 30, 36, 54, 55, 56, 65], "got": [29, 54, 61, 65], "overal": [30, 51, 56, 68, 95, 97, 107], "algorithm": [30, 33, 45, 49, 56, 59, 95, 97, 100, 107, 114], "tweak": [30, 36, 56, 64, 65], "compressor": [30, 56], "static": [30, 35, 56, 61, 108], "visualization_url": [30, 56, 70], "callabl": [30, 33, 41, 42, 45, 51, 53, 54, 56, 59, 61, 66, 77, 83], "url": [30, 56, 70, 74, 75, 96, 111], "appear": [30, 36, 52, 56, 61, 62, 65], "compressionstat": [30, 56], "use_monotonic_fit": [30, 56], "saved_eval_scores_dict": [30, 56, 70], "variabl": [30, 35, 56, 61, 74, 75, 78, 89, 96, 97], "express": [30, 56], "comp": [30, 56], "greater": [30, 36, 56, 65, 83, 95, 97], "monoton": [30, 56, 97], "dict": [30, 36, 39, 42, 45, 46, 48, 55, 56, 58, 59, 60, 61, 64, 65, 66, 68, 69, 88, 89], "eval_scor": [30, 46, 56, 66], "pickl": [30, 56], "input_op_nam": 30, "output_op_nam": [30, 33], "union": [30, 32, 35, 36, 39, 42, 44, 46, 51, 52, 53, 55, 56, 57, 58, 59, 65, 66, 68, 83, 86], "manualmodeparam": [30, 56], "rank": [30, 56, 64, 110, 113], "noth": [30, 56, 90], "list_of_module_comp_ratio_pair": [30, 56], "modulecompratiopair": [30, 56], "space": [30, 56, 83], "weight_svd": [30, 56], "comp_ratio": [30, 56], "ivar": 30, "aimet_common_def": 30, "aimet_tensorflow_def": 30, "inp_data": 30, "aimet_spatial_svd": 30, "evalfunct": 30, "denot": [30, 114], "80": [30, 78, 84, 89], "being": [30, 33, 34, 36, 49, 56, 60, 61, 62, 65, 66, 72, 83, 94], "driver": [30, 73, 75], "stat": [30, 46, 54, 56, 82, 84], "comprehens": 31, "detect": [31, 100], "shall": [31, 49], "cle": [31, 43, 57, 63, 67, 91, 92, 96, 102, 107, 109], "rtype": [31, 35, 36, 59, 81], "cross_layer_equalization_auto": [31, 57], "individu": [31, 36, 46, 57, 66, 83, 93, 97, 102, 104, 106, 107], "accord": [32, 44, 58, 102], "amongst": [32, 44, 58], "miss": [32, 35, 44, 49, 58, 62], "issu": [32, 35, 44, 52, 58, 62, 93, 98, 101, 107, 109, 111, 112], "layer_output_util": [32, 44, 58], "layeroutpututil": [32, 44, 58], "save_dir": 32, "keraslayeroutput": 32, "constructor": [32, 36, 44, 48, 55, 58, 60, 61, 65, 68], "generate_layer_output": [32, 44, 58], "input_batch": [32, 44, 58], "disk": [32, 44, 58], "obtain": [32, 36, 44, 46, 49, 58, 65, 69, 75, 95, 104], "aimet_export_artifact": [32, 44, 58], "h5": [32, 98, 102], "simplic": [32, 44, 58], "mandatori": [32, 44, 58], "load_encodings_to_sim": [32, 44, 58], "construct": [32, 44, 52, 58, 74, 75, 90, 101], "properli": [32, 44, 58, 78, 89, 90], "pre": [32, 44, 58, 73, 74, 75, 94, 98, 103, 104], "get_pre_processed_input": [32, 44, 58], "fp32_layer_output_util": [32, 44, 58], "fp32_layer_output": [32, 44, 58], "quantsim_layer_output_util": [32, 44, 58], "quantsim_layer_output": [32, 44, 58], "bitop": [33, 45, 59], "starting_op_nam": 33, "quantizergroup": [33, 45, 59], "wrt": 33, "vari": [33, 45, 59, 95, 103, 112], "earli": [33, 45, 59], "exit": [33, 45, 59, 77, 88, 90], "forward_pass_callback_2": 33, "nupi": 33, "last": [33, 99], "kept": [33, 107], "func": [33, 45, 59, 66], "encapsul": [33, 45, 59, 66], "back": [33, 45, 51, 59, 63, 68, 81, 90, 106], "OF": 33, "SUCH": 33, "damag": 33, "spdx": 33, "licens": 33, "identifi": [33, 55, 62, 74, 75, 83, 94, 96, 104, 107, 109, 114], "bsd": 33, "claus": 33, "copyright": 33, "pylint": 33, "statement": [33, 61, 67, 72, 101], "alpha": [33, 64], "directrori": 33, "preset": 33, "parent": [33, 77, 88], "retuern": 33, "seed": [33, 56], "set_se": 33, "evalutaion": 33, "org_top1": 33, "get_quantizated_model": 33, "accept": [33, 97, 103, 107], "09": 33, "cmp_re": 33, "mixed_preision_quant_model": 33, "fast_mixed_precis": 33, "sever": [34, 38, 60, 62, 67, 83, 88, 95, 104], "encourag": [34, 35, 38, 60, 61, 67], "mix": 34, "had": [34, 60, 90], "x2": [34, 60, 61], "relu2": [34, 35, 60, 62], "manditori": 35, "submodul": [35, 60], "via": [35, 67, 87, 95, 108], "inherit": [35, 77, 88], "pure": [35, 60], "over": [35, 42, 46, 53, 56, 66, 78, 84, 88, 91, 97, 100, 112], "inputlay": 35, "portion": 35, "taken": [35, 114], "get_text_classificaiton_model": 35, "model_preparer_two_subclassed_lay": 35, "get_subclass_model_with_functional_lay": 35, "sigmoid": [35, 61, 88], "binary_classifi": 35, "myfunctionalmodel": 35, "my_functional_model": 35, "classifi": 35, "model_preparer_subclassed_model_with_functional_lay": 35, "resembl": 35, "piec": [35, 61], "python": [35, 68, 73, 74, 75], "trace": [35, 60, 82], "symbol": 35, "touch": 35, "part": [35, 37, 42, 46, 53, 63, 66, 83, 100, 103, 104], "static_patch_count": 35, "guarante": 35, "furthermor": 35, "resu": 35, "resblock": 35, "twice": 35, "bad": 35, "bn1": [35, 52, 62, 65], "bn2": 35, "relu1": [35, 60, 62, 69], "plug": [36, 65], "conv2dtranspos": 36, "depthwiseconv2d": [36, 99], "crosslayersc": [36, 65], "scale_model": [36, 65], "clssetinfo": 36, "highbiasfold": [36, 65], "bias_fold": [36, 65], "cls_set_info_list": [36, 65], "bn_layer": [36, 65], "sigma": [36, 65], "element": [36, 49, 65], "model_transform_util": 36, "replace_relu6_with_relu": 36, "cross_layer_equalization_auto_stepwis": 36, "relu6": [36, 55, 65, 88, 103], "model_for_cl": 36, "folded_pair": [36, 65], "bn_dict": [36, 65], "conv_or_linear": 36, "fold_given_batch_norm": [36, 65], "layer_pair": [36, 65], "conv_linear": 36, "is_batch_norm_second": 36, "scale_cls_set": [36, 65], "cls_set": [36, 65], "cls_pair_1": [36, 65], "cls_pair_2": [36, 65], "hold": [36, 55, 65, 81, 83, 86, 88, 106, 107], "along": [36, 64, 65, 81, 83, 90, 105, 108], "depth": [36, 65, 87, 95, 107], "wise": [36, 46, 56, 65, 66, 86, 107], "clssetlayerpairinfo": [36, 65], "scale_factor": [36, 65], "relu_activation_between_lay": [36, 65], "relat": [36, 55, 56, 65, 72, 104, 108], "whose": [36, 58, 61, 65, 72, 82, 83, 103, 106], "cross_layer_equalization_manu": [36, 65], "get_example_layer_pairs_resnet50_for_fold": 36, "consecutive_layer_list": [36, 65], "get_consecutive_layer_list_from_resnet50_for_sc": 36, "scaling_factor_list": [36, 65], "format_info_for_high_bias_fold": 36, "conv_op_1": 36, "bn_op_1": 36, "conv_op_2": 36, "bn_op_2": 36, "conv_op_3": 36, "bn_op_3": 36, "bn_op": 36, "upstream": [36, 94, 114], "downstream": [36, 49, 114], "usag": [36, 49, 62, 64, 68, 84, 87], "conv_op": 36, "bn_op_with_meta": 36, "_fold_upstream_flag": 36, "append": [36, 56], "boolean": [36, 77], "is_relu_activation_in_cls_set": 36, "fill": [36, 68], "create_cls_set_info_list": 36, "mse": [37, 46, 66, 72, 104, 108], "quantanalyz": [37, 46, 47, 66, 67, 72, 102, 109], "pdf": [37, 46, 66, 109], "scalar": [37, 46, 66], "hotspot": [37, 46, 66, 104], "stochast": [37, 39, 55, 68], "toi": [37, 45, 59], "num_class": [37, 39, 53], "ey": 37, "image_dataset": 37, "label_dataset": 37, "serv": [37, 42, 46, 53, 66, 88, 111], "own": [37, 42, 46, 48, 51, 53, 54, 55, 66, 68], "action": [37, 46, 48, 51, 54, 55, 66, 68, 114], "prepared_model": [37, 51, 61, 66, 68, 69, 90], "forward_pass_callback_fn": [37, 46, 66], "eval_callback_fn": [37, 46, 66], "approxim": [37, 46, 66, 91, 95, 103, 104], "quant_analyzer_result": [37, 46, 66], "abil": [38, 47, 67, 109], "hardwar": [38, 47, 67, 71, 98, 102, 103, 108], "cross": [38, 42, 47, 53, 55, 63, 67, 71, 91, 92, 96, 101, 102, 104, 107, 112], "estim": [38, 67, 90, 102, 103], "in_plac": [39, 68], "default_data_typ": [39, 48, 68], "mechan": [39, 61, 68], "rule": [39, 83, 106], "custom_object": 39, "pth": [39, 56, 58, 64, 68], "quantize_model": [39, 48], "dummy_x": 39, "dummy_i": 39, "randint": 39, "to_categor": 39, "lr": [39, 90], "param_bw_override_list": [41, 51], "ignore_quant_ops_list": [41, 51], "default_config_fil": [41, 51], "user_onnx_lib": [41, 48], "modelproto": [41, 42, 43, 44, 46, 48], "affect": [41, 51, 83, 93, 106], "id": [41, 42, 44, 53, 70, 74, 111], "librari": [41, 48, 64, 69, 100], "commonli": [41, 51], "among": [41, 42, 51], "ceil": [41, 42, 51], "10k": [41, 51], "15k": [41, 51], "simplifi": [41, 42, 43, 44, 45, 46, 48, 72], "ada_rounded_model": 41, "auto_quant_v2": [42, 53], "cache_id": [42, 53], "strict_valid": [42, 53], "integr": [42, 47, 53, 63, 64, 67, 102], "includ": [42, 45, 49, 53, 59, 68, 72, 82, 83, 93, 97, 104, 105, 106, 108, 109, 111], "manner": [42, 53, 92], "onnxmodel": [42, 46], "proce": [42, 53, 92], "unid": [42, 53], "unintuit": [42, 53], "explicitli": [42, 86, 114], "get_quant_scheme_candid": 42, "highest": [42, 97], "_quantschemepair": 42, "set_quant_scheme_candid": 42, "math": [42, 84, 90], "onnx_model": [42, 43, 46, 48], "dummy_data": [42, 46, 48], "astyp": [42, 45, 46, 48], "float32": [42, 45, 46, 48, 69], "Its": [42, 114], "fed": 42, "unlabelled_data_load": 42, "num_of_sampl": 42, "evaldataload": 42, "acc_top1": 42, "acc_top5": 42, "batch_avg_top_1_5": 42, "4f": [42, 53], "happen": [43, 57, 90], "dir_path": [44, 58], "wherein": [44, 58], "dummy_input_dict": 44, "amp": [45, 59], "quantizer_group": [45, 59], "parameter_quant": [45, 59], "factori": [45, 59], "activation_quant": 45, "get_activation_quant": 45, "name_to_quantizer_dict": [45, 59], "get_active_quant": [45, 59], "qcquantizeop": 45, "get_candid": [45, 59], "get_param_quant": 45, "set_quantizers_to_candid": [45, 59], "bw": [45, 59, 60, 64, 68, 83], "to_list": [45, 59], "quantizer_info": 45, "fp32_output": 45, "quantize_with_mixed_precis": [45, 59], "flow": [45, 59, 61, 63, 67, 102, 107, 108], "algo": [45, 59], "default_bitwidth": [45, 59], "eval_callback_for_phase_1": [45, 59], "eval_callback_func": [45, 59], "eval_callback_for_phase_2": [45, 59], "clean": [45, 59], "quantize_with_mixed_precision_start_from_existing_cach": [45, 59], "90": [45, 59], "number_of_sampl": [45, 59], "popul": [45, 49, 59], "perform_ev": [45, 59], "in_tensor": 45, "historgram": 46, "unlabeled_dataset_iter": [46, 53, 66], "interest": [46, 66], "create_quantsim_and_encod": 46, "check_model_sensitivity_to_quant": [46, 66], "perform_per_layer_analysis_by_enabling_quant": 46, "occurr": [46, 66, 94], "record": [46, 52, 66, 84], "layer_nam": [46, 52, 66], "perform_per_layer_analysis_by_disabling_quant": 46, "export_per_layer_encoding_min_max_rang": [46, 66], "esults_dir": [46, 66], "pcq": [46, 66, 93, 104], "param_nam": [46, 66], "export_per_layer_stats_histogram": [46, 66], "ctivations_pdf": [46, 66], "eights_pdf": [46, 66], "n": [46, 66, 83, 90, 109], "am": [46, 66], "channel_index": [46, 66], "export_per_layer_mse_loss": [46, 66], "discard": [46, 66], "unlabeled_data_load": [46, 53, 66], "_get_unlabled_data_load": [46, 66], "autoqu": [47, 67, 96, 102, 105, 109], "unifi": [47, 67], "use_symmetric_encod": [48, 72], "attempt": [48, 102, 103], "line": [48, 51, 54, 55, 68, 71], "max_batch_count": [48, 51, 68], "current_batch_count": [48, 51, 68], "forward_pass_funct": 48, "syntax": 49, "usabl": 49, "xx": 49, "yy": 49, "zz": 49, "major": [49, 100], "revis": 49, "minor": [49, 109], "patch": 49, "substanti": 49, "fulli": [49, 67, 90, 99, 100, 113], "bug": [49, 109], "backward": [49, 65, 90], "assum": [49, 53, 75, 83, 86, 97], "string": [49, 106], "activation_encod": 49, "tensor_nam": 49, "param_encod": [49, 72], "constraint": [49, 83], "depict": 49, "6086959838867188": 49, "109158515930176": 49, "114": 49, "018501389771699905": 49, "21": [49, 84], "558866932988167": 49, "12636379897594452": 49, "12": [49, 73, 74, 75, 78, 83, 84], "010530316270887852": 49, "06318144500255585": 49, "06268782913684845": 49, "127": [49, 81], "0004936049808748066": 49, "fc1": [49, 61], "05589814856648445": 49, "05546144023537636": 49, "0004367042565718293": 49, "184721499681473": 49, "10788747668266296": 49, "0089906234367221": 49, "conv2d_1": 49, "1020304188132286": 49, "10380396991968155": 49, "008650330936207491": 49, "readvariableop": 49, "1462666392326355": 49, "1451239287853241": 49, "126": 49, "0011427081098743512": 49, "08333279937505722": 49, "08268175274133682": 49, "0006510374592799766": 49, "dtype": [49, 61, 64, 72, 79, 80, 81, 83, 86], "datatyp": [49, 69], "highlight": [49, 103, 111, 112], "quantizer_arg": 49, "activation_bitwidth": 49, "param_bitwidth": 49, "broken": 49, "occur": [49, 82, 83, 86], "who": 49, "benefit": [49, 83, 91], "knowledg": 49, "experiment": [51, 52, 53, 66, 68, 72, 83, 100], "v2": [51, 53, 66, 68, 77, 78, 79, 80, 81, 82, 83, 84, 86, 87, 88, 89, 90], "namespac": [51, 53, 66, 67, 68, 72], "visit": [51, 53, 66, 68, 75, 87], "overview": [51, 53, 66, 68, 72], "pars": [51, 68, 86], "get_train_dataload": [51, 54], "emploi": [51, 68], "quantized_resnet18": [51, 68], "arch_check": 52, "archcheck": 52, "check_model_arch": 52, "result_dir": 52, "_node_check_dict": 52, "arch_checker_report": 52, "dotted_name_op": 52, "nodeerrorreportobject": 52, "archcheckerreport": 52, "condit": [52, 61, 62], "modelwithnotenoughchannel": 52, "prelu": [52, 88], "stride": [52, 61, 62, 90], "batchnorm2d": [52, 62, 65, 88, 90], "example_check_for_number_of_conv_channel": 52, "fewer": [52, 100], "logger": [52, 62], "_check_conv_channel_32_bas": 52, "_check_conv_channel_larger_than_32": 52, "modelwithprelu": 52, "prelu1": 52, "example_check_for_non_performant_activ": 52, "num_paramet": 52, "_activation_check": 52, "standalon": [52, 102], "modelwithnonfoldablebn": 52, "foldabl": 52, "avg_pool1": 52, "avgpool2d": [52, 88], "example_check_for_standalone_bn": 52, "averagepool": 52, "prevent": [52, 61, 72, 94, 101], "ep": [52, 90], "05": [52, 64, 78, 90], "momentum": [52, 90], "affin": [52, 64, 67, 77, 81, 83, 86, 87, 88, 89, 90], "track_running_stat": [52, 90], "_check_batch_norm_fold": 52, "model_prepare_requir": 53, "hen": 53, "_subset_sampl": 53, "sampler": 53, "fp32_model": 53, "fakedata": 53, "eval_data_load": 53, "num_correct_predict": 53, "argmax": [53, 90], "deprec": [53, 72, 102], "dummy_input_on_cpu": 53, "dummy_input_on_gpu": 53, "preced": [54, 114], "var": 54, "load_fp32_model": 54, "imagenetpipelin": 54, "quant_sim": [54, 68], "quant_param": 55, "conv_bn_dict": 55, "perform_only_empirical_bias_corr": 55, "layers_to_ignor": 55, "unless": [55, 75, 77, 86, 114], "remain": [55, 72, 102, 103, 108], "calc": 55, "corr": 55, "irrespect": 55, "fact": [55, 83], "elig": 55, "input_bn": 55, "output_bn": 55, "in_activation_typ": 55, "no_activ": 55, "out_activation_typ": 55, "hode": 55, "No": [55, 62], "mobilenetv2": [55, 65], "512": 55, "module_prop_dict": 55, "find_all_conv_bn_with_activ": 55, "train_model": 56, "train_flag": 56, "weightsvdparamet": 56, "rank_select_schem": 56, "select_param": 56, "rankselectschem": 56, "tar": 56, "evaluate_model": 56, "honor": 56, "obvious": 56, "spatial_svd_auto_mod": 56, "mnist": 56, "mnist_trained_on_gpu": 56, "pretti": 56, "easili": 56, "spatial_svd_manual_mod": 56, "manual_param": 56, "weight_svd_auto_mod": 56, "rank_select": 56, "weight_svd_manual_mod": 56, "channel_pruning_auto_mod": 56, "mnist_torch_model": 56, "dataloadermnist": 56, "channel_pruning_manual_mod": 56, "_layer_db": 56, "ture": 56, "batch_callback": 56, "spatial_svd_auto_mode_with_layerwise_finetun": 56, "torchscript": [58, 68, 87], "naming_schem": 58, "namingschem": 58, "onnx_export_arg": [58, 68, 69], "onnxexportapiarg": [58, 68], "numer": 58, "onnx_util": 58, "pythonpath": [58, 96], "successfulli": 58, "map_loc": 58, "model_torch": 58, "phase2_revers": 59, "phase2": 59, "input_quant": [59, 72, 77, 88, 90], "output_quant": [59, 72, 77, 88, 90], "supported_kernel_op": 59, "get_input_quantizer_modul": 59, "roughli": 59, "convers": 60, "onnx_file_nam": 60, "jit": 60, "traceabl": [60, 61], "stateless": 60, "former": 60, "retrain": [60, 102], "whenev": [60, 90], "image_rgb": 60, "rgb_output": 60, "image_bw": 60, "bw_output": 60, "rgb": 60, "elementwis": [61, 88, 109], "unrol": 61, "independ": [61, 107], "modules_to_exclud": 61, "module_classes_to_exclud": 61, "concrete_arg": 61, "instanc": [61, 62, 68, 77, 111], "duplic": 61, "exclud": [61, 62, 66, 86], "partial": 61, "special": [61, 90], "control": [61, 88, 108], "won": 61, "symbolic_trac": 61, "graphmodul": [61, 90], "modelwithfunctionalrelu": 61, "9216": 61, "fc2": 61, "model_preparer_functional_exampl": 61, "allclos": 61, "modelwithreusedrelu": 61, "model_preparer_reused_exampl": 61, "modelwithelementwiseaddop": 61, "x1": 61, "model_preparer_elementwise_add_exampl": 61, "dynam": [61, 79, 80, 103, 108, 109, 112], "branch": [61, 96, 106], "weren": 61, "traceerror": 61, "workaround": [61, 101], "problem": [61, 107], "across": [61, 64, 83, 103, 104, 112], "Such": 61, "concret": 61, "truli": 61, "scope": 61, "preserv": 61, "custom_function_not_to_be_trac": 61, "call_funct": 61, "__torch_function__": 61, "sqrt": 61, "modelwithnontorchfunct": 61, "model_transform": 61, "tracer": 61, "is_leaf_modul": 61, "leaf": [61, 86, 109], "expos": [61, 91, 104], "module_to_exclud": 61, "examin": 61, "custommodul": 61, "softplu": [61, 88], "custommodel": 61, "arang": [61, 69, 78], "traceback": 61, "typeerror": 61, "receiv": 61, "invalid": [61, 83], "proxi": 61, "layout": 61, "requires_grad": [61, 81], "problemat": [61, 107, 112], "determinist": 61, "hard": 61, "do_not_trace_m": 61, "known": [62, 83, 98], "share": [62, 69, 88], "modelwithreusednod": 62, "inplac": 62, "2592": [62, 84], "view": [62, 69, 82, 87, 90, 93, 98, 101, 103, 104, 111], "model_valid": 62, "modelvalid": 62, "validate_example_model": 62, "validate_model": 62, "validate_for_reused_modul": 62, "0x7f127685a598": 62, "resolv": 62, "warn": [62, 102], "redefin": [62, 90], "distinct": [62, 90], "rewrit": [62, 101], "modelwithoutreusednod": 62, "rerun": 62, "0x7ff577373598": 62, "validate_for_missing_modul": 62, "0x7ff5703eff28": 62, "modelwithfunctionallinear": 62, "0x7f9dd9bd90d0": 62, "matmul_8": 62, "connectedgraph": 62, "op_type_map": 62, "recogn": [62, 108], "functional_op": 62, "modelwithoutfunctionallinear": 62, "parallel": [63, 84], "dataparallel": [63, 67], "move": [63, 96, 102], "forth": 63, "huggingfac": 64, "similar": [64, 83, 103, 105, 108], "alon": 64, "loraconfig": 64, "get_peft_model": 64, "lora_config": 64, "lora_alpha": 64, "lora_dropout": 64, "target_modul": 64, "replace_lora_layers_with_quantizable_lay": 64, "meta": [64, 98, 102], "track_lora_meta_data": 64, "meta_data": 64, "tmp_dir": 64, "convinplacelinear": 64, "peftquantutil": 64, "peft_util": 64, "name_to_module_dict": 64, "disable_lora_adapt": 64, "recomput": 64, "freeze_base_model_param_quant": 64, "tmpdir": 64, "export_model": [64, 68], "filename_prefix_encod": [64, 68], "base_encod": 64, "enable_adapter_and_load_weight": 64, "lora_weights_after_adaptation_for_adapter1": 64, "safetensor": 64, "use_safetensor": 64, "lora_modul": 64, "get_quantized_lora_lay": 64, "param_quant": [64, 72, 77, 83, 88, 90], "quantizedequant": [64, 72, 78, 80, 81, 83, 88, 89, 90], "base_model": 64, "adapter1": 64, "export_adapter_weight": 64, "adapter1_weight": 64, "configr": 64, "adaptermetadata": 64, "lora_a": 64, "lora_b": 64, "replaced_module_typ": 64, "adapater_name_to_meta_data": 64, "init": 64, "track_meta_data": 64, "pt": 64, "adapter_weights_path": 64, "bin": [64, 74, 75, 84], "freeze_base_model": 64, "freeze_base_model_activation_quant": 64, "get_fp_lora_lay": 64, "quantize_lora_scale_with_fixed_rang": 64, "scale_min": 64, "scale_max": 64, "mul": 64, "set_bitwidth_for_lora_adapt": 64, "conv1d": [65, 88, 109], "convtranspose2d": [65, 88], "batchnorm1d": [65, 88], "cross_layer_equalization_auto_step_by_step": 65, "conv_bn": 65, "replace_modules_of_type1_with_type2": 65, "layer_list": 65, "clspairinfo": 65, "depthwis": [65, 93, 109], "cross_layer_equalization_depthwise_lay": 65, "perform_per_layer_analysis_by_enabling_quant_wrapp": 66, "perform_per_layer_analysis_by_disabling_quant_wrapp": 66, "wrapped_module_nam": 66, "tap": 66, "packag": [67, 86, 96, 109], "plan": 67, "upgrad": [67, 75], "flexibil": 67, "extens": [67, 74, 75, 88, 96], "futur": [67, 82, 83, 86], "releas": [67, 96, 101], "core": 67, "checker": 67, "concern": 67, "peft": 67, "lora": 67, "introduc": [67, 83, 88, 102, 106, 108], "power": [67, 107], "blockwis": [67, 86], "lpbq": [67, 86], "dispatch": 67, "carefulli": 67, "compatibil": 67, "public": 67, "seq_ms": [67, 72], "apply_seq_ms": [67, 72], "orthogon": 67, "migrat": 67, "quantizationmixin": [67, 87, 88], "save_checkpoint": 68, "file_path": 68, "checkpoint": [68, 98, 102], "load_checkpoint": 68, "quant_sim_model": 68, "propagate_encod": 68, "export_to_torchscript": 68, "use_embedded_encod": 68, "opset_vers": [68, 69], "enable_onnx_check": 68, "entri": [68, 106], "data_typ": [68, 72], "fakequ": 68, "trainingextens": 68, "src": 68, "forward_pass_arg": 68, "quatiz": 68, "unction": 68, "idea": [69, 90], "travel": 69, "sparseconvolution3d": 69, "spars": 69, "sparsetensorwrapp": 69, "sparseconvtensor": 69, "scriptmodul": 69, "scatterdens": 69, "pro": [69, 83], "spconv3d": 69, "spconvmodel": 69, "spconv_tensor": 69, "sparseconv3d": 69, "spconv1": 69, "in_channel": [69, 83, 90], "out_channel": [69, 83, 90], "spconv2": 69, "conv3d": [69, 88], "normal_conv3d": 69, "spconv_scatter_dens": 69, "coord": 69, "voxel": 69, "sp_tensor": 69, "sp_outputs1": 69, "sp_outputs2": 69, "sp_outputs2_dens": 69, "sp_output": 69, "sp_outputs_relu": 69, "dense_tensor_sp_input": 69, "ncdhw": 69, "permut": 69, "ndhwc": 69, "stack": 69, "meshgrid": 69, "ij": 69, "reshap": [69, 88], "operator_export_typ": 69, "operatorexporttyp": 69, "onnx_aten_fallback": 69, "converter_arg": 69, "input_dtyp": 69, "int32": 69, "expand_sparse_op_structur": 69, "preserve_io": 69, "exported_sp_conv_model": 69, "visualize_serialized_data": 70, "visualizecompress": [70, 111], "bokeh": [70, 71], "server": 70, "publish": [70, 71], "tabl": [70, 82, 96, 111], "display_eval_scor": [70, 111], "saved_eval_scores_dict_path": 70, "display_comp_ratio_plot": [70, 111], "comp_ratio_list_path": 70, "pkl": 70, "start_bokeh_server_sess": 70, "model_compression_with_visu": 70, "65": [70, 95], "resnet18_eval_scor": 70, "comp_ratios_file_path": 70, "greedy_selection_comp_ratios_list": 70, "eval_scores_path": 70, "compression_visu": 70, "termin": [70, 96], "visualize_model": 71, "visualize_relative_weight_ranges_to_identify_problematic_lay": 71, "selected_lay": 71, "figur": [71, 91, 94, 97, 107, 110, 111, 113, 114], "visualize_weight_rang": 71, "scatter": 71, "deviat": 71, "visualize_changes_after_optim": 71, "old_model": 71, "new_model": 71, "visualize_changes_in_model_after_and_before_cl": 71, "visualiz": 71, "model_copi": 71, "visualize_weight_ranges_model": 71, "usual": [71, 90, 100, 105, 108], "visualize_relative_weight_ranges_model": 71, "easier": [72, 83], "simpler": 72, "extend": 72, "fundament": 72, "advis": 72, "subject": 72, "interact": [72, 82], "hood": 72, "properti": 72, "compon": 72, "stai": 72, "quantizewrapp": 72, "quantizationsimmodelv1": 72, "all_quant_wrapp": 72, "quant_wrapp": 72, "staticgridquantwrapp": 72, "_module_to_wrap": 72, "in_featur": [72, 77, 88, 90], "out_featur": [72, 77, 88, 90], "quantizedlinear": [72, 77, 83, 88, 90], "quantizedconv2d": [72, 83, 88, 90], "quantizationsimmodelv2": 72, "sim2": 72, "all_q_modul": 72, "qmodul": 72, "q_modul": 72, "moduledict": [72, 77, 88, 90], "modulelist": [72, 77, 88, 90], "quantizedrelu": [72, 88, 90], "staticgridquant": 72, "learnedgridquant": 72, "tensor_quant": 72, "staticgridperchannelquant": 72, "fp_quantiz": 72, "affine_quant": 72, "affinequant": [72, 79, 80], "floatquant": [72, 79, 80], "q": [72, 77, 78, 79, 80, 81, 88, 89, 108], "affine_q": 72, "affine_qdq": 72, "fp_qdq": 72, "floatquantizedequant": [72, 80], "float16": [72, 79, 80, 83], "setup": [72, 73], "sim1": 72, "wrap_linear": 72, "qlinear": [72, 77, 88], "symmetri": 72, "is_unsigned_symmetr": 72, "use_strict_symmetr": 72, "sign": [72, 78, 108], "libpymo": 72, "tfencod": 72, "copy_": 72, "OR": 72, "_remove_input_quant": 72, "_remove_output_quant": 72, "_remove_param_quant": 72, "temporarili": 72, "_is_encoding_frozen": 72, "freeze_encod": 72, "concept": 72, "mimick": 72, "allow_overwrit": [72, 86, 89], "requires_grad_": 72, "overwritten": 72, "pypi": 73, "intel": 73, "x86": 73, "processor": 73, "linux": [73, 75], "ubuntu": [73, 75], "22": [73, 75, 84, 90], "04": [73, 75], "lt": [73, 75], "pip": [73, 74, 75, 87, 96, 111], "apt": [73, 74, 75, 87], "liblapack": [73, 74, 75, 87], "libpython3": 73, "dev": [73, 74, 75], "python3": [73, 74, 75, 87, 96], "variant": [73, 75, 91, 92, 93, 102, 103, 104, 108], "latest": [73, 74], "whl": [73, 74, 75], "host": [73, 74, 75, 109, 111], "github": [73, 74, 75, 96, 109], "com": [73, 74, 75, 96, 109], "quic": [73, 74, 75, 96, 109], "prerequisit": [73, 111], "requisit": [73, 75], "cu121": [73, 74, 75], "cp310": [73, 74, 75], "manylinux_2_34_x86_64": [73, 74, 75], "torch_stabl": [73, 74, 75], "13": [73, 74, 78, 84], "cu117": 73, "cu118": 73, "older": 73, "brows": [73, 74, 75], "bash": [73, 74], "command": [73, 74, 75, 96, 111], "shell": 73, "nvidia": [73, 74, 75], "card": 73, "capabl": [73, 88, 111], "docker": 73, "455": 73, "alwai": [73, 97], "newer": 73, "cudnn": 73, "machin": [73, 74, 100], "develop": [73, 74, 75, 82, 83, 86], "click": 73, "instruct": [74, 75, 87, 96], "variant_str": 74, "ONE": 74, "pt113": 74, "aimet_vari": 74, "workspac": [74, 96], "absolute_path_to_workspac": [74, 96], "docker_image_nam": 74, "codelinaro": 74, "docker_container_nam": 74, "any_nam": 74, "any_tag": 74, "jenkin": 74, "dockerfil": 74, "grep": 74, "kill": 74, "rm": 74, "passwd": 74, "ro": 74, "home": 74, "mnt": 74, "entrypoint": 74, "hostnam": 74, "filesystem": 74, "port": [74, 111], "port_id": 74, "project": [74, 75], "wish": [74, 75], "tip": [74, 75], "post1": [74, 75], "prepend": [74, 75, 88, 96], "sudo": [74, 75, 96], "wheel": [74, 75], "tag": [74, 75, 96, 109], "ex": [74, 75, 83], "34": [74, 75], "release_tag": [74, 75, 96], "download_url": [74, 75], "wheel_file_nam": [74, 75], "find_pkg_url_str": [74, 75], "usr": [74, 75], "lib": [74, 75], "dist": [74, 75], "envsetup": [74, 75], "sh": [74, 75], "pend": 75, "pip3": 75, "h": [75, 96, 113, 114], "local": [75, 96, 111], "accordingli": 75, "ye": [75, 100], "wget": 75, "gnupg2": 75, "archiv": 75, "exact": [75, 93, 102], "date": 75, "aforement": 75, "repo": 75, "ubuntu2204": 75, "x86_64": 75, "keyring_1": 75, "1_all": 75, "deb": 75, "dpkg": 75, "cat": 75, "reqs_deb_common": 75, "txt": 75, "xarg": 75, "reqs_deb_torch_common": 75, "reqs_deb_onnx_common": 75, "reqs_deb_tf_gpu": 75, "reqs_deb_torch_gpu": 75, "reqs_deb_onnx_gpu": 75, "uninstal": 75, "onnxruntime_v": 75, "c": [75, 95], "__version__": 75, "ln": 75, "gnu": 75, "libjpeg": 75, "chose": 75, "mixin": [77, 88], "quantizerbas": [77, 88, 89], "behav": [77, 88, 107], "abstract": [77, 88, 89], "__quant_init__": [77, 88], "initializd": [77, 88], "overridden": [77, 88, 106], "length": [77, 83, 88], "set_kernel": 77, "quantizedtensor": [77, 78, 81, 89], "keyword": 77, "output_encod": 77, "context": [77, 88, 90], "underli": [77, 107], "int_multipli": 77, "enc": 77, "notimplementederror": 77, "q_output": 77, "quantized_repr": [77, 81], "dq_output": 77, "qmult": 77, "quantizedmultipli": [77, 88], "classmethod": 77, "set_default_kernel": 77, "get_kernel": 77, "enter": [77, 88, 92], "is_initi": [77, 78, 79, 80, 88, 89], "from_modul": 77, "quantized_linear": 77, "get_default_kernel": 77, "retriev": 77, "module_cl": 77, "decor": 77, "subpackag": 77, "throw": 77, "declar": 77, "maskedadd": 77, "mask": 77, "quantizedmaskedadd": 77, "input_qtzr": 77, "value_qtzr": 77, "output_qtzr": 77, "clamp": [78, 79, 80, 89, 108], "lceil": [78, 79, 80, 89], "frac": [78, 79, 80, 89], "rfloor": [78, 79, 80, 89], "qmin": [78, 89, 108], "qmax": [78, 89, 108], "learnabl": [78, 89], "theta_": [78, 89], "pmatrix": [78, 89], "b_0": [78, 89], "b_1": [78, 83, 89], "cdot": [78, 89], "b_": [78, 89], "d": [78, 89], "equat": [78, 83, 89, 108], "out_": [78, 89], "j_0": [78, 89], "j_": [78, 89], "input_": [78, 89], "scale_": [78, 89], "i_0": [78, 89], "i_": [78, 89], "offset_": [78, 89], "quad": [78, 89, 108], "forall_": [78, 89], "leq": [78, 89], "i_d": [78, 89], "lfloor": [78, 79, 80, 89], "j_d": [78, 89], "b_d": [78, 89], "asymmetr": [78, 84, 89, 106, 108], "encoding_analyz": [78, 79, 80, 84, 89], "encodinganalyz": [78, 79, 80, 84, 89], "block_siz": [78, 83, 89], "129": [78, 89, 101], "255": [78, 81, 89], "122": [78, 89], "192": [78, 89], "106": [78, 89], "94": [78, 89], "145": [78, 89], "181": [78, 89], "144": [78, 89], "194": [78, 89], "74": [78, 89], "86": [78, 89], "150": [78, 89], "103": [78, 89], "37": [78, 89], "111": [78, 89], "237": [78, 89], "218": [78, 89], "49": [78, 89], "155": [78, 89], "179": [78, 89], "89": [78, 89], "110": [78, 89], "17": [78, 84, 89], "36": [78, 89], "83": [78, 89], "grad_fn": [78, 81, 89], "aliasbackward0": [78, 81, 89], "ones_lik": [78, 89], "187": [78, 89], "186": [78, 89], "131": [78, 89], "203": [78, 89], "143": [78, 89], "152": [78, 89], "226": [78, 89], "55": [78, 89], "172": [78, 89], "207": [78, 89], "146": [78, 89], "216": [78, 89], "238": [78, 89], "141": [78, 89], "178": [78, 89], "188": [78, 89], "63": [78, 89], "59": [78, 89], "19": [78, 84, 89], "162": [78, 89], "30": [78, 89], "109": [78, 89], "dequant": [78, 81, 89], "overlin": [78, 89], "qdq": [78, 79, 80, 89], "dequantizedtensor": [78, 81, 89], "2771": [78, 89], "3038": [78, 89], "0819": [78, 89], "9700": [78, 89], "9487": [78, 89], "1307": [78, 89], "7894": [78, 89], "1709": [78, 89], "2212": [78, 89], "7741": [78, 89], "0295": [78, 89], "2265": [78, 89], "0564": [78, 89], "6177": [78, 89], "0386": [78, 89], "0176": [78, 89], "6054": [78, 89], "8836": [78, 89], "1232": [78, 89], "8229": [78, 89], "5540": [78, 89], "3992": [78, 89], "2363": [78, 89], "2546": [78, 89], "0036": [78, 89], "2355": [78, 89], "1741": [78, 89], "6079": [78, 89], "6247": [78, 89], "0115": [78, 89], "2458": [78, 89], "9157": [78, 89], "4694": [78, 89], "0639": [78, 89], "2568": [78, 89], "0680": [78, 89], "6695": [78, 89], "7932": [78, 89], "1889": [78, 89], "0158": [78, 89], "5695": [78, 89], "5220": [78, 89], "1977": [78, 89], "4475": [78, 89], "0424": [78, 89], "1128": [78, 89], "8796": [78, 89], "1060": [78, 89], "5897": [78, 89], "6196": [78, 89], "9961": [78, 89], "0549": [78, 89], "6431": [78, 89], "0039": [78, 89], "8706": [78, 89], "4706": [78, 89], "2353": [78, 89], "8078": [78, 89], "3451": [78, 89], "1176": [78, 89], "4549": [78, 89], "0471": [78, 89], "5255": [78, 89], "4157": [78, 89], "0784": [78, 89], "5333": [78, 89], "1647": [78, 89], "2118": [78, 89], "2196": [78, 89], "9176": [78, 89], "9490": [78, 89], "7765": [78, 89], "4784": [78, 89], "6039": [78, 89], "3137": [78, 89], "3216": [78, 89], "8000": [78, 89], "4392": [78, 89], "4863": [78, 89], "overload": 78, "rceil": 78, "num_step": [78, 84], "num": 78, "_step": 78, "0000e": 78, "5000e": 78, "02": 78, "1921e": 78, "08": 78, "0500e": 78, "1000e": 78, "1500e": 78, "2000e": 78, "2500e": 78, "14": [78, 90], "quantize_dequant": 78, "0000": [78, 81], "0667": 78, "1333": 78, "2667": 78, "3333": 78, "4000": [78, 81], "4667": 78, "6000": [78, 81], "6667": 78, "7333": 78, "8667": 78, "9333": 78, "exponent_bit": [79, 80, 83], "mantissa_bit": [79, 80, 83], "cast": [79, 80], "expon": [79, 80, 83], "mantissa": [79, 80, 83], "x_c": [79, 80], "log_2": [79, 80], "ieee": [79, 80, 100, 103], "_max": [79, 80], "mutual": [79, 80, 83], "exclus": [79, 80, 83], "finer": [79, 80, 83], "8998": [79, 80], "0947": [79, 80], "0891": [79, 80], "1727": [79, 80], "is_bfloat16": [79, 80], "8984": [79, 80], "0859": [79, 80], "1729": [79, 80], "minmaxencodinganalyz": [79, 80, 84], "is_float16": [79, 80], "8994": [79, 80], "0889": [79, 80], "alia": [79, 80], "encodingbas": [81, 89], "57": 81, "312": 81, "153": 81, "205": 81, "set_rang": 81, "x_q": 81, "26": 81, "23": [81, 84], "x_dq": 81, "carri": 81, "gradient": 81, "thu": 81, "autograd": 81, "backpropag": 81, "38": [81, 100], "40": 81, "39": [81, 90], "51": 81, "521": 81, "41": 81, "quant_dequ": 81, "x_qdq": 81, "52": 81, "68": 81, "97": 81, "uint8": 81, "heavi": [82, 83, 86, 111, 112], "notic": [82, 83, 86], "visualization_tool": 82, "visualize_stat": 82, "save_path": 82, "quant_stats_visu": 82, "threshold": [82, 88, 92], "exce": 82, "exceed": 82, "counterpart": [83, 88], "come": [83, 100, 105], "split": 83, "con": 83, "storag": 83, "drawback": 83, "outlier": [83, 104, 108], "dimens": [83, 86, 88, 107, 110, 113], "influenc": 83, "resid": [83, 109], "chunk": 83, "isol": 83, "favor": 83, "relationship": 83, "long": [83, 86], "b_2": 83, "b_n": 83, "s_1": 83, "s_2": 83, "s_n": 83, "evenli": 83, "divid": [83, 88, 95, 105], "divis": 83, "permit": 83, "3d": 83, "arbitrari": 83, "restrict": [83, 101], "themselv": [83, 105], "linear_1": 83, "lie": 83, "leverag": 83, "expans": [83, 100], "groupedblockquantizedequant": 83, "decompressed_bw": 83, "expand": 83, "block_group": 83, "config_util": 83, "set_blockwise_quantization_for_weight": 83, "input_channel": 83, "linear1": 83, "isinst": 83, "signific": [83, 107], "switch": 83, "docstr": 83, "4d": 83, "mention": 83, "assist": 83, "set_activation_quantizers_to_float": 83, "set_grouped_blockwise_quantization_for_weight": 83, "decompress": 83, "addition": 83, "larger": [83, 110, 113], "encoding_vers": [83, 86], "exported_model": [83, 86], "gather": 84, "reset_stat": 84, "reset": 84, "update_stat": 84, "pow": 84, "0991": 84, "3696": 84, "_minmaxrang": 84, "1721": 84, "sqnrencodinganalyz": 84, "num_bin": 84, "2048": [84, 86], "asymmetric_delta_candid": 84, "symmetric_delta_candid": 84, "101": 84, "offset_candid": 84, "max_parallel": 84, "gamma": 84, "lowest": [84, 94], "3612": 84, "8497": 84, "_histogram": 84, "bin_edg": 84, "8907": 84, "3625": 84, "8343": 84, "3061": 84, "7779": 84, "2497": 84, "2784": 84, "8066": 84, "3348": 84, "8630": 84, "3912": 84, "7080": 84, "2438": 84, "percentileencodinganalyz": 84, "largest": 84, "smallest": 84, "1188": 84, "3368": 84, "27": 84, "5710": 84, "0989": 84, "6269": 84, "1548": 84, "6827": 84, "2106": 84, "2614": 84, "7335": 84, "2056": 84, "6776": 84, "1497": 84, "gptvq_weight": 86, "apply_gptvq": 86, "gptvq_param": 86, "param_encoding_path": 86, "module_names_to_exclud": 86, "block_level_module_nam": 86, "file_name_prefix": 86, "config_file_path": 86, "gptvqparamet": 86, "dataclass": 86, "row_axi": 86, "col_axi": 86, "rows_per_block": 86, "cols_per_block": 86, "vector_dim": 86, "vector_bw": 86, "vector_strid": 86, "index_bw": 86, "num_of_kmeans_iter": 86, "assignment_chunk_s": 86, "carrier": 86, "125m": 86, "optforcausallm": 86, "from_pretrain": 86, "facebook": 86, "gptvq_applied_model": 86, "lm_head": 86, "gptvq_opt": 86, "load_encod": 86, "deploi": [87, 108], "edg": [87, 98], "incur": [87, 98, 104], "workflow": [87, 90, 95, 98], "sample_input": [87, 90], "sample_output": 87, "out_dir": 87, "quantized_model": 87, "quickstart": 87, "product": [87, 95, 98], "technologi": [87, 98], "subsidiari": [87, 98], "extra": 88, "nativ": 88, "quantizedsoftmax": [88, 90], "qmul": 88, "sens": 88, "qadd": 88, "quantizedadd": 88, "calibration_data_load": 88, "adaptiveavgpool1d": 88, "quantizedadaptiveavgpool1d": 88, "adaptiveavgpool2d": 88, "quantizedadaptiveavgpool2d": 88, "adaptiveavgpool3d": 88, "quantizedadaptiveavgpool3d": 88, "adaptivemaxpool1d": 88, "quantizedadaptivemaxpool1d": 88, "adaptivemaxpool2d": 88, "quantizedadaptivemaxpool2d": 88, "adaptivemaxpool3d": 88, "quantizedadaptivemaxpool3d": 88, "alphadropout": 88, "quantizedalphadropout": 88, "avgpool1d": 88, "quantizedavgpool1d": 88, "quantizedavgpool2d": 88, "avgpool3d": 88, "quantizedavgpool3d": 88, "quantizedbatchnorm1d": 88, "quantizedbatchnorm2d": 88, "batchnorm3d": 88, "quantizedbatchnorm3d": 88, "celu": 88, "quantizedcelu": 88, "channelshuffl": 88, "quantizedchannelshuffl": 88, "constantpad1d": 88, "quantizedconstantpad1d": 88, "constantpad2d": 88, "quantizedconstantpad2d": 88, "constantpad3d": 88, "quantizedconstantpad3d": 88, "quantizedconv1d": 88, "quantizedconv3d": 88, "convtranspose1d": [88, 109], "quantizedconvtranspose1d": 88, "quantizedconvtranspose2d": 88, "convtranspose3d": 88, "quantizedconvtranspose3d": 88, "quantizeddropout": 88, "dropout2d": 88, "quantizeddropout2d": 88, "dropout3d": 88, "quantizeddropout3d": 88, "elu": 88, "quantizedelu": 88, "featurealphadropout": 88, "quantizedfeaturealphadropout": 88, "quantizedflatten": 88, "quantizedfold": 88, "fractionalmaxpool2d": 88, "quantizedfractionalmaxpool2d": 88, "fractionalmaxpool3d": 88, "quantizedfractionalmaxpool3d": 88, "gelu": 88, "quantizedgelu": 88, "glu": 88, "quantizedglu": 88, "groupnorm": 88, "quantizedgroupnorm": 88, "hardshrink": 88, "quantizedhardshrink": 88, "hardsigmoid": 88, "quantizedhardsigmoid": 88, "hardswish": 88, "quantizedhardswish": 88, "hardtanh": 88, "quantizedhardtanh": 88, "instancenorm1d": 88, "quantizedinstancenorm1d": 88, "instancenorm2d": 88, "quantizedinstancenorm2d": 88, "instancenorm3d": 88, "quantizedinstancenorm3d": 88, "lppool1d": 88, "quantizedlppool1d": 88, "lppool2d": 88, "quantizedlppool2d": 88, "quantizedlayernorm": 88, "leakyrelu": 88, "quantizedleakyrelu": 88, "localresponsenorm": 88, "quantizedlocalresponsenorm": 88, "logsigmoid": 88, "quantizedlogsigmoid": 88, "logsoftmax": 88, "quantizedlogsoftmax": 88, "maxpool1d": 88, "quantizedmaxpool1d": 88, "maxpool2d": 88, "quantizedmaxpool2d": 88, "maxpool3d": 88, "quantizedmaxpool3d": 88, "maxunpool1d": 88, "quantizedmaxunpool1d": 88, "maxunpool2d": 88, "quantizedmaxunpool2d": 88, "maxunpool3d": 88, "quantizedmaxunpool3d": 88, "mish": 88, "quantizedmish": 88, "quantizedprelu": 88, "pixelshuffl": 88, "quantizedpixelshuffl": 88, "pixelunshuffl": 88, "quantizedpixelunshuffl": 88, "rrelu": 88, "quantizedrrelu": 88, "quantizedrelu6": 88, "reflectionpad1d": 88, "quantizedreflectionpad1d": 88, "reflectionpad2d": 88, "quantizedreflectionpad2d": 88, "replicationpad1d": 88, "quantizedreplicationpad1d": 88, "replicationpad2d": 88, "quantizedreplicationpad2d": 88, "replicationpad3d": 88, "quantizedreplicationpad3d": 88, "selu": 88, "quantizedselu": 88, "silu": 88, "quantizedsilu": 88, "quantizedsigmoid": 88, "softmax2d": 88, "quantizedsoftmax2d": 88, "softmin": 88, "quantizedsoftmin": 88, "quantizedsoftplu": 88, "softshrink": 88, "quantizedsoftshrink": 88, "softsign": 88, "quantizedsoftsign": 88, "tanh": 88, "quantizedtanh": 88, "tanhshrink": 88, "quantizedtanhshrink": 88, "quantizedthreshold": 88, "unflatten": 88, "quantizedunflatten": 88, "unfold": 88, "quantizedunfold": 88, "upsampl": [88, 101], "quantizedupsampl": 88, "upsamplingbilinear2d": 88, "quantizedupsamplingbilinear2d": 88, "upsamplingnearest2d": 88, "quantizedupsamplingnearest2d": 88, "zeropad2d": 88, "quantizedzeropad2d": 88, "bceloss": 88, "quantizedbceloss": 88, "bcewithlogitsloss": 88, "quantizedbcewithlogitsloss": 88, "bilinear": [88, 101], "quantizedbilinear": 88, "ctcloss": 88, "quantizedctcloss": 88, "cosinesimilar": 88, "quantizedcosinesimilar": 88, "crossentropyloss": [88, 90], "quantizedcrossentropyloss": 88, "hingeembeddingloss": 88, "quantizedhingeembeddingloss": 88, "huberloss": 88, "quantizedhuberloss": 88, "kldivloss": 88, "quantizedkldivloss": 88, "l1loss": 88, "quantizedl1loss": 88, "mseloss": 88, "quantizedmseloss": 88, "multilabelmarginloss": 88, "quantizedmultilabelmarginloss": 88, "multilabelsoftmarginloss": 88, "quantizedmultilabelsoftmarginloss": 88, "multimarginloss": 88, "quantizedmultimarginloss": 88, "nllloss": 88, "quantizednllloss": 88, "nllloss2d": 88, "quantizednllloss2d": 88, "pairwisedist": 88, "quantizedpairwisedist": 88, "poissonnllloss": 88, "quantizedpoissonnllloss": 88, "smoothl1loss": 88, "quantizedsmoothl1loss": 88, "softmarginloss": 88, "quantizedsoftmarginloss": 88, "cosineembeddingloss": 88, "quantizedcosineembeddingloss": 88, "gaussiannllloss": 88, "quantizedgaussiannllloss": 88, "marginrankingloss": 88, "quantizedmarginrankingloss": 88, "tripletmarginloss": 88, "quantizedtripletmarginloss": 88, "tripletmarginwithdistanceloss": 88, "quantizedtripletmarginwithdistanceloss": 88, "quantizedembed": 88, "embeddingbag": 88, "quantizedembeddingbag": 88, "gru": [88, 109], "quantizedgru": 88, "rnn": [88, 109], "quantizedrnn": 88, "grucel": 88, "quantizedgrucel": 88, "rnncell": 88, "quantizedrnncel": 88, "lstm": [88, 109], "quantizedlstm": 88, "lstmcell": 88, "quantizedlstmcel": 88, "cumsum": 88, "quantizedcumsum": 88, "sin": 88, "quantizedsin": 88, "co": 88, "quantizedco": 88, "rsqrt": 88, "quantizedrsqrt": 88, "quantizedreshap": 88, "matmul": [88, 109], "quantizedmatmul": 88, "subtract": 88, "quantizedsubtract": 88, "quantizeddivid": 88, "bmm": 88, "quantizedbmm": 88, "baddbmm": 88, "quantizedbaddbmm": 88, "addmm": 88, "quantizedaddmm": 88, "concat": [88, 109], "quantizedconcat": 88, "allow_overwit": 89, "get_encod": 89, "get_legacy_encod": 89, "register_quantization_paramet": 89, "set_legacy_encod": 89, "tutori": 90, "meant": 90, "clearli": 90, "cifar10_train_data": 90, "fashionmnist": 90, "cifar10": 90, "cifar10_test_data": 90, "test_load": 90, "bn_1": 90, "bn_2": 90, "establish": 90, "send": 90, "batch_idx": 90, "zero_grad": 90, "fp_accuraci": 90, "91": 90, "70999908447266": 90, "coupl": 90, "care": [90, 100], "conform": 90, "incorrectli": 90, "thankfulli": 90, "fp_accuracy_prepar": 90, "2024": 90, "07": 90, "747": 90, "806": 90, "module_relu": 90, "module_relu_1": 90, "module_softmax": 90, "12544": 90, "getattr_1": 90, "getitem": 90, "graph_modul": 90, "print_read": 90, "passthrough": 90, "previous": 90, "theoret": 90, "idx": 90, "quantized_accuraci": 90, "1500015258789": 90, "advanc": 90, "post_qat_accuraci": 90, "92": 90, "05333709716797": 90, "happi": 90, "export_path": 90, "model_nam": 90, "fashion_mnist_model": 90, "sent": 90, "terminologi": 91, "abbrevi": 91, "bnf": 91, "hbf": 91, "often": [91, 92, 100, 105], "16x": 91, "caution": 91, "soon": 92, "prone": 92, "preprat": 92, "preceed": 93, "decreas": 93, "main": [93, 106, 109, 112], "oscil": 93, "cp": [94, 95, 97, 114], "magnitud": 94, "connect": [94, 99, 100, 113], "residu": 94, "regress": 94, "outlin": 95, "svd": [95, 96, 97, 99, 100, 109], "spatial": [95, 96, 97, 99, 100, 109], "accumul": [95, 100], "uncompress": 95, "latenc": 95, "bandwidth": 95, "websit": 95, "half": 95, "unknown": 95, "ssvd": 95, "f0": 95, "75": 95, "2b": 95, "revisit": 95, "close": [95, 108], "jupyt": 96, "familiar": 96, "teach": 96, "viewabl": 96, "metapackag": 96, "grant": 96, "admin": 96, "privileg": 96, "ip": 96, "browser": 96, "past": 96, "mkdir": 96, "cd": 96, "repositori": 96, "git": 96, "www": 96, "navig": 96, "launch": 96, "ipynb": 96, "assess": 97, "column": 97, "unmodifi": 97, "omit": [97, 106], "account": [97, 102, 105, 107], "drastic": 97, "redund": 98, "dilat": 99, "guidebook": 100, "greedi": [100, 111], "decompos": [100, 110, 113], "fc": [100, 113], "sharp": 100, "decai": 100, "slow": 100, "searcher": 100, "wors": 100, "strike": 100, "balanc": 100, "seem": [100, 102], "xiangyu": 100, "zhang": 100, "jianhua": 100, "zou": 100, "kaim": 100, "he": 100, "jian": 100, "sun": 100, "deep": 100, "transact": 100, "pattern": 100, "intellig": 100, "vol": 100, "pp": 100, "1943": 100, "1955": 100, "oct": 100, "2016": 100, "yihui": 100, "confer": [100, 103], "vision": [100, 103], "venic": 100, "2017": 100, "1398": 100, "1406": 100, "jaderberg": 100, "andrea": 100, "vedaldi": 100, "andrew": 100, "zisserman": 100, "british": 100, "jan": 100, "2014": 100, "andrei": 100, "kuzmin": 100, "marku": [100, 103], "nagel": [100, 103], "saurabh": 100, "pitr": 100, "sandeep": 100, "pendyam": 100, "tijmen": [100, 103], "blankevoort": [100, 103], "taxonomi": 100, "primit": 101, "sure": 101, "slice": 101, "align_corn": 101, "deconvolut": 101, "dconvolut": 101, "deeplabv3": 101, "address": [101, 107, 111], "briefli": 102, "suffici": [102, 104, 105, 108], "fast": 102, "easi": 102, "robust": 102, "_aimet": 102, "prep": 102, "complainc": 102, "align": 102, "retri": 102, "ref": 102, "satisfactori": [102, 107], "onto": 102, "pb": 102, "trial": [102, 107], "diagnost": 102, "becom": 103, "paper": 103, "surround": 103, "big": 103, "discrep": 103, "wide": 103, "significantli": 103, "quantizaion": 103, "analyt": [103, 111], "bottleneck": [103, 107], "hybrid": 103, "approach": [103, 108], "mart": 103, "van": 103, "baalen": 103, "seoul": 103, "octob": 103, "area": 104, "situat": 104, "pinpoint": 104, "culprit": 104, "squar": [104, 108], "monitor": 104, "contribut": [104, 107], "read": 104, "presenc": 105, "hyperparamet": 105, "converg": 105, "six": 106, "turn": 106, "empti": 106, "outsid": 106, "strict": [106, 108], "unsign": [106, 108], "throughout": [106, 112], "convent": 106, "member": 106, "insight": [107, 111, 112], "underperform": 107, "chart": 107, "confid": 107, "toward": 107, "uneven": 107, "global": 107, "inner": 107, "bert": 107, "reveal": 107, "resort": 107, "revert": 107, "mitig": 108, "ingest": 108, "000": 108, "de": 108, "hook": 108, "intercept": 108, "four": 108, "textrm": 108, "dfrac": 108, "elimin": 108, "induc": 108, "signal": 108, "satur": 108, "erro": 108, "alongsid": 108, "settabl": 108, "slim": 109, "backslash": 109, "io": 109, "user_guid": 109, "api_doc": 109, "quantizablemultiheadattent": 109, "kyuykim": 109, "mangal": 109, "geunle": 109, "correctli": 109, "klhsieh": 109, "akhobar": 109, "ashvkuma": 109, "fp16": 109, "stand": 109, "adaptiveround": 109, "recurr": 109, "\ud835\udc5a": [110, 113], "\ud835\udc5b": [110, 113], "\u210e": [110, 113], "\ud835\udc64": [110, 113], "\ud835\udc58": [110, 113], "degre": [110, 113], "augment": 111, "progress": [111, 112], "computation": [111, 112], "arrang": 111, "websocket": 111, "listen": 111, "5006": 111, "lot": 112, "term": 113, "lose": 114, "volum": 114, "hxwx8": 114, "hxwx5": 114, "propag": 114, "green": 114, "side": 114, "pink": 114, "color": 114, "orang": 114}, "objects": {"aimet_common.bias_correction": [[55, 0, 1, "", "ConvBnInfoType"]], "aimet_common.defs": [[55, 0, 1, "", "ActivationType"], [59, 0, 1, "", "CallbackFunc"], [30, 0, 1, "", "CompressionScheme"], [30, 0, 1, "", "CostMetric"], [56, 0, 1, "", "GreedySelectionParameters"], [68, 0, 1, "", "QuantScheme"]], "aimet_common.defs.ActivationType": [[55, 1, 1, "", "no_activation"], [55, 1, 1, "", "relu"], [55, 1, 1, "", "relu6"]], "aimet_common.defs.CompressionScheme": [[30, 1, 1, "", "channel_pruning"], [30, 1, 1, "", "spatial_svd"], [30, 1, 1, "", "weight_svd"]], "aimet_common.defs.CostMetric": [[30, 1, 1, "", "mac"], [30, 1, 1, "", "memory"]], "aimet_common.defs.QuantScheme": [[68, 1, 1, "", "post_training_percentile"], [68, 1, 1, "", "post_training_tf"], [68, 1, 1, "", "post_training_tf_enhanced"], [68, 1, 1, "", "training_range_learning_with_tf_enhanced_init"], [68, 1, 1, "", "training_range_learning_with_tf_init"]], "aimet_common.utils": [[66, 0, 1, "", "CallbackFunc"]], "aimet_onnx.adaround.adaround_weight.Adaround": [[41, 2, 1, "", "apply_adaround"]], "aimet_onnx.adaround.adaround_weight": [[41, 0, 1, "", "AdaroundParameters"]], "aimet_onnx.amp.mixed_precision_algo": [[45, 0, 1, "", "EvalCallbackFactory"]], "aimet_onnx.amp.mixed_precision_algo.EvalCallbackFactory": [[45, 3, 1, "", "sqnr"]], "aimet_onnx.amp.quantizer_groups": [[45, 0, 1, "", "QuantizerGroup"]], "aimet_onnx.amp.quantizer_groups.QuantizerGroup": [[45, 3, 1, "", "get_activation_quantizers"], [45, 3, 1, "", "get_active_quantizers"], [45, 3, 1, "", "get_candidate"], [45, 3, 1, "", "get_param_quantizers"], [45, 3, 1, "", "set_quantizers_to_candidate"], [45, 3, 1, "", "to_list"]], "aimet_onnx.auto_quant_v2": [[42, 0, 1, "", "AutoQuant"]], "aimet_onnx.auto_quant_v2.AutoQuant": [[42, 3, 1, "", "get_quant_scheme_candidates"], [42, 3, 1, "", "optimize"], [42, 3, 1, "", "run_inference"], [42, 3, 1, "", "set_adaround_params"], [42, 3, 1, "", "set_quant_scheme_candidates"]], "aimet_onnx.cross_layer_equalization": [[43, 2, 1, "", "equalize_model"]], "aimet_onnx.layer_output_utils": [[44, 0, 1, "", "LayerOutputUtil"]], "aimet_onnx.layer_output_utils.LayerOutputUtil": [[44, 3, 1, "", "generate_layer_outputs"]], "aimet_onnx.mixed_precision": [[45, 2, 1, "", "choose_mixed_precision"]], "aimet_onnx.quant_analyzer": [[46, 0, 1, "", "QuantAnalyzer"]], "aimet_onnx.quant_analyzer.QuantAnalyzer": [[46, 3, 1, "", "analyze"], [46, 3, 1, "", "check_model_sensitivity_to_quantization"], [46, 3, 1, "", "create_quantsim_and_encodings"], [46, 3, 1, "", "enable_per_layer_mse_loss"], [46, 3, 1, "", "export_per_layer_encoding_min_max_range"], [46, 3, 1, "", "export_per_layer_mse_loss"], [46, 3, 1, "", "export_per_layer_stats_histogram"], [46, 3, 1, "", "perform_per_layer_analysis_by_disabling_quantizers"], [46, 3, 1, "", "perform_per_layer_analysis_by_enabling_quantizers"]], "aimet_onnx.quantsim": [[48, 0, 1, "", "QuantizationSimModel"]], "aimet_onnx.quantsim.QuantizationSimModel": [[48, 3, 1, "", "compute_encodings"], [48, 3, 1, "", "export"]], "aimet_tensorflow.keras.adaround_weight.Adaround": [[28, 2, 1, "", "apply_adaround"]], "aimet_tensorflow.keras.adaround_weight": [[28, 0, 1, "", "AdaroundParameters"]], "aimet_tensorflow.keras.batch_norm_fold": [[36, 2, 1, "", "fold_all_batch_norms"], [29, 2, 1, "", "fold_all_batch_norms_to_scale"], [36, 2, 1, "", "fold_given_batch_norms"]], "aimet_tensorflow.keras.bn_reestimation": [[29, 2, 1, "", "reestimate_bn_stats"]], "aimet_tensorflow.keras.compress": [[30, 0, 1, "", "ModelCompressor"]], "aimet_tensorflow.keras.compress.ModelCompressor": [[30, 3, 1, "", "compress_model"]], "aimet_tensorflow.keras.cross_layer_equalization": [[36, 0, 1, "", "ClsSetInfo"], [31, 2, 1, "", "equalize_model"]], "aimet_tensorflow.keras.cross_layer_equalization.ClsSetInfo": [[36, 0, 1, "", "ClsSetLayerPairInfo"]], "aimet_tensorflow.keras.cross_layer_equalization.CrossLayerScaling": [[36, 2, 1, "", "scale_cls_sets"], [36, 2, 1, "", "scale_model"]], "aimet_tensorflow.keras.cross_layer_equalization.HighBiasFold": [[36, 2, 1, "id0", "bias_fold"]], "aimet_tensorflow.keras.defs": [[30, 0, 1, "", "ModuleCompRatioPair"], [30, 0, 1, "", "SpatialSvdParameters"]], "aimet_tensorflow.keras.defs.SpatialSvdParameters": [[30, 0, 1, "", "AutoModeParams"], [30, 0, 1, "", "ManualModeParams"], [30, 0, 1, "", "Mode"]], "aimet_tensorflow.keras.defs.SpatialSvdParameters.Mode": [[30, 1, 1, "", "auto"], [30, 1, 1, "", "manual"]], "aimet_tensorflow.keras.layer_output_utils": [[32, 0, 1, "", "LayerOutputUtil"]], "aimet_tensorflow.keras.layer_output_utils.LayerOutputUtil": [[32, 3, 1, "", "generate_layer_outputs"]], "aimet_tensorflow.keras.mixed_precision": [[33, 2, 1, "", "choose_fast_mixed_precision"], [33, 2, 1, "", "choose_mixed_precision"]], "aimet_tensorflow.keras.model_preparer": [[35, 2, 1, "", "prepare_model"]], "aimet_tensorflow.keras.quant_analyzer": [[37, 0, 1, "", "QuantAnalyzer"]], "aimet_tensorflow.keras.quant_analyzer.QuantAnalyzer": [[37, 3, 1, "", "analyze"]], "aimet_tensorflow.keras.quantsim": [[39, 0, 1, "", "QuantizationSimModel"]], "aimet_tensorflow.keras.quantsim.QuantizationSimModel": [[39, 3, 1, "", "compute_encodings"], [39, 3, 1, "", "export"]], "aimet_torch.amp.mixed_precision_algo": [[59, 0, 1, "", "EvalCallbackFactory"]], "aimet_torch.amp.mixed_precision_algo.EvalCallbackFactory": [[59, 3, 1, "", "sqnr"]], "aimet_torch.amp.quantizer_groups": [[59, 0, 1, "", "QuantizerGroup"]], "aimet_torch.amp.quantizer_groups.QuantizerGroup": [[59, 3, 1, "", "get_active_quantizers"], [59, 3, 1, "", "get_candidate"], [59, 3, 1, "", "get_input_quantizer_modules"], [59, 3, 1, "", "set_quantizers_to_candidate"], [59, 3, 1, "", "to_list"]], "aimet_torch.arch_checker.arch_checker.ArchChecker": [[52, 2, 1, "", "check_model_arch"]], "aimet_torch.batch_norm_fold": [[65, 2, 1, "", "fold_all_batch_norms"], [54, 2, 1, "", "fold_all_batch_norms_to_scale"], [65, 2, 1, "", "fold_given_batch_norms"]], "aimet_torch.bias_correction": [[55, 2, 1, "", "correct_bias"]], "aimet_torch.bn_reestimation": [[54, 2, 1, "", "reestimate_bn_stats"]], "aimet_torch.compress": [[56, 0, 1, "", "ModelCompressor"]], "aimet_torch.compress.ModelCompressor": [[56, 3, 1, "", "compress_model"]], "aimet_torch.cross_layer_equalization": [[65, 0, 1, "", "ClsSetInfo"], [57, 2, 1, "", "equalize_model"]], "aimet_torch.cross_layer_equalization.ClsSetInfo": [[65, 0, 1, "", "ClsSetLayerPairInfo"]], "aimet_torch.cross_layer_equalization.CrossLayerScaling": [[65, 2, 1, "", "scale_cls_sets"], [65, 2, 1, "", "scale_model"]], "aimet_torch.cross_layer_equalization.HighBiasFold": [[65, 2, 1, "id0", "bias_fold"]], "aimet_torch.defs": [[56, 0, 1, "", "ChannelPruningParameters"], [56, 0, 1, "", "ModuleCompRatioPair"], [56, 0, 1, "", "SpatialSvdParameters"], [56, 0, 1, "", "WeightSvdParameters"]], "aimet_torch.defs.ChannelPruningParameters": [[56, 0, 1, "", "AutoModeParams"], [56, 0, 1, "", "ManualModeParams"], [56, 0, 1, "", "Mode"]], "aimet_torch.defs.ChannelPruningParameters.Mode": [[56, 1, 1, "", "auto"], [56, 1, 1, "", "manual"]], "aimet_torch.defs.SpatialSvdParameters": [[56, 0, 1, "", "AutoModeParams"], [56, 0, 1, "", "ManualModeParams"], [56, 0, 1, "", "Mode"]], "aimet_torch.defs.SpatialSvdParameters.Mode": [[56, 1, 1, "", "auto"], [56, 1, 1, "", "manual"]], "aimet_torch.defs.WeightSvdParameters": [[56, 0, 1, "", "AutoModeParams"], [56, 0, 1, "", "ManualModeParams"], [56, 0, 1, "", "Mode"]], "aimet_torch.defs.WeightSvdParameters.Mode": [[56, 1, 1, "", "auto"], [56, 1, 1, "", "manual"]], "aimet_torch.gptvq.defs": [[86, 0, 1, "", "GPTVQParameters"]], "aimet_torch.gptvq.gptvq_weight.GPTVQ": [[86, 2, 1, "", "apply_gptvq"]], "aimet_torch.layer_output_utils": [[58, 0, 1, "", "LayerOutputUtil"], [58, 0, 1, "", "NamingScheme"]], "aimet_torch.layer_output_utils.LayerOutputUtil": [[58, 3, 1, "", "generate_layer_outputs"]], "aimet_torch.layer_output_utils.NamingScheme": [[58, 1, 1, "", "ONNX"], [58, 1, 1, "", "PYTORCH"], [58, 1, 1, "", "TORCHSCRIPT"]], "aimet_torch.mixed_precision": [[59, 2, 1, "", "choose_mixed_precision"]], "aimet_torch.model_preparer": [[61, 2, 1, "", "prepare_model"]], "aimet_torch.nn.modules.custom": [[69, 0, 1, "", "ScatterDense"], [69, 0, 1, "", "SparseTensorWrapper"]], "aimet_torch.peft": [[64, 0, 1, "", "AdapterMetaData"], [64, 0, 1, "", "PeftQuantUtils"], [64, 3, 1, "", "replace_lora_layers_with_quantizable_layers"], [64, 3, 1, "", "track_lora_meta_data"]], "aimet_torch.peft.PeftQuantUtils": [[64, 3, 1, "", "disable_lora_adapters"], [64, 3, 1, "", "enable_adapter_and_load_weights"], [64, 3, 1, "", "export_adapter_weights"], [64, 3, 1, "", "freeze_base_model"], [64, 3, 1, "", "freeze_base_model_activation_quantizers"], [64, 3, 1, "", "freeze_base_model_param_quantizers"], [64, 3, 1, "", "get_fp_lora_layer"], [64, 3, 1, "", "get_quantized_lora_layer"], [64, 3, 1, "", "quantize_lora_scale_with_fixed_range"], [64, 3, 1, "", "set_bitwidth_for_lora_adapters"]], "aimet_torch.v1.adaround.adaround_weight.Adaround": [[51, 2, 1, "", "apply_adaround"]], "aimet_torch.v1.adaround.adaround_weight": [[51, 0, 1, "", "AdaroundParameters"]], "aimet_torch.v1.auto_quant": [[53, 0, 1, "", "AutoQuant"]], "aimet_torch.v1.quant_analyzer": [[66, 0, 1, "", "QuantAnalyzer"]], "aimet_torch.v1.quant_analyzer.QuantAnalyzer": [[66, 3, 1, "", "analyze"], [66, 3, 1, "", "check_model_sensitivity_to_quantization"], [66, 3, 1, "", "enable_per_layer_mse_loss"], [66, 3, 1, "", "export_per_layer_encoding_min_max_range"], [66, 3, 1, "", "export_per_layer_mse_loss"], [66, 3, 1, "", "export_per_layer_stats_histogram"], [66, 3, 1, "", "perform_per_layer_analysis_by_disabling_quant_wrappers"], [66, 3, 1, "", "perform_per_layer_analysis_by_enabling_quant_wrappers"]], "aimet_torch.v1.quantsim": [[55, 0, 1, "", "QuantParams"], [68, 0, 1, "", "QuantizationSimModel"], [68, 3, 1, "", "load_checkpoint"], [68, 3, 1, "", "save_checkpoint"]], "aimet_torch.v1.quantsim.QuantizationSimModel": [[68, 3, 1, "", "compute_encodings"], [68, 3, 1, "", "export"]], "aimet_torch.v2.nn": [[88, 0, 1, "", "QuantizationMixin"]], "aimet_torch.v2.nn.QuantizationMixin": [[88, 3, 1, "", "__quant_init__"], [88, 3, 1, "", "compute_encodings"], [88, 3, 1, "", "forward"], [77, 3, 1, "", "from_module"], [77, 3, 1, "", "get_default_kernel"], [77, 3, 1, "", "get_kernel"], [77, 3, 1, "", "implements"], [88, 1, 1, "", "input_quantizers"], [88, 1, 1, "", "output_quantizers"], [88, 1, 1, "", "param_quantizers"], [77, 3, 1, "", "set_default_kernel"], [77, 3, 1, "", "set_kernel"]], "aimet_torch.v2.quantization": [[78, 4, 0, "-", "affine"], [80, 4, 0, "-", "float"]], "aimet_torch.v2.quantization.affine": [[78, 0, 1, "", "Quantize"], [78, 0, 1, "", "QuantizeDequantize"], [78, 2, 1, "", "dequantize"], [78, 2, 1, "", "quantize"], [78, 2, 1, "", "quantize_dequantize"]], "aimet_torch.v2.quantization.affine.quantizer": [[89, 0, 1, "", "Quantize"], [89, 0, 1, "", "QuantizeDequantize"], [89, 0, 1, "", "QuantizerBase"]], "aimet_torch.v2.quantization.affine.quantizer.Quantize": [[89, 3, 1, "", "forward"]], "aimet_torch.v2.quantization.affine.quantizer.QuantizeDequantize": [[89, 3, 1, "", "forward"]], "aimet_torch.v2.quantization.affine.quantizer.QuantizerBase": [[89, 3, 1, "", "allow_overwrite"], [89, 3, 1, "", "compute_encodings"], [89, 3, 1, "", "get_encoding"], [89, 3, 1, "", "get_legacy_encodings"], [89, 3, 1, "", "is_initialized"], [89, 3, 1, "", "register_quantization_parameter"], [89, 3, 1, "", "set_legacy_encodings"]], "aimet_torch.v2.quantization.encoding_analyzer": [[84, 0, 1, "", "EncodingAnalyzer"], [84, 0, 1, "", "MinMaxEncodingAnalyzer"], [84, 0, 1, "", "PercentileEncodingAnalyzer"], [84, 0, 1, "", "SqnrEncodingAnalyzer"]], "aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer": [[84, 3, 1, "", "compute_encodings"], [84, 3, 1, "", "reset_stats"], [84, 3, 1, "", "update_stats"]], "aimet_torch.v2.quantization.float": [[80, 0, 1, "", "FloatQuantizeDequantize"], [80, 0, 1, "", "QuantizeDequantize"]], "aimet_torch.v2.quantization.tensor": [[81, 0, 1, "", "DequantizedTensor"], [81, 0, 1, "", "QuantizedTensor"]], "aimet_torch.v2.quantization.tensor.DequantizedTensor": [[81, 3, 1, "", "dequantize"], [81, 3, 1, "", "quantize"], [81, 3, 1, "", "quantized_repr"]], "aimet_torch.v2.quantization.tensor.QuantizedTensor": [[81, 3, 1, "", "dequantize"], [81, 3, 1, "", "quantize"], [81, 3, 1, "", "quantized_repr"]], "aimet_torch.v2.quantsim.config_utils": [[83, 2, 1, "", "set_activation_quantizers_to_float"], [83, 2, 1, "", "set_blockwise_quantization_for_weights"], [83, 2, 1, "", "set_grouped_blockwise_quantization_for_weights"]], "aimet_torch.v2.visualization_tools": [[82, 2, 1, "", "visualize_stats"]], "aimet_torch.visualize_model": [[71, 2, 1, "", "visualize_changes_after_optimization"], [71, 2, 1, "", "visualize_relative_weight_ranges_to_identify_problematic_layers"], [71, 2, 1, "", "visualize_weight_ranges"]], "aimet_torch.visualize_serialized_data": [[70, 0, 1, "", "VisualizeCompression"]], "aimet_torch.visualize_serialized_data.VisualizeCompression": [[70, 3, 1, "", "display_comp_ratio_plot"], [70, 3, 1, "", "display_eval_scores"]]}, "objtypes": {"0": "py:class", "1": "py:attribute", "2": "py:function", "3": "py:method", "4": "py:module"}, "objnames": {"0": ["py", "class", "Python class"], "1": ["py", "attribute", "Python attribute"], "2": ["py", "function", "Python function"], "3": ["py", "method", "Python method"], "4": ["py", "module", "Python module"]}, "titleterms": {"automat": [0, 4, 18], "mix": [0, 4, 18, 33, 45, 59], "precis": [0, 4, 18, 33, 45, 59], "amp": [0, 4, 18, 33], "overal": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 90], "flow": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 64, 90, 103], "what": [0, 4, 12, 13, 18, 21, 25, 67], "thi": [0, 4, 12, 13, 18, 21, 25], "notebook": [0, 4, 12, 13, 18, 21, 25, 28, 29, 31, 51, 53, 54, 57, 66, 68, 96], "i": [0, 4, 12, 13, 18, 21, 25], "dataset": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25], "1": [0, 1, 2, 3, 4, 5, 6, 7, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 49, 55, 75, 90, 96, 109], "exampl": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 28, 29, 30, 31, 32, 33, 35, 36, 37, 39, 41, 42, 43, 44, 45, 46, 48, 49, 51, 53, 54, 55, 56, 57, 58, 59, 61, 65, 66, 68, 69, 70, 71, 72, 86, 87, 96], "evalu": [0, 1, 2, 3, 4, 5, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25], "pipelin": [0, 1, 2, 3, 5, 6, 7, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25], "2": [0, 1, 2, 3, 4, 5, 6, 7, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 33, 49, 55, 75, 90, 96, 109], "convert": [0, 1, 2, 3, 9], "an": [0, 1, 2, 3], "fp32": [0, 1, 2, 3, 4, 5, 6, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24], "pytorch": [0, 1, 2, 3, 49, 50, 51, 53, 54, 55, 56, 57, 58, 59, 60, 63, 65, 66, 67, 68, 75, 87, 90, 101, 102, 112], "model": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 34, 35, 60, 61, 62, 87, 90, 98, 100, 101, 102], "onnx": [0, 1, 2, 3, 40, 41, 42, 43, 44, 45, 46, 47, 48, 69, 75], "simplifi": [0, 1, 2, 3], "baselin": [0, 1, 2, 3, 4, 5, 6, 10, 11, 13, 14, 15, 16, 17, 18, 19, 22, 23, 24], "accuraci": [0, 1, 2, 3, 4, 5, 6, 10, 11, 13, 14, 15, 16, 17, 18, 19, 22, 23, 24], "3": [0, 1, 2, 3, 4, 5, 6, 7, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 49, 96], "creat": [0, 1, 2, 3, 4, 5, 7, 9, 10, 11, 13, 14, 18, 19, 21, 22, 23, 24], "quantiz": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 18, 19, 21, 22, 23, 24, 25, 33, 38, 39, 45, 47, 48, 55, 59, 67, 68, 71, 72, 78, 80, 81, 83, 85, 88, 89, 90, 102, 103, 105, 106, 107, 108, 112], "simul": [0, 1, 2, 3, 4, 5, 10, 11, 13, 14, 18, 19, 21, 22, 23, 24, 106, 108], "fold": [0, 1, 2, 3, 5, 7, 10, 11, 13, 14, 18, 19, 21, 22, 23, 24, 90], "batch": [0, 1, 2, 3, 5, 10, 11, 13, 14, 18, 19, 22, 23, 24, 93], "normal": [0, 1, 3, 5, 10, 11, 13, 14, 18, 19, 23, 24], "layer": [0, 1, 2, 3, 5, 7, 9, 10, 11, 12, 13, 14, 18, 19, 21, 22, 23, 24, 25, 31, 32, 36, 43, 44, 57, 58, 65, 97, 100, 103], "sim": [0, 1, 2, 3, 5, 10, 11, 14, 18, 19, 21, 22, 23, 24, 39, 48, 68], "comput": [0, 4, 18, 88], "encod": [0, 4, 12, 18, 25, 49, 84, 88, 108], "4": [0, 1, 2, 4, 5, 6, 7, 9, 10, 11, 13, 14, 18, 19, 21, 22, 23, 24, 49], "run": [0, 4, 18, 20, 46, 66, 96], "algorithm": [0, 4, 18], "defin": [0, 6, 7, 18, 20], "callback": [0, 7, 18], "function": [0, 6, 7, 9, 18, 20, 78], "paramet": [0, 4, 18, 28, 30, 41, 51, 56, 86, 91, 108], "call": [0, 4, 18], "api": [0, 4, 18, 26, 27, 28, 29, 30, 31, 32, 33, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 61, 64, 65, 66, 67, 68, 69, 70, 71, 83, 86, 87, 88, 89, 91, 92, 93, 103, 104, 108], "adapt": [1, 5, 19, 41, 51], "round": [1, 5, 19, 41, 51, 100], "adaround": [1, 5, 13, 19, 28, 41, 51, 91], "instanti": [1, 2, 3, 4, 5, 6, 7, 10, 11, 14, 15, 16, 17, 19, 22, 23, 24], "train": [1, 2, 3, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 19, 21, 22, 23, 24, 25, 68, 85, 90, 102, 103, 105], "valid": [1, 2, 3, 5, 6, 14, 15, 16, 17, 19, 22, 23, 24, 62], "determin": [1, 2, 3, 5, 6, 10, 11, 13, 14, 19, 22, 23, 24, 108], "appli": [1, 2, 5, 6, 12, 13, 14, 19, 22, 25], "next": [1, 5, 10, 11, 14, 15, 16, 17, 19, 20, 22, 23, 24], "step": [1, 5, 10, 11, 14, 15, 16, 17, 19, 20, 22, 23, 24, 75], "For": [1, 2, 3, 5, 6, 10, 11, 14, 15, 16, 17, 19, 20, 22, 23, 24], "more": [1, 2, 3, 5, 6, 10, 11, 14, 15, 16, 17, 19, 20, 22, 23, 24, 98], "inform": [1, 2, 3, 5, 6, 10, 11, 14, 15, 16, 17, 19, 20, 22, 23, 24, 98], "cross": [2, 14, 22, 31, 36, 43, 57, 65, 103], "equal": [2, 14, 22, 31, 36, 43, 57, 65, 103], "norm": [2, 22, 93], "cle": [2, 14, 22, 36], "method": [4, 36], "load": [4, 5, 6, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25], "find": 4, "fake": 4, "op": 4, "insert": 4, "regular": [4, 33], "fast": [4, 33], "0": [4, 33, 49, 109], "summari": [4, 7, 9, 13, 21], "get": [5, 10, 11, 13, 14, 15, 16, 17, 18, 19, 22, 23, 24, 87], "score": [5, 10, 11, 13, 14, 15, 16, 17, 18, 19, 22, 23, 24], "autoqu": [6, 20, 42, 53, 92], "pretrain": [6, 12, 20], "constant": [6, 7, 20], "helper": [6, 20, 36], "5": [6, 7, 21, 49], "awar": [7, 8, 10, 11, 21, 23, 24, 68, 90, 105], "batchnorm": [7, 21, 29, 54, 90], "re": [7, 21, 29, 54, 93], "estim": [7, 21, 29, 54, 93], "prepar": [7, 9, 35, 61, 90], "kera": [7, 8, 9], "quantizationsim": 7, "perform": [7, 10, 11, 21, 23, 24, 36], "qat": [7, 10, 11, 21, 23, 24, 68, 105], "export": [7, 21, 69, 83, 90], "transform": 8, "subclass": 9, "show": 9, "similar": 9, "differ": 9, "between": 9, "origin": 9, "discuss": 9, "limit": [9, 29, 35, 61], "rang": [11, 12, 24, 25], "learn": [11, 24], "quant": [12, 25, 37, 46, 66], "analyz": [12, 25, 37, 46, 66, 84], "quantanalyz": [12, 25, 104], "per": [12, 13, 25, 97, 100], "analysi": [12, 25, 102, 104], "enabl": [12, 25], "disabl": [12, 25], "wrapper": [12, 25], "min": [12, 25], "max": [12, 25], "pdf": [12, 25], "statist": [12, 21, 25], "mse": [12, 25], "loss": [12, 25], "quantsim": [13, 14, 90, 108], "channel": [13, 15, 17, 56, 94], "pcq": 13, "compress": [15, 16, 17, 30, 56, 70, 95, 97, 100, 111], "us": [15, 16, 17, 36, 74, 91, 100, 102], "prune": [15, 17, 56, 94], "fine": [15, 16, 17, 90, 100], "tune": [15, 16, 17, 90, 100], "spatial": [16, 17, 30, 56, 110], "svd": [16, 17, 30, 56, 110, 113], "reestim": [21, 54], "bia": [22, 55], "correct": [22, 55], "techniqu": [22, 100, 103], "bc": 22, "welcom": 26, "ai": [26, 87, 98], "effici": [26, 87, 98], "toolkit": [26, 87, 98], "doc": 26, "indic": 26, "tabl": 26, "aimet": [27, 28, 29, 30, 31, 32, 33, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 50, 51, 53, 54, 55, 56, 57, 58, 59, 65, 66, 67, 68, 69, 70, 71, 73, 74, 75, 87, 91, 92, 93, 94, 95, 96, 97, 99, 100, 102, 103, 104, 105, 107, 108, 109, 110, 111, 112, 113, 114], "tensorflow": [27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 49, 75, 112], "user": [28, 31, 39, 41, 42, 43, 51, 53, 55, 57, 64, 66, 68, 98, 103], "guid": [28, 31, 39, 41, 42, 43, 51, 53, 55, 57, 66, 68, 90, 98], "link": [28, 29, 31, 39, 41, 42, 43, 51, 53, 54, 55, 57, 66, 68], "top": [28, 29, 30, 32, 33, 35, 37, 39, 41, 42, 44, 45, 46, 48, 51, 53, 54, 56, 58, 59, 61, 64, 66, 68, 70, 71, 83, 86, 88, 89], "level": [28, 29, 30, 32, 33, 35, 36, 37, 39, 41, 42, 44, 45, 46, 48, 51, 53, 54, 56, 58, 59, 61, 64, 65, 66, 68, 70, 71, 83, 86, 88, 89], "enum": [28, 51, 58, 68], "definit": [28, 30, 33, 45, 51, 56, 58, 59, 65, 68], "code": [28, 29, 30, 31, 32, 33, 35, 36, 37, 39, 41, 42, 43, 44, 45, 46, 48, 51, 53, 54, 55, 56, 57, 58, 59, 61, 65, 66, 68, 69, 70, 71, 72, 86, 96], "introduct": [29, 30, 31, 36, 43, 54, 56, 57, 65], "greedi": [30, 56, 97], "select": [30, 56, 94, 97, 100], "configur": [30, 56, 88, 106, 108], "primit": [31, 36, 57, 65], "output": [32, 44, 58], "gener": [32, 44, 58], "group": [33, 45, 59], "callbackfunc": [33, 45, 59], "guidelin": [34, 60, 68, 91, 101], "higher": [36, 65], "lower": [36, 65], "custom": [36, 69], "datatyp": 36, "manual": 36, "mode": [36, 105], "specif": [46, 49, 66], "util": [46, 62, 66], "format": 49, "version": 49, "up": 49, "file": [49, 106], "6": 49, "architectur": 52, "checker": 52, "html": 52, "report": 52, "content": 52, "bn": [54, 93], "convbninfotyp": 55, "activationtyp": 55, "param": 55, "empir": 55, "analyt": 55, "weight": [56, 94, 113], "torch": [61, 69, 75], "fx": 61, "symbol": 61, "trace": 61, "multi": 63, "gpu": [63, 75], "support": 63, "peft": 64, "lora": 64, "clssetinfo": 65, "aimet_torch": [67, 72], "refer": [67, 100, 103], "v2": [67, 72], "": 67, "new": 67, "backward": 67, "compat": 67, "sparseconvolut": 69, "spconv": 69, "modul": [69, 72, 88], "visual": [70, 71, 82, 111, 112], "migrat": 72, "chang": 72, "process": 72, "import": 72, "quantizationsimmodel": 72, "move": 72, "from": [72, 74, 75], "quantwrapp": 72, "staticgrid": 72, "learnedgrid": 72, "affin": [72, 78], "float": [72, 80, 90], "instal": [73, 74, 75], "quick": 73, "releas": [73, 74, 75, 98, 109], "packag": [73, 74, 75], "system": 73, "requir": [73, 104], "advanc": 73, "instruct": 73, "docker": 74, "set": 74, "variant": [74, 84], "prebuilt": 74, "imag": 74, "build": 74, "local": 74, "start": [74, 87, 111], "contain": 74, "pypi": [74, 75], "environ": [74, 75], "setup": [74, 75], "prerequisit": [75, 90], "13": [75, 109], "common": 75, "debian": 75, "replac": 75, "pillow": 75, "simd": 75, "onnxruntim": 75, "post": [75, 85, 102, 103], "quantizationmixin": 77, "class": [78, 80, 81, 88], "floatquantizedequant": 79, "quantizedequant": 79, "tensor": 81, "tool": [82, 102], "blockwis": 83, "low": 83, "power": 83, "lpbq": 83, "gptvq": 86, "document": 87, "featur": [87, 95, 98, 102], "descript": [87, 104], "quickstart": 90, "point": 90, "case": [91, 100, 102], "hyper": 91, "overview": [92, 93, 97, 98, 100, 103, 104, 105, 106, 108, 111, 112, 114], "workflow": [92, 93, 102, 105, 108], "procedur": 94, "winnow": [94, 114], "reconstruct": 94, "guidebook": 95, "brows": 96, "server": [96, 111], "download": 96, "relat": 96, "ratio": [97, 100, 111], "how": [97, 114], "work": [97, 114], "explor": 97, "toc": 98, "tree": 98, "known": 99, "issu": 99, "option": 100, "rank": 100, "note": [100, 109], "faq": [100, 103], "debug": 102, "detail": 104, "recommend": 105, "structur": 106, "modifi": 106, "section": 106, "diagnost": 107, "nois": 108, "scheme": 108, "oper": 108, "22": 109, "21": 109, "20": 109, "19": 109, "py37": 109, "18": 109, "17": 109, "16": 109, "14": 109, "design": 111, "bokeh": 111, "session": 111}, "envversion": {"sphinx.domains.c": 2, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 8, "sphinx.domains.index": 1, "sphinx.domains.javascript": 2, "sphinx.domains.math": 2, "sphinx.domains.python": 3, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "nbsphinx": 4, "sphinx.ext.intersphinx": 1, "sphinx.ext.viewcode": 1, "sphinx": 57}, "alltitles": {"Automatic Mixed-Precision (AMP)": [[0, "Automatic-Mixed-Precision-(AMP)"], [4, "Automatic-Mixed-Precision-(AMP)"], [18, "Automatic-Mixed-Precision-(AMP)"]], "Overall flow": [[0, "Overall-flow"], [1, "Overall-flow"], [2, "Overall-flow"], [3, "Overall-flow"], [4, "Overall-flow"], [5, "Overall-flow"], [6, "Overall-flow"], [7, "Overall-flow"], [8, "Overall-flow"], [9, "Overall-flow"], [10, "Overall-flow"], [11, "Overall-flow"], [12, "Overall-flow"], [13, "Overall-flow"], [14, "Overall-flow"], [15, "Overall-flow"], [16, "Overall-flow"], [17, "Overall-flow"], [18, "Overall-flow"], [19, "Overall-flow"], [20, "Overall-flow"], [21, "Overall-flow"], [22, "Overall-flow"], [23, "Overall-flow"], [24, "Overall-flow"], [25, "Overall-flow"], [90, "overall-flow"]], "What this notebook is not": [[0, "What-this-notebook-is-not"], [4, "What-this-notebook-is-not"], [12, "What-this-notebook-is-not"], [13, "What-this-notebook-is-not"], [18, "What-this-notebook-is-not"], [21, "What-this-notebook-is-not"], [25, "What-this-notebook-is-not"]], "Dataset": [[0, "Dataset"], [1, "Dataset"], [2, "Dataset"], [3, "Dataset"], [4, "Dataset"], [5, "Dataset"], [6, "Dataset"], [7, "Dataset"], [10, "Dataset"], [11, "Dataset"], [12, "Dataset"], [13, "Dataset"], [14, "Dataset"], [15, "Dataset"], [16, "Dataset"], [17, "Dataset"], [18, "Dataset"], [19, "Dataset"], [20, "Dataset"], [21, "Dataset"], [22, "Dataset"], [23, "Dataset"], [24, "Dataset"], [25, "Dataset"]], "1. Example evaluation pipeline": [[0, "1.-Example-evaluation-pipeline"], [18, "1.-Example-evaluation-pipeline"]], "2. Convert an FP32 PyTorch model to ONNX, simplify & then evaluate baseline FP32 accuracy": [[0, "2.-Convert-an-FP32-PyTorch-model-to-ONNX,-simplify-&-then-evaluate-baseline-FP32-accuracy"], [1, "2.-Convert-an-FP32-PyTorch-model-to-ONNX,-simplify-&-then-evaluate-baseline-FP32-accuracy"], [2, "2.-Convert-an-FP32-PyTorch-model-to-ONNX,-simplify-&-then-evaluate-baseline-FP32-accuracy"], [3, "2.-Convert-an-FP32-PyTorch-model-to-ONNX,-simplify-&-then-evaluate-baseline-FP32-accuracy"]], "3. Create a quantization simulation model": [[0, "3.-Create-a-quantization-simulation-model"], [18, "3.-Create-a-quantization-simulation-model"]], "Fold Batch Normalization layers": [[0, "Fold-Batch-Normalization-layers"], [1, "Fold-Batch-Normalization-layers"], [3, "Fold-Batch-Normalization-layers"], [5, "Fold-Batch-Normalization-layers"], [10, "Fold-Batch-Normalization-layers"], [11, "Fold-Batch-Normalization-layers"], [13, "Fold-Batch-Normalization-layers"], [14, "Fold-Batch-Normalization-layers"], [18, "Fold-Batch-Normalization-layers"], [19, "Fold-Batch-Normalization-layers"], [23, "Fold-Batch-Normalization-layers"], [24, "Fold-Batch-Normalization-layers"]], "Create Quantization Sim Model": [[0, "Create-Quantization-Sim-Model"], [18, "Create-Quantization-Sim-Model"], [21, "Create-Quantization-Sim-Model"]], "Compute Encodings": [[0, "Compute-Encodings"], [4, "Compute-Encodings"], [18, "Compute-Encodings"]], "4. Run AMP algorithm on the quantized model": [[0, "4.-Run-AMP-algorithm-on-the-quantized-model"], [4, "4.-Run-AMP-algorithm-on-the-quantized-model"], [18, "4.-Run-AMP-algorithm-on-the-quantized-model"]], "Define callback functions for AMP": [[0, "Define-callback-functions-for-AMP"], [18, "Define-callback-functions-for-AMP"]], "Parameters for AMP algorithm": [[0, "Parameters-for-AMP-algorithm"], [4, "Parameters-for-AMP-algorithm"], [18, "Parameters-for-AMP-algorithm"]], "Call AMP API": [[0, "Call-AMP-API"], [18, "Call-AMP-API"]], "Adaptive Rounding (AdaRound)": [[1, "Adaptive-Rounding-(AdaRound)"], [5, "Adaptive-Rounding-(AdaRound)"], [19, "Adaptive-Rounding-(AdaRound)"]], "1. Instantiate the example training and validation pipeline": [[1, "1.-Instantiate-the-example-training-and-validation-pipeline"], [2, "1.-Instantiate-the-example-training-and-validation-pipeline"], [3, "1.-Instantiate-the-example-training-and-validation-pipeline"], [5, "1.-Instantiate-the-example-training-and-validation-pipeline"], [6, "1.-Instantiate-the-example-training-and-validation-pipeline"], [14, "1.-Instantiate-the-example-training-and-validation-pipeline"], [15, "1.-Instantiate-the-example-training-and-validation-pipeline"], [16, "1.-Instantiate-the-example-training-and-validation-pipeline"], [17, "1.-Instantiate-the-example-training-and-validation-pipeline"], [19, "1.-Instantiate-the-example-training-and-validation-pipeline"], [22, "1.-Instantiate-the-example-training-and-validation-pipeline"], [23, "1.-Instantiate-the-example-training-and-validation-pipeline"], [24, "1.-Instantiate-the-example-training-and-validation-pipeline"]], "3. Create a quantization simulation model and determine quantized accuracy": [[1, "3.-Create-a-quantization-simulation-model-and-determine-quantized-accuracy"], [2, "3.-Create-a-quantization-simulation-model-and-determine-quantized-accuracy"], [3, "3.-Create-a-quantization-simulation-model-and-determine-quantized-accuracy"], [5, "3.-Create-a-quantization-simulation-model-and-determine-quantized-accuracy"], [10, "3.-Create-a-quantization-simulation-model-and-determine-quantized-accuracy"], [11, "3.-Create-a-quantization-simulation-model-and-determine-quantized-accuracy"], [13, "3.-Create-a-quantization-simulation-model-and-determine-quantized-accuracy"], [14, "3.-Create-a-quantization-simulation-model-and-determine-quantized-accuracy"], [19, "3.-Create-a-quantization-simulation-model-and-determine-quantized-accuracy"], [22, "3.-Create-a-quantization-simulation-model-and-determine-quantized-accuracy"], [23, "3.-Create-a-quantization-simulation-model-and-determine-quantized-accuracy"], [24, "3.-Create-a-quantization-simulation-model-and-determine-quantized-accuracy"]], "Create the Quantization Sim Model": [[1, "Create-the-Quantization-Sim-Model"], [2, "Create-the-Quantization-Sim-Model"], [3, "Create-the-Quantization-Sim-Model"], [5, "Create-the-Quantization-Sim-Model"], [10, "Create-the-Quantization-Sim-Model"], [11, "Create-the-Quantization-Sim-Model"], [14, "Create-the-Quantization-Sim-Model"], [19, "Create-the-Quantization-Sim-Model"], [22, "Create-the-Quantization-Sim-Model"], [23, "Create-the-Quantization-Sim-Model"], [24, "Create-the-Quantization-Sim-Model"]], "4. Apply Adaround": [[1, "4.-Apply-Adaround"], [5, "4.-Apply-Adaround"], [13, "4.-Apply-Adaround"], [19, "4.-Apply-Adaround"]], "Next steps": [[1, "Next-steps"], [5, "Next-steps"], [10, "Next-steps"], [11, "Next-steps"], [14, "Next-steps"], [15, "Next-steps"], [16, "Next-steps"], [17, "Next-steps"], [19, "Next-steps"], [20, "Next-steps"], [22, "Next-steps"], [23, "Next-steps"], [24, "Next-steps"]], "For more information": [[1, "For-more-information"], [2, "For-more-information"], [3, "For-more-information"], [5, "For-more-information"], [6, "For-more-information"], [10, "For-more-information"], [11, "For-more-information"], [14, "For-more-information"], [15, "For-more-information"], [16, "For-more-information"], [17, "For-more-information"], [19, "For-more-information"], [20, "For-more-information"], [22, "For-more-information"], [23, "For-more-information"], [24, "For-more-information"]], "Cross-Layer Equalization": [[2, "Cross-Layer-Equalization"]], "Fold Batch Norm layers": [[2, "Fold-Batch-Norm-layers"], [22, "Fold-Batch-Norm-layers"]], "4. Apply CLE": [[2, "4.-Apply-CLE"], [14, "4.-Apply-CLE"]], "Quantization simulation": [[3, "Quantization-simulation"]], "1. Instantiate the example evaluation method": [[4, "1.-Instantiate-the-example-evaluation-method"]], "2. Load the FP32 model and evaluate the model to find the baseline FP32 accuracy": [[4, "2.-Load-the-FP32-model-and-evaluate-the-model-to-find-the-baseline-FP32-accuracy"]], "3.Create a quantization simulation model (with fake quantization ops inserted)": [[4, "3.Create-a-quantization-simulation-model-(with-fake-quantization-ops-inserted)"]], "Regular AMP": [[4, "Regular-AMP"]], "API Call for Regular AMP": [[4, "API-Call-for-Regular-AMP"]], "Fast AMP (AMP 2.0)": [[4, "Fast-AMP-(AMP-2.0)"]], "Summary": [[4, "Summary"], [7, "Summary"], [9, "Summary"], [13, "Summary"], [21, "Summary"]], "2. Load the model and evaluate to get a baseline FP32 accuracy score": [[5, "2.-Load-the-model-and-evaluate-to-get-a-baseline-FP32-accuracy-score"], [10, "2.-Load-the-model-and-evaluate-to-get-a-baseline-FP32-accuracy-score"], [11, "2.-Load-the-model-and-evaluate-to-get-a-baseline-FP32-accuracy-score"], [13, "2.-Load-the-model-and-evaluate-to-get-a-baseline-FP32-accuracy-score"], [14, "2.-Load-the-model-and-evaluate-to-get-a-baseline-FP32-accuracy-score"], [15, "2.-Load-the-model-and-evaluate-to-get-a-baseline-FP32-accuracy-score"], [16, "2.-Load-the-model-and-evaluate-to-get-a-baseline-FP32-accuracy-score"], [17, "2.-Load-the-model-and-evaluate-to-get-a-baseline-FP32-accuracy-score"], [18, "2.-Load-the-model-and-evaluate-to-get-a-baseline-FP32-accuracy-score"], [19, "2.-Load-the-model-and-evaluate-to-get-a-baseline-FP32-accuracy-score"], [22, "2.-Load-the-model-and-evaluate-to-get-a-baseline-FP32-accuracy-score"], [23, "2.-Load-the-model-and-evaluate-to-get-a-baseline-FP32-accuracy-score"], [24, "2.-Load-the-model-and-evaluate-to-get-a-baseline-FP32-accuracy-score"]], "AutoQuant": [[6, "AutoQuant"], [20, "AutoQuant"]], "2. Load a pretrained FP32 model": [[6, "2.-Load-a-pretrained-FP32-model"], [12, "2.-Load-a-pretrained-FP32-model"], [20, "2.-Load-a-pretrained-FP32-model"]], "3. Determine the baseline FP32 accuracy": [[6, "3.-Determine-the-baseline-FP32-accuracy"]], "4. Define constants and helper functions": [[6, "4.-Define-constants-and-helper-functions"]], "5. Apply AutoQuant": [[6, "5.-Apply-AutoQuant"]], "Quantization-Aware Training with BatchNorm Re-estimation": [[7, "Quantization-Aware-Training-with-BatchNorm-Re-estimation"], [21, "Quantization-Aware-Training-with-BatchNorm-Re-estimation"]], "1. Instantiate the example evaluation and training pipeline": [[7, "1.-Instantiate-the-example-evaluation-and-training-pipeline"]], "2. Define Constants and Datasets Prepare": [[7, "2.-Define-Constants-and-Datasets-Prepare"]], "2. Create the model in Keras": [[7, "2.-Create-the-model-in-Keras"]], "3. Train and evaluate the model": [[7, "3.-Train-and-evaluate-the-model"]], "4. Create a QuantizationSim Model": [[7, "4.-Create-a-QuantizationSim-Model"]], "Prepare the evaluation callback function": [[7, "Prepare-the-evaluation-callback-function"]], "5. Perform QAT": [[7, "5.-Perform-QAT"]], "Fold BatchNorm Layers": [[7, "Fold-BatchNorm-Layers"], [21, "Fold-BatchNorm-Layers"]], "5. Export Model": [[7, "5.-Export-Model"], [21, "5.-Export-Model"]], "Quantization-Aware Training with a Keras Transformer Model": [[8, "Quantization-Aware-Training-with-a-Keras-Transformer-Model"]], "Keras Model Preparer": [[9, "Keras-Model-Preparer"]], "1. Creating a Keras model with subclass layers": [[9, "1.-Creating-a-Keras-model-with-subclass-layers"]], "2. Converting the Keras model with subclass layers to a Keras model with functional layers": [[9, "2.-Converting-the-Keras-model-with-subclass-layers-to-a-Keras-model-with-functional-layers"]], "3. Showing similarities and differences between the original and converted models": [[9, "3.-Showing-similarities-and-differences-between-the-original-and-converted-models"]], "4. Discussing the limitations of the Keras Model Preparer": [[9, "4.-Discussing-the-limitations-of-the-Keras-Model-Preparer"]], "Quantization-aware training": [[10, "Quantization-aware-training"], [23, "Quantization-aware-training"]], "1. Instantiate the example evaluation and training datasets": [[10, "1.-Instantiate-the-example-evaluation-and-training-datasets"], [11, "1.-Instantiate-the-example-evaluation-and-training-datasets"]], "4. Perform QAT": [[10, "4.-Perform-QAT"], [11, "4.-Perform-QAT"], [23, "4.-Perform-QAT"], [24, "4.-Perform-QAT"]], "Quantization-Aware training with range learning": [[11, "Quantization-Aware-training-with-range-learning"]], "Quant Analyzer": [[12, "Quant-Analyzer"], [25, "Quant-Analyzer"]], "1. Example evaluation and training pipeline": [[12, "1.-Example-evaluation-and-training-pipeline"], [13, "1.-Example-evaluation-and-training-pipeline"], [21, "1.-Example-evaluation-and-training-pipeline"], [25, "1.-Example-evaluation-and-training-pipeline"]], "3. Apply QuantAnalyzer to the model": [[12, "3.-Apply-QuantAnalyzer-to-the-model"], [25, "3.-Apply-QuantAnalyzer-to-the-model"]], "Per-layer analysis by enabling/disabling quantization wrappers": [[12, "Per-layer-analysis-by-enabling/disabling-quantization-wrappers"], [25, "Per-layer-analysis-by-enabling/disabling-quantization-wrappers"]], "Encoding min/max ranges": [[12, "Encoding-min/max-ranges"], [25, "Encoding-min/max-ranges"]], "PDF of statistics": [[12, "PDF-of-statistics"], [25, "PDF-of-statistics"]], "Per-layer MSE loss": [[12, "Per-layer-MSE-loss"], [25, "Per-layer-MSE-loss"]], "Quantsim and Adaround - Per Channel Quantization (PCQ)": [[13, "Quantsim-and-Adaround---Per-Channel-Quantization-(PCQ)"]], "Cross-Layer Equalization with QuantSim": [[14, "Cross-Layer-Equalization-with-QuantSim"]], "Model compression using channel pruning": [[15, "Model-compression-using-channel-pruning"]], "3. Compress the model and fine-tune": [[15, "3.-Compress-the-model-and-fine-tune"], [16, "3.-Compress-the-model-and-fine-tune"], [17, "3.-Compress-the-model-and-fine-tune"]], "Model compression using spatial SVD": [[16, "Model-compression-using-spatial-SVD"]], "Model compression using spatial SVD and channel pruning": [[17, "Model-compression-using-spatial-SVD-and-channel-pruning"]], "1. Define Constants and Helper functions": [[20, "1.-Define-Constants-and-Helper-functions"]], "3. Run AutoQuant": [[20, "3.-Run-AutoQuant"]], "2. Load FP32 model": [[21, "2.-Load-FP32-model"]], "3. Create a quantization simulation model and Perform QAT": [[21, "3.-Create-a-quantization-simulation-model-and-Perform-QAT"]], "Perform QAT": [[21, "Perform-QAT"]], "4. Perform BatchNorm Reestimation": [[21, "4.-Perform-BatchNorm-Reestimation"]], "Re-estimate BatchNorm Statistics": [[21, "Re-estimate-BatchNorm-Statistics"]], "Cross-Layer Equalization and Bias Correction": [[22, "Cross-Layer-Equalization-and-Bias-Correction"]], "Techniques": [[22, "Techniques"]], "4. Apply CLE and BC": [[22, "4.-Apply-CLE-and-BC"]], "CLE": [[22, "CLE"]], "Bias Correction": [[22, "Bias-Correction"]], "Quantization-aware training with range learning": [[24, "Quantization-aware-training-with-range-learning"]], "2. Load the model": [[25, "2.-Load-the-model"]], "Welcome to AI Model Efficiency Toolkit API Docs!": [[26, "welcome-to-ai-model-efficiency-toolkit-api-docs"]], "Indices and tables": [[26, "indices-and-tables"]], "AIMET TensorFlow APIs": [[27, "aimet-tensorflow-apis"]], "AIMET TensorFlow AdaRound API": [[28, "aimet-tensorflow-adaround-api"]], "User Guide Link": [[28, "user-guide-link"], [31, "user-guide-link"], [39, "user-guide-link"], [41, "user-guide-link"], [42, "user-guide-link"], [43, "user-guide-link"], [51, "user-guide-link"], [53, "user-guide-link"], [55, "user-guide-link"], [57, "user-guide-link"], [66, "user-guide-link"], [68, "user-guide-link"]], "Examples Notebook Link": [[28, "examples-notebook-link"], [29, "examples-notebook-link"], [31, "examples-notebook-link"], [51, "examples-notebook-link"], [53, "examples-notebook-link"], [54, "examples-notebook-link"], [57, "examples-notebook-link"], [66, "examples-notebook-link"], [68, "examples-notebook-link"]], "Top-level API": [[28, "top-level-api"], [32, "top-level-api"], [35, "top-level-api"], [37, "top-level-api"], [39, "top-level-api"], [41, "top-level-api"], [42, "top-level-api"], [44, "top-level-api"], [45, "top-level-api"], [46, "top-level-api"], [48, "top-level-api"], [51, "top-level-api"], [53, "top-level-api"], [58, "top-level-api"], [59, "top-level-api"], [61, "top-level-api"], [64, "top-level-api"], [66, "top-level-api"], [68, "top-level-api"], [88, "top-level-api"], [89, "top-level-api"]], "Adaround Parameters": [[28, "adaround-parameters"], [41, "adaround-parameters"], [51, "adaround-parameters"]], "Enum Definition": [[28, "enum-definition"], [51, "enum-definition"], [58, "enum-definition"], [68, "enum-definition"]], "Code Examples": [[28, "code-examples"], [30, "code-examples"], [33, "code-examples"], [35, "code-examples"], [37, "code-examples"], [39, "code-examples"], [42, "code-examples"], [45, "code-examples"], [46, "code-examples"], [48, "code-examples"], [53, "code-examples"], [56, "code-examples"], [59, "code-examples"], [61, "code-examples"], [66, "code-examples"], [70, "code-examples"], [71, "code-examples"], [72, "code-examples"]], "AIMET TensorFlow BatchNorm Re-estimation APIs": [[29, "aimet-tensorflow-batchnorm-re-estimation-apis"]], "Introduction": [[29, "introduction"], [30, "introduction"], [31, "introduction"], [36, "introduction"], [43, "introduction"], [54, "introduction"], [56, "introduction"], [57, "introduction"], [65, "introduction"]], "Top-level APIs": [[29, "top-level-apis"], [54, "top-level-apis"]], "Code Example": [[29, "code-example"], [31, "code-example"], [32, "code-example"], [43, "code-example"], [44, "code-example"], [57, "code-example"], [58, "code-example"], [69, "code-example"], [86, "code-example"]], "Limitations": [[29, "limitations"], [35, "limitations"]], "AIMET TensorFlow Compression API": [[30, "aimet-tensorflow-compression-api"]], "Top-level API for Compression": [[30, "top-level-api-for-compression"], [56, "top-level-api-for-compression"]], "Greedy Selection Parameters": [[30, "greedy-selection-parameters"], [56, "greedy-selection-parameters"]], "Spatial SVD Configuration": [[30, "spatial-svd-configuration"], [56, "spatial-svd-configuration"]], "Configuration Definitions": [[30, "configuration-definitions"], [56, "configuration-definitions"]], "AIMET TensorFlow Cross Layer Equalization APIs": [[31, "aimet-tensorflow-cross-layer-equalization-apis"]], "Cross Layer Equalization API": [[31, "cross-layer-equalization-api"], [43, "cross-layer-equalization-api"], [57, "cross-layer-equalization-api"]], "Primitive APIs": [[31, "primitive-apis"], [57, "primitive-apis"]], "AIMET TensorFlow Layer Output Generation API": [[32, "aimet-tensorflow-layer-output-generation-api"]], "AIMET TensorFlow Mixed Precision API": [[33, "aimet-tensorflow-mixed-precision-api"]], "Top-level API for Regular AMP": [[33, "top-level-api-for-regular-amp"]], "Top-level API for Fast AMP (AMP 2.0)": [[33, "top-level-api-for-fast-amp-amp-2-0"]], "Quantizer Groups definition": [[33, "quantizer-groups-definition"], [45, "quantizer-groups-definition"], [59, "quantizer-groups-definition"]], "CallbackFunc Definition": [[33, "callbackfunc-definition"], [45, "callbackfunc-definition"], [59, "callbackfunc-definition"]], "TensorFlow Model Guidelines": [[34, "tensorflow-model-guidelines"]], "TensorFlow Model Preparer API": [[35, "tensorflow-model-preparer-api"]], "AIMET TensorFlow Cross Layer Equalization Primitive API": [[36, "aimet-tensorflow-cross-layer-equalization-primitive-api"]], "Higher Level APIs for Cross Layer Equalization": [[36, "higher-level-apis-for-cross-layer-equalization"], [65, "higher-level-apis-for-cross-layer-equalization"]], "Code Examples for Higher Level APIs": [[36, "code-examples-for-higher-level-apis"], [65, "code-examples-for-higher-level-apis"]], "Lower Level APIs for Cross Layer Equalization": [[36, "lower-level-apis-for-cross-layer-equalization"], [65, "lower-level-apis-for-cross-layer-equalization"]], "Custom Datatype used": [[36, "custom-datatype-used"]], "Code Example for Lower level APIs": [[36, "code-example-for-lower-level-apis"]], "Example helper methods to perform CLE in manual mode": [[36, "example-helper-methods-to-perform-cle-in-manual-mode"]], "AIMET TensorFlow Quant Analyzer API": [[37, "aimet-tensorflow-quant-analyzer-api"]], "AIMET TensorFlow Quantization APIs": [[38, "aimet-tensorflow-quantization-apis"]], "AIMET TensorFlow Quantization SIM API": [[39, "aimet-tensorflow-quantization-sim-api"]], "AIMET ONNX APIs": [[40, "aimet-onnx-apis"]], "AIMET ONNX AdaRound API": [[41, "aimet-onnx-adaround-api"]], "Code Example - Adaptive Rounding (AdaRound)": [[41, "code-example-adaptive-rounding-adaround"], [51, "code-example-adaptive-rounding-adaround"]], "AIMET ONNX AutoQuant API": [[42, "aimet-onnx-autoquant-api"]], "AIMET ONNX Cross Layer Equalization APIs": [[43, "aimet-onnx-cross-layer-equalization-apis"]], "AIMET ONNX Layer Output Generation API": [[44, "aimet-onnx-layer-output-generation-api"]], "AIMET ONNX Mixed Precision API": [[45, "aimet-onnx-mixed-precision-api"]], "AIMET ONNX Quant Analyzer API": [[46, "aimet-onnx-quant-analyzer-api"]], "Run specific utility": [[46, "run-specific-utility"], [66, "run-specific-utility"]], "AIMET ONNX Quantization APIs": [[47, "aimet-onnx-quantization-apis"]], "AIMET ONNX Quantization SIM API": [[48, "aimet-onnx-quantization-sim-api"]], "Encoding Format Specification": [[49, "encoding-format-specification"]], "1. Versioning": [[49, "versioning"]], "2. Version 0.4.0 (up to)": [[49, "version-0-4-0-up-to"]], "2.1. Encoding Specification": [[49, "encoding-specification"]], "2.2. Encoding File Example for PyTorch": [[49, "encoding-file-example-for-pytorch"]], "2.3. Encoding File Example for TensorFlow": [[49, "encoding-file-example-for-tensorflow"]], "3. Version 0.5.0": [[49, "version-0-5-0"]], "3.1. Encoding Specification": [[49, "id1"]], "3.2. Encoding File Example for PyTorch": [[49, "id2"]], "3.3. Encoding File Example for TensorFlow": [[49, "id3"]], "4. Version 0.6.1": [[49, "version-0-6-1"]], "4.1. Encoding Specification": [[49, "id4"]], "AIMET PyTorch APIs": [[50, "aimet-pytorch-apis"]], "AIMET PyTorch AdaRound API": [[51, "aimet-pytorch-adaround-api"]], "Architecture Checker API": [[52, "architecture-checker-api"]], "HTML report content": [[52, "id1"]], "AIMET PyTorch AutoQuant API": [[53, "aimet-pytorch-autoquant-api"]], "AIMET PyTorch BatchNorm Re-estimation APIs": [[54, "aimet-pytorch-batchnorm-re-estimation-apis"]], "Code Example - BN-Reestimation": [[54, "code-example-bn-reestimation"]], "AIMET PyTorch Bias Correction API": [[55, "aimet-pytorch-bias-correction-api"]], "Bias Correction API": [[55, "bias-correction-api"]], "ConvBnInfoType": [[55, "convbninfotype"]], "ActivationType": [[55, "activationtype"]], "Quantization Params": [[55, "quantization-params"]], "Code Example #1 Empirical Bias Correction": [[55, "code-example-1-empirical-bias-correction"]], "Code Example #2 Analytical + Empirical Bias correction": [[55, "code-example-2-analytical-empirical-bias-correction"]], "AIMET PyTorch Compression API": [[56, "aimet-pytorch-compression-api"]], "Weight SVD Configuration": [[56, "weight-svd-configuration"]], "Channel Pruning Configuration": [[56, "channel-pruning-configuration"]], "AIMET PyTorch Cross Layer Equalization APIs": [[57, "aimet-pytorch-cross-layer-equalization-apis"]], "AIMET PyTorch Layer Output Generation API": [[58, "aimet-pytorch-layer-output-generation-api"]], "AIMET PyTorch Mixed Precision API": [[59, "aimet-pytorch-mixed-precision-api"]], "PyTorch Model Guidelines": [[60, "pytorch-model-guidelines"]], "Model Preparer API": [[61, "model-preparer-api"]], "Limitations of torch.fx symbolic trace API": [[61, "limitations-of-torch-fx-symbolic-trace-api"]], "Model Validator Utility": [[62, "model-validator-utility"]], "PyTorch Multi-GPU support": [[63, "pytorch-multi-gpu-support"]], "PEFT LoRA": [[64, "peft-lora"]], "User flow": [[64, "user-flow"]], "AIMET PyTorch Cross Layer Equalization Primitive API": [[65, "aimet-pytorch-cross-layer-equalization-primitive-api"]], "ClsSetInfo Definition": [[65, "clssetinfo-definition"]], "Code Examples for Lower Level APIs": [[65, "code-examples-for-lower-level-apis"]], "AIMET PyTorch Quant Analyzer API": [[66, "aimet-pytorch-quant-analyzer-api"]], "AIMET PyTorch Quantization APIs": [[67, "aimet-pytorch-quantization-apis"]], "aimet_torch": [[67, "aimet-torch"]], "API Reference": [[67, "api-reference"], [67, "id1"]], "aimet_torch.v2": [[67, "aimet-torch-v2"]], "What\u2019s New": [[67, "what-s-new"]], "Backwards Compatibility": [[67, "backwards-compatibility"]], "AIMET PyTorch Quantization SIM API": [[68, "aimet-pytorch-quantization-sim-api"]], "Guidelines": [[68, "guidelines"]], "Code Example - Quantization Aware Training (QAT)": [[68, "code-example-quantization-aware-training-qat"]], "AIMET Torch SparseConvolution custom onnx export": [[69, "aimet-torch-sparseconvolution-custom-onnx-export"]], "Custom API for the spconv modules": [[69, "custom-api-for-the-spconv-modules"]], "AIMET Visualization Compression API": [[70, "aimet-visualization-compression-api"]], "Top-level API Compression": [[70, "top-level-api-compression"]], "AIMET Visualization for Quantization API": [[71, "aimet-visualization-for-quantization-api"]], "Top-level API Quantization": [[71, "top-level-api-quantization"]], "Migrate to aimet_torch.v2": [[72, "migrate-to-aimet-torch-v2"]], "Changes in aimet_torch v2": [[72, "changes-in-aimet-torch-v2"]], "Migration Process": [[72, "migration-process"]], "Imports": [[72, "imports"]], "QuantizationSimModel": [[72, "quantizationsimmodel"]], "Moving from QuantWrapper to Quantized Modules": [[72, "moving-from-quantwrapper-to-quantized-modules"]], "Moving from StaticGrid and LearnedGrid Quantizer to Affine and Float Quantizer": [[72, "moving-from-staticgrid-and-learnedgrid-quantizer-to-affine-and-float-quantizer"]], "AIMET Installation": [[73, "aimet-installation"]], "Quick Install": [[73, "quick-install"]], "Release Packages": [[73, "release-packages"]], "System Requirements": [[73, "system-requirements"]], "Advanced Installation Instructions": [[73, "advanced-installation-instructions"]], "AIMET Installation in Docker": [[74, "aimet-installation-in-docker"]], "Set variant": [[74, "set-variant"]], "Use prebuilt docker image": [[74, "use-prebuilt-docker-image"]], "Build docker image locally": [[74, "build-docker-image-locally"]], "Start docker container": [[74, "start-docker-container"]], "Install AIMET packages": [[74, "install-aimet-packages"], [75, "install-aimet-packages"]], "From PyPI": [[74, "from-pypi"], [75, "from-pypi"]], "From Release Package": [[74, "from-release-package"], [75, "from-release-package"]], "Environment setup": [[74, "environment-setup"], [75, "environment-setup"]], "AIMET Installation and Setup": [[75, "aimet-installation-and-setup"]], "Install prerequisite packages": [[75, "install-prerequisite-packages"]], "Install GPU packages": [[75, "install-gpu-packages"]], "Install GPU packages for PyTorch 2.1 or PyTorch 1.13 or ONNX or TensorFlow": [[75, "install-gpu-packages-for-pytorch-2-1-or-pytorch-1-13-or-onnx-or-tensorflow"]], "Install common debian packages": [[75, "install-common-debian-packages"]], "Install tensorflow GPU debian packages": [[75, "install-tensorflow-gpu-debian-packages"]], "Install torch GPU debian packages": [[75, "install-torch-gpu-debian-packages"]], "Install ONNX GPU debian packages": [[75, "install-onnx-gpu-debian-packages"]], "Replace Pillow with Pillow-SIMD": [[75, "replace-pillow-with-pillow-simd"]], "Replace onnxruntime with onnxruntime-gpu": [[75, "replace-onnxruntime-with-onnxruntime-gpu"]], "Post installation steps": [[75, "post-installation-steps"]], "QuantizationMixin": [[77, "quantizationmixin"]], "quantization.affine": [[78, "module-aimet_torch.v2.quantization.affine"]], "Classes": [[78, "classes"], [80, "classes"], [81, "classes"]], "Functions": [[78, "functions"]], "FloatQuantizeDequantize": [[79, "floatquantizedequantize"]], "QuantizeDequantize": [[79, "quantizedequantize"]], "quantization.float": [[80, "module-aimet_torch.v2.quantization.float"]], "quantization.tensor": [[81, "quantization-tensor"]], "Visualization Tools": [[82, "visualization-tools"]], "Blockwise Quantization": [[83, "blockwise-quantization"]], "Low Power Blockwise Quantization (LPBQ)": [[83, "low-power-blockwise-quantization-lpbq"]], "Top Level API": [[83, "top-level-api"], [86, "top-level-api"]], "Export": [[83, "export"]], "Encoding Analyzers": [[84, "encoding-analyzers"]], "Variants": [[84, "variants"]], "Post-Training Quantization": [[85, "post-training-quantization"], [102, "post-training-quantization"]], "GPTVQ": [[86, "gptvq"]], "GPTVQ Parameters": [[86, "gptvq-parameters"]], "AIMET: AI Model Efficiency Toolkit Documentation": [[87, "aimet-ai-model-efficiency-toolkit-documentation"]], "Getting Started": [[87, "getting-started"]], "Examples": [[87, null]], "Feature Descriptions": [[87, null]], "AIMET PyTorch API": [[87, null]], "Quantized Modules": [[88, "quantized-modules"]], "Configuration": [[88, "configuration"]], "Computing Encodings": [[88, "computing-encodings"]], "Quantized Module Classes": [[88, "quantized-module-classes"]], "Quantizers": [[89, "quantizers"]], "Quickstart Guide": [[90, "quickstart-guide"]], "PyTorch prerequisites": [[90, "pytorch-prerequisites"]], "Prepare the floating point model for quantization": [[90, "prepare-the-floating-point-model-for-quantization"]], "1) Model preparation": [[90, "model-preparation"]], "2) BatchNorm fold": [[90, "batchnorm-fold"]], "Quantize the model": [[90, "quantize-the-model"]], "Fine-tune the model with quantization aware training": [[90, "fine-tune-the-model-with-quantization-aware-training"]], "Export the quantsim model": [[90, "export-the-quantsim-model"]], "AIMET AdaRound": [[91, "aimet-adaround"]], "AdaRound use cases": [[91, "adaround-use-cases"]], "AdaRound hyper parameters guidelines": [[91, "adaround-hyper-parameters-guidelines"]], "AdaRound API": [[91, "adaround-api"]], "AIMET AutoQuant": [[92, "aimet-autoquant"]], "Overview": [[92, "overview"], [93, "overview"], [97, "overview"], [98, "overview"], [100, "overview"], [103, "overview"], [104, "overview"], [105, "overview"], [106, "overview"], [108, "overview"], [111, "overview"], [112, "overview"], [114, "overview"]], "Workflow": [[92, "workflow"], [93, "workflow"]], "AutoQuant API": [[92, "autoquant-api"]], "AIMET Batch Norm Re-estimation": [[93, "aimet-batch-norm-re-estimation"]], "BN Re-estimation API": [[93, "bn-re-estimation-api"]], "AIMET channel pruning": [[94, "aimet-channel-pruning"]], "Procedure": [[94, "procedure"]], "Channel selection": [[94, "channel-selection"]], "Winnowing": [[94, "winnowing"]], "Weight reconstruction": [[94, "weight-reconstruction"]], "AIMET Compression Features Guidebook": [[95, "aimet-compression-features-guidebook"]], "AIMET examples": [[96, "aimet-examples"]], "Browse the notebooks": [[96, "browse-the-notebooks"]], "Running the notebooks": [[96, "running-the-notebooks"]], "1. Run the notebook server": [[96, "run-the-notebook-server"]], "2. Download the example notebooks and related code": [[96, "download-the-example-notebooks-and-related-code"]], "3. Run the notebooks": [[96, "run-the-notebooks"]], "AIMET greedy compression ratio selection": [[97, "aimet-greedy-compression-ratio-selection"]], "How it works": [[97, "how-it-works"]], "Per-layer exploration": [[97, "per-layer-exploration"]], "Compression ratio selection": [[97, "compression-ratio-selection"], [100, "compression-ratio-selection"]], "AI Model Efficiency Toolkit User Guide": [[98, "ai-model-efficiency-toolkit-user-guide"]], "Features": [[98, "features"]], "More Information": [[98, "more-information"]], "Release Information": [[98, "release-information"]], "toc tree": [[98, "toc-tree"]], "AIMET Known Issues": [[99, "aimet-known-issues"]], "AIMET model compression": [[100, "aimet-model-compression"]], "Use Case": [[100, "use-case"]], "Model compression": [[100, "model-compression"]], "Optional techniques": [[100, "optional-techniques"]], "Rank Rounding": [[100, "rank-rounding"]], "Per-layer fine-tuning": [[100, "per-layer-fine-tuning"]], "NOTE": [[100, null]], "FAQs": [[100, "faqs"], [103, "faqs"]], "References": [[100, "references"], [103, "references"]], "Model Guidelines for PyTorch": [[101, "model-guidelines-for-pytorch"]], "AIMET model quantization": [[102, "aimet-model-quantization"]], "Use cases": [[102, "use-cases"]], "AIMET quantization features": [[102, "aimet-quantization-features"]], "Debugging and Analysis Tools": [[102, "debugging-and-analysis-tools"]], "AIMET quantization workflow": [[102, "aimet-quantization-workflow"]], "PyTorch": [[102, "pytorch"], [112, "pytorch"]], "Debugging": [[102, "debugging"]], "AIMET post-training quantization techniques": [[103, "aimet-post-training-quantization-techniques"]], "User Flow": [[103, "user-flow"]], "Cross-Layer Equalization API": [[103, "cross-layer-equalization-api"]], "AIMET QuantAnalyzer": [[104, "aimet-quantanalyzer"]], "Requirements": [[104, "requirements"]], "Detailed analysis descriptions": [[104, "detailed-analysis-descriptions"]], "QuantAnalyzer API": [[104, "quantanalyzer-api"]], "AIMET quantization aware training": [[105, "aimet-quantization-aware-training"]], "QAT workflow": [[105, "qat-workflow"]], "QAT modes": [[105, "qat-modes"]], "Recommendations for quantization-aware training": [[105, "recommendations-for-quantization-aware-training"]], "Quantization simulation configuration": [[106, "quantization-simulation-configuration"]], "Configuration file structure": [[106, "configuration-file-structure"]], "Modifying configuration file sections": [[106, "modifying-configuration-file-sections"]], "AIMET quantization diagnostics": [[107, "aimet-quantization-diagnostics"]], "AIMET quantization simulation": [[108, "aimet-quantization-simulation"]], "QuantSim workflow": [[108, "quantsim-workflow"]], "Simulating quantization noise": [[108, "simulating-quantization-noise"]], "Determining quantization parameters (encodings)": [[108, "determining-quantization-parameters-encodings"]], "Quantization schemes": [[108, "quantization-schemes"]], "Configuring quantization simulation operations": [[108, "configuring-quantization-simulation-operations"]], "Quantization Simulation APIs": [[108, "quantization-simulation-apis"]], "AIMET Release Notes": [[109, "aimet-release-notes"]], "1.22.2": [[109, "id1"]], "1.22.1": [[109, "id2"]], "1.22.0": [[109, "id3"]], "1.21.0": [[109, "id4"]], "1.20.0": [[109, "id5"]], "1.19.1.py37": [[109, "py37"]], "1.19.1": [[109, "id6"]], "1.18.0.py37": [[109, "id7"]], "1.18.0": [[109, "id8"]], "1.17.0.py37": [[109, "id9"]], "1.17.0": [[109, "id10"]], "1.16.2.py37": [[109, "id11"]], "1.16.2": [[109, "id12"]], "1.16.1.py37": [[109, "id13"]], "1.16.1": [[109, "id14"]], "1.16.0": [[109, "id15"]], "1.14.0": [[109, "id16"]], "1.13.0": [[109, "id17"]], "AIMET spatial SVD": [[110, "aimet-spatial-svd"]], "AIMET visualization": [[111, "aimet-visualization"]], "Design": [[111, "design"]], "Compression": [[111, "compression"]], "Starting a Bokeh server session": [[111, "starting-a-bokeh-server-session"]], "Visualizing compression ratios": [[111, "visualizing-compression-ratios"]], "AIMET visualization for quantization": [[112, "aimet-visualization-for-quantization"]], "Quantization": [[112, "quantization"]], "TensorFlow": [[112, "tensorflow"]], "AIMET weight SVD": [[113, "aimet-weight-svd"]], "AIMET winnowing": [[114, "aimet-winnowing"]], "Winnowing overview": [[114, "winnowing-overview"]], "How winnowing works": [[114, "how-winnowing-works"]]}, "indexentries": {"adaroundparameters (class in aimet_tensorflow.keras.adaround_weight)": [[28, "aimet_tensorflow.keras.adaround_weight.AdaroundParameters"]], "quantscheme (class in aimet_common.defs)": [[28, "aimet_common.defs.QuantScheme"], [51, "aimet_common.defs.QuantScheme"], [68, "aimet_common.defs.QuantScheme"]], "apply_adaround() (in module aimet_tensorflow.keras.adaround_weight.adaround)": [[28, "aimet_tensorflow.keras.adaround_weight.Adaround.apply_adaround"]], "post_training_percentile (aimet_common.defs.quantscheme attribute)": [[28, "aimet_common.defs.QuantScheme.post_training_percentile"], [51, "aimet_common.defs.QuantScheme.post_training_percentile"], [68, "aimet_common.defs.QuantScheme.post_training_percentile"]], "post_training_tf (aimet_common.defs.quantscheme attribute)": [[28, "aimet_common.defs.QuantScheme.post_training_tf"], [51, "aimet_common.defs.QuantScheme.post_training_tf"], [68, "aimet_common.defs.QuantScheme.post_training_tf"]], "post_training_tf_enhanced (aimet_common.defs.quantscheme attribute)": [[28, "aimet_common.defs.QuantScheme.post_training_tf_enhanced"], [51, "aimet_common.defs.QuantScheme.post_training_tf_enhanced"], [68, "aimet_common.defs.QuantScheme.post_training_tf_enhanced"]], "training_range_learning_with_tf_enhanced_init (aimet_common.defs.quantscheme attribute)": [[28, "aimet_common.defs.QuantScheme.training_range_learning_with_tf_enhanced_init"], [51, "aimet_common.defs.QuantScheme.training_range_learning_with_tf_enhanced_init"], [68, "aimet_common.defs.QuantScheme.training_range_learning_with_tf_enhanced_init"]], "training_range_learning_with_tf_init (aimet_common.defs.quantscheme attribute)": [[28, "aimet_common.defs.QuantScheme.training_range_learning_with_tf_init"], [51, "aimet_common.defs.QuantScheme.training_range_learning_with_tf_init"], [68, "aimet_common.defs.QuantScheme.training_range_learning_with_tf_init"]], "fold_all_batch_norms_to_scale() (in module aimet_tensorflow.keras.batch_norm_fold)": [[29, "aimet_tensorflow.keras.batch_norm_fold.fold_all_batch_norms_to_scale"]], "reestimate_bn_stats() (in module aimet_tensorflow.keras.bn_reestimation)": [[29, "aimet_tensorflow.keras.bn_reestimation.reestimate_bn_stats"]], "compressionscheme (class in aimet_common.defs)": [[30, "aimet_common.defs.CompressionScheme"]], "costmetric (class in aimet_common.defs)": [[30, "aimet_common.defs.CostMetric"]], "modelcompressor (class in aimet_tensorflow.keras.compress)": [[30, "aimet_tensorflow.keras.compress.ModelCompressor"]], "modulecompratiopair (class in aimet_tensorflow.keras.defs)": [[30, "aimet_tensorflow.keras.defs.ModuleCompRatioPair"]], "spatialsvdparameters (class in aimet_tensorflow.keras.defs)": [[30, "aimet_tensorflow.keras.defs.SpatialSvdParameters"]], "spatialsvdparameters.automodeparams (class in aimet_tensorflow.keras.defs)": [[30, "aimet_tensorflow.keras.defs.SpatialSvdParameters.AutoModeParams"]], "spatialsvdparameters.manualmodeparams (class in aimet_tensorflow.keras.defs)": [[30, "aimet_tensorflow.keras.defs.SpatialSvdParameters.ManualModeParams"]], "spatialsvdparameters.mode (class in aimet_tensorflow.keras.defs)": [[30, "aimet_tensorflow.keras.defs.SpatialSvdParameters.Mode"]], "auto (aimet_tensorflow.keras.defs.spatialsvdparameters.mode attribute)": [[30, "aimet_tensorflow.keras.defs.SpatialSvdParameters.Mode.auto"]], "channel_pruning (aimet_common.defs.compressionscheme attribute)": [[30, "aimet_common.defs.CompressionScheme.channel_pruning"]], "compress_model() (aimet_tensorflow.keras.compress.modelcompressor static method)": [[30, "aimet_tensorflow.keras.compress.ModelCompressor.compress_model"]], "mac (aimet_common.defs.costmetric attribute)": [[30, "aimet_common.defs.CostMetric.mac"]], "manual (aimet_tensorflow.keras.defs.spatialsvdparameters.mode attribute)": [[30, "aimet_tensorflow.keras.defs.SpatialSvdParameters.Mode.manual"]], "memory (aimet_common.defs.costmetric attribute)": [[30, "aimet_common.defs.CostMetric.memory"]], "spatial_svd (aimet_common.defs.compressionscheme attribute)": [[30, "aimet_common.defs.CompressionScheme.spatial_svd"]], "weight_svd (aimet_common.defs.compressionscheme attribute)": [[30, "aimet_common.defs.CompressionScheme.weight_svd"]], "equalize_model() (in module aimet_tensorflow.keras.cross_layer_equalization)": [[31, "aimet_tensorflow.keras.cross_layer_equalization.equalize_model"]], "layeroutpututil (class in aimet_tensorflow.keras.layer_output_utils)": [[32, "aimet_tensorflow.keras.layer_output_utils.LayerOutputUtil"]], "generate_layer_outputs() (aimet_tensorflow.keras.layer_output_utils.layeroutpututil method)": [[32, "aimet_tensorflow.keras.layer_output_utils.LayerOutputUtil.generate_layer_outputs"]], "callbackfunc (class in aimet_common.defs)": [[33, "aimet_common.defs.CallbackFunc"], [45, "aimet_common.defs.CallbackFunc"], [59, "aimet_common.defs.CallbackFunc"]], "choose_fast_mixed_precision() (in module aimet_tensorflow.keras.mixed_precision)": [[33, "aimet_tensorflow.keras.mixed_precision.choose_fast_mixed_precision"]], "choose_mixed_precision() (in module aimet_tensorflow.keras.mixed_precision)": [[33, "aimet_tensorflow.keras.mixed_precision.choose_mixed_precision"]], "prepare_model() (in module aimet_tensorflow.keras.model_preparer)": [[35, "aimet_tensorflow.keras.model_preparer.prepare_model"]], "clssetinfo (class in aimet_tensorflow.keras.cross_layer_equalization)": [[36, "aimet_tensorflow.keras.cross_layer_equalization.ClsSetInfo"]], "clssetinfo.clssetlayerpairinfo (class in aimet_tensorflow.keras.cross_layer_equalization)": [[36, "aimet_tensorflow.keras.cross_layer_equalization.ClsSetInfo.ClsSetLayerPairInfo"]], "bias_fold() (in module aimet_tensorflow.keras.cross_layer_equalization.highbiasfold)": [[36, "aimet_tensorflow.keras.cross_layer_equalization.HighBiasFold.bias_fold"], [36, "id0"]], "fold_all_batch_norms() (in module aimet_tensorflow.keras.batch_norm_fold)": [[36, "aimet_tensorflow.keras.batch_norm_fold.fold_all_batch_norms"]], "fold_given_batch_norms() (in module aimet_tensorflow.keras.batch_norm_fold)": [[36, "aimet_tensorflow.keras.batch_norm_fold.fold_given_batch_norms"]], "scale_cls_sets() (in module aimet_tensorflow.keras.cross_layer_equalization.crosslayerscaling)": [[36, "aimet_tensorflow.keras.cross_layer_equalization.CrossLayerScaling.scale_cls_sets"]], "scale_model() (in module aimet_tensorflow.keras.cross_layer_equalization.crosslayerscaling)": [[36, "aimet_tensorflow.keras.cross_layer_equalization.CrossLayerScaling.scale_model"]], "quantanalyzer (class in aimet_tensorflow.keras.quant_analyzer)": [[37, "aimet_tensorflow.keras.quant_analyzer.QuantAnalyzer"]], "analyze() (aimet_tensorflow.keras.quant_analyzer.quantanalyzer method)": [[37, "aimet_tensorflow.keras.quant_analyzer.QuantAnalyzer.analyze"]], "quantizationsimmodel (class in aimet_tensorflow.keras.quantsim)": [[39, "aimet_tensorflow.keras.quantsim.QuantizationSimModel"]], "compute_encodings() (aimet_tensorflow.keras.quantsim.quantizationsimmodel method)": [[39, "aimet_tensorflow.keras.quantsim.QuantizationSimModel.compute_encodings"]], "export() (aimet_tensorflow.keras.quantsim.quantizationsimmodel method)": [[39, "aimet_tensorflow.keras.quantsim.QuantizationSimModel.export"]], "adaroundparameters (class in aimet_onnx.adaround.adaround_weight)": [[41, "aimet_onnx.adaround.adaround_weight.AdaroundParameters"]], "apply_adaround() (in module aimet_onnx.adaround.adaround_weight.adaround)": [[41, "aimet_onnx.adaround.adaround_weight.Adaround.apply_adaround"]], "autoquant (class in aimet_onnx.auto_quant_v2)": [[42, "aimet_onnx.auto_quant_v2.AutoQuant"]], "get_quant_scheme_candidates() (aimet_onnx.auto_quant_v2.autoquant method)": [[42, "aimet_onnx.auto_quant_v2.AutoQuant.get_quant_scheme_candidates"]], "optimize() (aimet_onnx.auto_quant_v2.autoquant method)": [[42, "aimet_onnx.auto_quant_v2.AutoQuant.optimize"]], "run_inference() (aimet_onnx.auto_quant_v2.autoquant method)": [[42, "aimet_onnx.auto_quant_v2.AutoQuant.run_inference"]], "set_adaround_params() (aimet_onnx.auto_quant_v2.autoquant method)": [[42, "aimet_onnx.auto_quant_v2.AutoQuant.set_adaround_params"]], "set_quant_scheme_candidates() (aimet_onnx.auto_quant_v2.autoquant method)": [[42, "aimet_onnx.auto_quant_v2.AutoQuant.set_quant_scheme_candidates"]], "equalize_model() (in module aimet_onnx.cross_layer_equalization)": [[43, "aimet_onnx.cross_layer_equalization.equalize_model"]], "layeroutpututil (class in aimet_onnx.layer_output_utils)": [[44, "aimet_onnx.layer_output_utils.LayerOutputUtil"]], "generate_layer_outputs() (aimet_onnx.layer_output_utils.layeroutpututil method)": [[44, "aimet_onnx.layer_output_utils.LayerOutputUtil.generate_layer_outputs"]], "evalcallbackfactory (class in aimet_onnx.amp.mixed_precision_algo)": [[45, "aimet_onnx.amp.mixed_precision_algo.EvalCallbackFactory"]], "quantizergroup (class in aimet_onnx.amp.quantizer_groups)": [[45, "aimet_onnx.amp.quantizer_groups.QuantizerGroup"]], "choose_mixed_precision() (in module aimet_onnx.mixed_precision)": [[45, "aimet_onnx.mixed_precision.choose_mixed_precision"]], "get_activation_quantizers() (aimet_onnx.amp.quantizer_groups.quantizergroup method)": [[45, "aimet_onnx.amp.quantizer_groups.QuantizerGroup.get_activation_quantizers"]], "get_active_quantizers() (aimet_onnx.amp.quantizer_groups.quantizergroup method)": [[45, "aimet_onnx.amp.quantizer_groups.QuantizerGroup.get_active_quantizers"]], "get_candidate() (aimet_onnx.amp.quantizer_groups.quantizergroup method)": [[45, "aimet_onnx.amp.quantizer_groups.QuantizerGroup.get_candidate"]], "get_param_quantizers() (aimet_onnx.amp.quantizer_groups.quantizergroup method)": [[45, "aimet_onnx.amp.quantizer_groups.QuantizerGroup.get_param_quantizers"]], "set_quantizers_to_candidate() (aimet_onnx.amp.quantizer_groups.quantizergroup method)": [[45, "aimet_onnx.amp.quantizer_groups.QuantizerGroup.set_quantizers_to_candidate"]], "sqnr() (aimet_onnx.amp.mixed_precision_algo.evalcallbackfactory method)": [[45, "aimet_onnx.amp.mixed_precision_algo.EvalCallbackFactory.sqnr"]], "to_list() (aimet_onnx.amp.quantizer_groups.quantizergroup method)": [[45, "aimet_onnx.amp.quantizer_groups.QuantizerGroup.to_list"]], "quantanalyzer (class in aimet_onnx.quant_analyzer)": [[46, "aimet_onnx.quant_analyzer.QuantAnalyzer"]], "analyze() (aimet_onnx.quant_analyzer.quantanalyzer method)": [[46, "aimet_onnx.quant_analyzer.QuantAnalyzer.analyze"]], "check_model_sensitivity_to_quantization() (aimet_onnx.quant_analyzer.quantanalyzer method)": [[46, "aimet_onnx.quant_analyzer.QuantAnalyzer.check_model_sensitivity_to_quantization"]], "create_quantsim_and_encodings() (aimet_onnx.quant_analyzer.quantanalyzer method)": [[46, "aimet_onnx.quant_analyzer.QuantAnalyzer.create_quantsim_and_encodings"]], "enable_per_layer_mse_loss() (aimet_onnx.quant_analyzer.quantanalyzer method)": [[46, "aimet_onnx.quant_analyzer.QuantAnalyzer.enable_per_layer_mse_loss"]], "export_per_layer_encoding_min_max_range() (aimet_onnx.quant_analyzer.quantanalyzer method)": [[46, "aimet_onnx.quant_analyzer.QuantAnalyzer.export_per_layer_encoding_min_max_range"]], "export_per_layer_mse_loss() (aimet_onnx.quant_analyzer.quantanalyzer method)": [[46, "aimet_onnx.quant_analyzer.QuantAnalyzer.export_per_layer_mse_loss"]], "export_per_layer_stats_histogram() (aimet_onnx.quant_analyzer.quantanalyzer method)": [[46, "aimet_onnx.quant_analyzer.QuantAnalyzer.export_per_layer_stats_histogram"]], "perform_per_layer_analysis_by_disabling_quantizers() (aimet_onnx.quant_analyzer.quantanalyzer method)": [[46, "aimet_onnx.quant_analyzer.QuantAnalyzer.perform_per_layer_analysis_by_disabling_quantizers"]], "perform_per_layer_analysis_by_enabling_quantizers() (aimet_onnx.quant_analyzer.quantanalyzer method)": [[46, "aimet_onnx.quant_analyzer.QuantAnalyzer.perform_per_layer_analysis_by_enabling_quantizers"]], "quantizationsimmodel (class in aimet_onnx.quantsim)": [[48, "aimet_onnx.quantsim.QuantizationSimModel"]], "compute_encodings() (aimet_onnx.quantsim.quantizationsimmodel method)": [[48, "aimet_onnx.quantsim.QuantizationSimModel.compute_encodings"]], "export() (aimet_onnx.quantsim.quantizationsimmodel method)": [[48, "aimet_onnx.quantsim.QuantizationSimModel.export"]], "adaroundparameters (class in aimet_torch.v1.adaround.adaround_weight)": [[51, "aimet_torch.v1.adaround.adaround_weight.AdaroundParameters"]], "apply_adaround() (in module aimet_torch.v1.adaround.adaround_weight.adaround)": [[51, "aimet_torch.v1.adaround.adaround_weight.Adaround.apply_adaround"]], "check_model_arch() (in module aimet_torch.arch_checker.arch_checker.archchecker)": [[52, "aimet_torch.arch_checker.arch_checker.ArchChecker.check_model_arch"]], "autoquant (class in aimet_torch.v1.auto_quant)": [[53, "aimet_torch.v1.auto_quant.AutoQuant"]], "fold_all_batch_norms_to_scale() (in module aimet_torch.batch_norm_fold)": [[54, "aimet_torch.batch_norm_fold.fold_all_batch_norms_to_scale"]], "reestimate_bn_stats() (in module aimet_torch.bn_reestimation)": [[54, "aimet_torch.bn_reestimation.reestimate_bn_stats"]], "activationtype (class in aimet_common.defs)": [[55, "aimet_common.defs.ActivationType"]], "convbninfotype (class in aimet_common.bias_correction)": [[55, "aimet_common.bias_correction.ConvBnInfoType"]], "quantparams (class in aimet_torch.v1.quantsim)": [[55, "aimet_torch.v1.quantsim.QuantParams"]], "correct_bias() (in module aimet_torch.bias_correction)": [[55, "aimet_torch.bias_correction.correct_bias"]], "no_activation (aimet_common.defs.activationtype attribute)": [[55, "aimet_common.defs.ActivationType.no_activation"]], "relu (aimet_common.defs.activationtype attribute)": [[55, "aimet_common.defs.ActivationType.relu"]], "relu6 (aimet_common.defs.activationtype attribute)": [[55, "aimet_common.defs.ActivationType.relu6"]], "channelpruningparameters (class in aimet_torch.defs)": [[56, "aimet_torch.defs.ChannelPruningParameters"]], "channelpruningparameters.automodeparams (class in aimet_torch.defs)": [[56, "aimet_torch.defs.ChannelPruningParameters.AutoModeParams"]], "channelpruningparameters.manualmodeparams (class in aimet_torch.defs)": [[56, "aimet_torch.defs.ChannelPruningParameters.ManualModeParams"]], "channelpruningparameters.mode (class in aimet_torch.defs)": [[56, "aimet_torch.defs.ChannelPruningParameters.Mode"]], "greedyselectionparameters (class in aimet_common.defs)": [[56, "aimet_common.defs.GreedySelectionParameters"]], "modelcompressor (class in aimet_torch.compress)": [[56, "aimet_torch.compress.ModelCompressor"]], "modulecompratiopair (class in aimet_torch.defs)": [[56, "aimet_torch.defs.ModuleCompRatioPair"]], "spatialsvdparameters (class in aimet_torch.defs)": [[56, "aimet_torch.defs.SpatialSvdParameters"]], "spatialsvdparameters.automodeparams (class in aimet_torch.defs)": [[56, "aimet_torch.defs.SpatialSvdParameters.AutoModeParams"]], "spatialsvdparameters.manualmodeparams (class in aimet_torch.defs)": [[56, "aimet_torch.defs.SpatialSvdParameters.ManualModeParams"]], "spatialsvdparameters.mode (class in aimet_torch.defs)": [[56, "aimet_torch.defs.SpatialSvdParameters.Mode"]], "weightsvdparameters (class in aimet_torch.defs)": [[56, "aimet_torch.defs.WeightSvdParameters"]], "weightsvdparameters.automodeparams (class in aimet_torch.defs)": [[56, "aimet_torch.defs.WeightSvdParameters.AutoModeParams"]], "weightsvdparameters.manualmodeparams (class in aimet_torch.defs)": [[56, "aimet_torch.defs.WeightSvdParameters.ManualModeParams"]], "weightsvdparameters.mode (class in aimet_torch.defs)": [[56, "aimet_torch.defs.WeightSvdParameters.Mode"]], "auto (aimet_torch.defs.channelpruningparameters.mode attribute)": [[56, "aimet_torch.defs.ChannelPruningParameters.Mode.auto"]], "auto (aimet_torch.defs.spatialsvdparameters.mode attribute)": [[56, "aimet_torch.defs.SpatialSvdParameters.Mode.auto"]], "auto (aimet_torch.defs.weightsvdparameters.mode attribute)": [[56, "aimet_torch.defs.WeightSvdParameters.Mode.auto"]], "compress_model() (aimet_torch.compress.modelcompressor static method)": [[56, "aimet_torch.compress.ModelCompressor.compress_model"]], "manual (aimet_torch.defs.channelpruningparameters.mode attribute)": [[56, "aimet_torch.defs.ChannelPruningParameters.Mode.manual"]], "manual (aimet_torch.defs.spatialsvdparameters.mode attribute)": [[56, "aimet_torch.defs.SpatialSvdParameters.Mode.manual"]], "manual (aimet_torch.defs.weightsvdparameters.mode attribute)": [[56, "aimet_torch.defs.WeightSvdParameters.Mode.manual"]], "equalize_model() (in module aimet_torch.cross_layer_equalization)": [[57, "aimet_torch.cross_layer_equalization.equalize_model"]], "layeroutpututil (class in aimet_torch.layer_output_utils)": [[58, "aimet_torch.layer_output_utils.LayerOutputUtil"]], "namingscheme (class in aimet_torch.layer_output_utils)": [[58, "aimet_torch.layer_output_utils.NamingScheme"]], "onnx (aimet_torch.layer_output_utils.namingscheme attribute)": [[58, "aimet_torch.layer_output_utils.NamingScheme.ONNX"]], "pytorch (aimet_torch.layer_output_utils.namingscheme attribute)": [[58, "aimet_torch.layer_output_utils.NamingScheme.PYTORCH"]], "torchscript (aimet_torch.layer_output_utils.namingscheme attribute)": [[58, "aimet_torch.layer_output_utils.NamingScheme.TORCHSCRIPT"]], "generate_layer_outputs() (aimet_torch.layer_output_utils.layeroutpututil method)": [[58, "aimet_torch.layer_output_utils.LayerOutputUtil.generate_layer_outputs"]], "evalcallbackfactory (class in aimet_torch.amp.mixed_precision_algo)": [[59, "aimet_torch.amp.mixed_precision_algo.EvalCallbackFactory"]], "quantizergroup (class in aimet_torch.amp.quantizer_groups)": [[59, "aimet_torch.amp.quantizer_groups.QuantizerGroup"]], "choose_mixed_precision() (in module aimet_torch.mixed_precision)": [[59, "aimet_torch.mixed_precision.choose_mixed_precision"]], "get_active_quantizers() (aimet_torch.amp.quantizer_groups.quantizergroup method)": [[59, "aimet_torch.amp.quantizer_groups.QuantizerGroup.get_active_quantizers"]], "get_candidate() (aimet_torch.amp.quantizer_groups.quantizergroup method)": [[59, "aimet_torch.amp.quantizer_groups.QuantizerGroup.get_candidate"]], "get_input_quantizer_modules() (aimet_torch.amp.quantizer_groups.quantizergroup method)": [[59, "aimet_torch.amp.quantizer_groups.QuantizerGroup.get_input_quantizer_modules"]], "set_quantizers_to_candidate() (aimet_torch.amp.quantizer_groups.quantizergroup method)": [[59, "aimet_torch.amp.quantizer_groups.QuantizerGroup.set_quantizers_to_candidate"]], "sqnr() (aimet_torch.amp.mixed_precision_algo.evalcallbackfactory method)": [[59, "aimet_torch.amp.mixed_precision_algo.EvalCallbackFactory.sqnr"]], "to_list() (aimet_torch.amp.quantizer_groups.quantizergroup method)": [[59, "aimet_torch.amp.quantizer_groups.QuantizerGroup.to_list"]], "prepare_model() (in module aimet_torch.model_preparer)": [[61, "aimet_torch.model_preparer.prepare_model"]], "adaptermetadata (class in aimet_torch.peft)": [[64, "aimet_torch.peft.AdapterMetaData"]], "peftquantutils (class in aimet_torch.peft)": [[64, "aimet_torch.peft.PeftQuantUtils"]], "disable_lora_adapters() (aimet_torch.peft.peftquantutils method)": [[64, "aimet_torch.peft.PeftQuantUtils.disable_lora_adapters"]], "enable_adapter_and_load_weights() (aimet_torch.peft.peftquantutils method)": [[64, "aimet_torch.peft.PeftQuantUtils.enable_adapter_and_load_weights"]], "export_adapter_weights() (aimet_torch.peft.peftquantutils method)": [[64, "aimet_torch.peft.PeftQuantUtils.export_adapter_weights"]], "freeze_base_model() (aimet_torch.peft.peftquantutils method)": [[64, "aimet_torch.peft.PeftQuantUtils.freeze_base_model"]], "freeze_base_model_activation_quantizers() (aimet_torch.peft.peftquantutils method)": [[64, "aimet_torch.peft.PeftQuantUtils.freeze_base_model_activation_quantizers"]], "freeze_base_model_param_quantizers() (aimet_torch.peft.peftquantutils method)": [[64, "aimet_torch.peft.PeftQuantUtils.freeze_base_model_param_quantizers"]], "get_fp_lora_layer() (aimet_torch.peft.peftquantutils method)": [[64, "aimet_torch.peft.PeftQuantUtils.get_fp_lora_layer"]], "get_quantized_lora_layer() (aimet_torch.peft.peftquantutils method)": [[64, "aimet_torch.peft.PeftQuantUtils.get_quantized_lora_layer"]], "quantize_lora_scale_with_fixed_range() (aimet_torch.peft.peftquantutils method)": [[64, "aimet_torch.peft.PeftQuantUtils.quantize_lora_scale_with_fixed_range"]], "replace_lora_layers_with_quantizable_layers() (aimet_torch.peft method)": [[64, "aimet_torch.peft.replace_lora_layers_with_quantizable_layers"]], "set_bitwidth_for_lora_adapters() (aimet_torch.peft.peftquantutils method)": [[64, "aimet_torch.peft.PeftQuantUtils.set_bitwidth_for_lora_adapters"]], "track_lora_meta_data() (aimet_torch.peft method)": [[64, "aimet_torch.peft.track_lora_meta_data"]], "clssetinfo (class in aimet_torch.cross_layer_equalization)": [[65, "aimet_torch.cross_layer_equalization.ClsSetInfo"]], "clssetinfo.clssetlayerpairinfo (class in aimet_torch.cross_layer_equalization)": [[65, "aimet_torch.cross_layer_equalization.ClsSetInfo.ClsSetLayerPairInfo"]], "bias_fold() (in module aimet_torch.cross_layer_equalization.highbiasfold)": [[65, "aimet_torch.cross_layer_equalization.HighBiasFold.bias_fold"], [65, "id0"]], "fold_all_batch_norms() (in module aimet_torch.batch_norm_fold)": [[65, "aimet_torch.batch_norm_fold.fold_all_batch_norms"]], "fold_given_batch_norms() (in module aimet_torch.batch_norm_fold)": [[65, "aimet_torch.batch_norm_fold.fold_given_batch_norms"]], "scale_cls_sets() (in module aimet_torch.cross_layer_equalization.crosslayerscaling)": [[65, "aimet_torch.cross_layer_equalization.CrossLayerScaling.scale_cls_sets"]], "scale_model() (in module aimet_torch.cross_layer_equalization.crosslayerscaling)": [[65, "aimet_torch.cross_layer_equalization.CrossLayerScaling.scale_model"]], "callbackfunc (class in aimet_common.utils)": [[66, "aimet_common.utils.CallbackFunc"]], "quantanalyzer (class in aimet_torch.v1.quant_analyzer)": [[66, "aimet_torch.v1.quant_analyzer.QuantAnalyzer"]], "analyze() (aimet_torch.v1.quant_analyzer.quantanalyzer method)": [[66, "aimet_torch.v1.quant_analyzer.QuantAnalyzer.analyze"]], "check_model_sensitivity_to_quantization() (aimet_torch.v1.quant_analyzer.quantanalyzer method)": [[66, "aimet_torch.v1.quant_analyzer.QuantAnalyzer.check_model_sensitivity_to_quantization"]], "enable_per_layer_mse_loss() (aimet_torch.v1.quant_analyzer.quantanalyzer method)": [[66, "aimet_torch.v1.quant_analyzer.QuantAnalyzer.enable_per_layer_mse_loss"]], "export_per_layer_encoding_min_max_range() (aimet_torch.v1.quant_analyzer.quantanalyzer method)": [[66, "aimet_torch.v1.quant_analyzer.QuantAnalyzer.export_per_layer_encoding_min_max_range"]], "export_per_layer_mse_loss() (aimet_torch.v1.quant_analyzer.quantanalyzer method)": [[66, "aimet_torch.v1.quant_analyzer.QuantAnalyzer.export_per_layer_mse_loss"]], "export_per_layer_stats_histogram() (aimet_torch.v1.quant_analyzer.quantanalyzer method)": [[66, "aimet_torch.v1.quant_analyzer.QuantAnalyzer.export_per_layer_stats_histogram"]], "perform_per_layer_analysis_by_disabling_quant_wrappers() (aimet_torch.v1.quant_analyzer.quantanalyzer method)": [[66, "aimet_torch.v1.quant_analyzer.QuantAnalyzer.perform_per_layer_analysis_by_disabling_quant_wrappers"]], "perform_per_layer_analysis_by_enabling_quant_wrappers() (aimet_torch.v1.quant_analyzer.quantanalyzer method)": [[66, "aimet_torch.v1.quant_analyzer.QuantAnalyzer.perform_per_layer_analysis_by_enabling_quant_wrappers"]], "quantizationsimmodel (class in aimet_torch.v1.quantsim)": [[68, "aimet_torch.v1.quantsim.QuantizationSimModel"]], "compute_encodings() (aimet_torch.v1.quantsim.quantizationsimmodel method)": [[68, "aimet_torch.v1.quantsim.QuantizationSimModel.compute_encodings"]], "export() (aimet_torch.v1.quantsim.quantizationsimmodel method)": [[68, "aimet_torch.v1.quantsim.QuantizationSimModel.export"]], "load_checkpoint() (aimet_torch.v1.quantsim method)": [[68, "aimet_torch.v1.quantsim.load_checkpoint"]], "save_checkpoint() (aimet_torch.v1.quantsim method)": [[68, "aimet_torch.v1.quantsim.save_checkpoint"]], "scatterdense (class in aimet_torch.nn.modules.custom)": [[69, "aimet_torch.nn.modules.custom.ScatterDense"]], "sparsetensorwrapper (class in aimet_torch.nn.modules.custom)": [[69, "aimet_torch.nn.modules.custom.SparseTensorWrapper"]], "visualizecompression (class in aimet_torch.visualize_serialized_data)": [[70, "aimet_torch.visualize_serialized_data.VisualizeCompression"]], "display_comp_ratio_plot() (aimet_torch.visualize_serialized_data.visualizecompression method)": [[70, "aimet_torch.visualize_serialized_data.VisualizeCompression.display_comp_ratio_plot"]], "display_eval_scores() (aimet_torch.visualize_serialized_data.visualizecompression method)": [[70, "aimet_torch.visualize_serialized_data.VisualizeCompression.display_eval_scores"]], "visualize_changes_after_optimization() (in module aimet_torch.visualize_model)": [[71, "aimet_torch.visualize_model.visualize_changes_after_optimization"]], "visualize_relative_weight_ranges_to_identify_problematic_layers() (in module aimet_torch.visualize_model)": [[71, "aimet_torch.visualize_model.visualize_relative_weight_ranges_to_identify_problematic_layers"]], "visualize_weight_ranges() (in module aimet_torch.visualize_model)": [[71, "aimet_torch.visualize_model.visualize_weight_ranges"]], "quantizationmixin (class in aimet_torch.v2.nn)": [[77, "aimet_torch.v2.nn.QuantizationMixin"], [88, "aimet_torch.v2.nn.QuantizationMixin"]], "__quant_init__() (aimet_torch.v2.nn.quantizationmixin method)": [[77, "aimet_torch.v2.nn.QuantizationMixin.__quant_init__"], [88, "aimet_torch.v2.nn.QuantizationMixin.__quant_init__"]], "compute_encodings() (aimet_torch.v2.nn.quantizationmixin method)": [[77, "aimet_torch.v2.nn.QuantizationMixin.compute_encodings"], [88, "aimet_torch.v2.nn.QuantizationMixin.compute_encodings"]], "forward() (aimet_torch.v2.nn.quantizationmixin method)": [[77, "aimet_torch.v2.nn.QuantizationMixin.forward"], [88, "aimet_torch.v2.nn.QuantizationMixin.forward"]], "from_module() (aimet_torch.v2.nn.quantizationmixin class method)": [[77, "aimet_torch.v2.nn.QuantizationMixin.from_module"]], "get_default_kernel() (aimet_torch.v2.nn.quantizationmixin class method)": [[77, "aimet_torch.v2.nn.QuantizationMixin.get_default_kernel"]], "get_kernel() (aimet_torch.v2.nn.quantizationmixin method)": [[77, "aimet_torch.v2.nn.QuantizationMixin.get_kernel"]], "implements() (aimet_torch.v2.nn.quantizationmixin class method)": [[77, "aimet_torch.v2.nn.QuantizationMixin.implements"]], "input_quantizers (aimet_torch.v2.nn.quantizationmixin attribute)": [[77, "aimet_torch.v2.nn.QuantizationMixin.input_quantizers"], [88, "aimet_torch.v2.nn.QuantizationMixin.input_quantizers"]], "output_quantizers (aimet_torch.v2.nn.quantizationmixin attribute)": [[77, "aimet_torch.v2.nn.QuantizationMixin.output_quantizers"], [88, "aimet_torch.v2.nn.QuantizationMixin.output_quantizers"]], "param_quantizers (aimet_torch.v2.nn.quantizationmixin attribute)": [[77, "aimet_torch.v2.nn.QuantizationMixin.param_quantizers"], [88, "aimet_torch.v2.nn.QuantizationMixin.param_quantizers"]], "set_default_kernel() (aimet_torch.v2.nn.quantizationmixin class method)": [[77, "aimet_torch.v2.nn.QuantizationMixin.set_default_kernel"]], "set_kernel() (aimet_torch.v2.nn.quantizationmixin method)": [[77, "aimet_torch.v2.nn.QuantizationMixin.set_kernel"]], "quantize (class in aimet_torch.v2.quantization.affine)": [[78, "aimet_torch.v2.quantization.affine.Quantize"]], "quantizedequantize (class in aimet_torch.v2.quantization.affine)": [[78, "aimet_torch.v2.quantization.affine.QuantizeDequantize"]], "aimet_torch.v2.quantization.affine": [[78, "module-aimet_torch.v2.quantization.affine"]], "dequantize() (in module aimet_torch.v2.quantization.affine)": [[78, "aimet_torch.v2.quantization.affine.dequantize"]], "module": [[78, "module-aimet_torch.v2.quantization.affine"], [80, "module-aimet_torch.v2.quantization.float"]], "quantize() (in module aimet_torch.v2.quantization.affine)": [[78, "aimet_torch.v2.quantization.affine.quantize"]], "quantize_dequantize() (in module aimet_torch.v2.quantization.affine)": [[78, "aimet_torch.v2.quantization.affine.quantize_dequantize"]], "floatquantizedequantize (class in aimet_torch.v2.quantization.float)": [[79, "aimet_torch.v2.quantization.float.FloatQuantizeDequantize"], [80, "aimet_torch.v2.quantization.float.FloatQuantizeDequantize"]], "quantizedequantize (class in aimet_torch.v2.quantization.float)": [[79, "aimet_torch.v2.quantization.float.QuantizeDequantize"], [80, "aimet_torch.v2.quantization.float.QuantizeDequantize"]], "aimet_torch.v2.quantization.float": [[80, "module-aimet_torch.v2.quantization.float"]], "dequantizedtensor (class in aimet_torch.v2.quantization.tensor)": [[81, "aimet_torch.v2.quantization.tensor.DequantizedTensor"]], "quantizedtensor (class in aimet_torch.v2.quantization.tensor)": [[81, "aimet_torch.v2.quantization.tensor.QuantizedTensor"]], "dequantize() (aimet_torch.v2.quantization.tensor.dequantizedtensor method)": [[81, "aimet_torch.v2.quantization.tensor.DequantizedTensor.dequantize"]], "dequantize() (aimet_torch.v2.quantization.tensor.quantizedtensor method)": [[81, "aimet_torch.v2.quantization.tensor.QuantizedTensor.dequantize"]], "quantize() (aimet_torch.v2.quantization.tensor.dequantizedtensor method)": [[81, "aimet_torch.v2.quantization.tensor.DequantizedTensor.quantize"]], "quantize() (aimet_torch.v2.quantization.tensor.quantizedtensor method)": [[81, "aimet_torch.v2.quantization.tensor.QuantizedTensor.quantize"]], "quantized_repr() (aimet_torch.v2.quantization.tensor.dequantizedtensor method)": [[81, "aimet_torch.v2.quantization.tensor.DequantizedTensor.quantized_repr"]], "quantized_repr() (aimet_torch.v2.quantization.tensor.quantizedtensor method)": [[81, "aimet_torch.v2.quantization.tensor.QuantizedTensor.quantized_repr"]], "visualize_stats() (in module aimet_torch.v2.visualization_tools)": [[82, "aimet_torch.v2.visualization_tools.visualize_stats"]], "set_activation_quantizers_to_float() (in module aimet_torch.v2.quantsim.config_utils)": [[83, "aimet_torch.v2.quantsim.config_utils.set_activation_quantizers_to_float"]], "set_blockwise_quantization_for_weights() (in module aimet_torch.v2.quantsim.config_utils)": [[83, "aimet_torch.v2.quantsim.config_utils.set_blockwise_quantization_for_weights"]], "set_grouped_blockwise_quantization_for_weights() (in module aimet_torch.v2.quantsim.config_utils)": [[83, "aimet_torch.v2.quantsim.config_utils.set_grouped_blockwise_quantization_for_weights"]], "encodinganalyzer (class in aimet_torch.v2.quantization.encoding_analyzer)": [[84, "aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer"]], "minmaxencodinganalyzer (class in aimet_torch.v2.quantization.encoding_analyzer)": [[84, "aimet_torch.v2.quantization.encoding_analyzer.MinMaxEncodingAnalyzer"]], "percentileencodinganalyzer (class in aimet_torch.v2.quantization.encoding_analyzer)": [[84, "aimet_torch.v2.quantization.encoding_analyzer.PercentileEncodingAnalyzer"]], "sqnrencodinganalyzer (class in aimet_torch.v2.quantization.encoding_analyzer)": [[84, "aimet_torch.v2.quantization.encoding_analyzer.SqnrEncodingAnalyzer"]], "compute_encodings() (aimet_torch.v2.quantization.encoding_analyzer.encodinganalyzer method)": [[84, "aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.compute_encodings"]], "reset_stats() (aimet_torch.v2.quantization.encoding_analyzer.encodinganalyzer method)": [[84, "aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.reset_stats"]], "update_stats() (aimet_torch.v2.quantization.encoding_analyzer.encodinganalyzer method)": [[84, "aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.update_stats"]], "gptvqparameters (class in aimet_torch.gptvq.defs)": [[86, "aimet_torch.gptvq.defs.GPTVQParameters"]], "apply_gptvq() (in module aimet_torch.gptvq.gptvq_weight.gptvq)": [[86, "aimet_torch.gptvq.gptvq_weight.GPTVQ.apply_gptvq"]], "quantize (class in aimet_torch.v2.quantization.affine.quantizer)": [[89, "aimet_torch.v2.quantization.affine.quantizer.Quantize"]], "quantizedequantize (class in aimet_torch.v2.quantization.affine.quantizer)": [[89, "aimet_torch.v2.quantization.affine.quantizer.QuantizeDequantize"]], "quantizerbase (class in aimet_torch.v2.quantization.affine.quantizer)": [[89, "aimet_torch.v2.quantization.affine.quantizer.QuantizerBase"]], "allow_overwrite() (aimet_torch.v2.quantization.affine.quantizer.quantizerbase method)": [[89, "aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.allow_overwrite"]], "compute_encodings() (aimet_torch.v2.quantization.affine.quantizer.quantizerbase method)": [[89, "aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.compute_encodings"]], "forward() (aimet_torch.v2.quantization.affine.quantizer.quantize method)": [[89, "aimet_torch.v2.quantization.affine.quantizer.Quantize.forward"]], "forward() (aimet_torch.v2.quantization.affine.quantizer.quantizedequantize method)": [[89, "aimet_torch.v2.quantization.affine.quantizer.QuantizeDequantize.forward"]], "get_encoding() (aimet_torch.v2.quantization.affine.quantizer.quantizerbase method)": [[89, "aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.get_encoding"]], "get_legacy_encodings() (aimet_torch.v2.quantization.affine.quantizer.quantizerbase method)": [[89, "aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.get_legacy_encodings"]], "is_initialized() (aimet_torch.v2.quantization.affine.quantizer.quantizerbase method)": [[89, "aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.is_initialized"]], "register_quantization_parameter() (aimet_torch.v2.quantization.affine.quantizer.quantizerbase method)": [[89, "aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.register_quantization_parameter"]], "set_legacy_encodings() (aimet_torch.v2.quantization.affine.quantizer.quantizerbase method)": [[89, "aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.set_legacy_encodings"]]}})
\ No newline at end of file
+Search.setIndex({"docnames": ["Examples/onnx/quantization/AMP", "Examples/onnx/quantization/adaround", "Examples/onnx/quantization/cle", "Examples/onnx/quantization/quantsim", "Examples/tensorflow/quantization/keras/KerasAMP", "Examples/tensorflow/quantization/keras/adaround", "Examples/tensorflow/quantization/keras/autoquant", "Examples/tensorflow/quantization/keras/bn_reestimation", "Examples/tensorflow/quantization/keras/keras_transformer_qat", "Examples/tensorflow/quantization/keras/model_preparer", "Examples/tensorflow/quantization/keras/qat", "Examples/tensorflow/quantization/keras/qat_range_learning", "Examples/tensorflow/quantization/keras/quant_analyzer", "Examples/tensorflow/quantization/keras/quantsim_adaround_pcq", "Examples/tensorflow/quantization/keras/quantsim_cle", "Examples/torch/compression/channel_pruning", "Examples/torch/compression/spatial_svd", "Examples/torch/compression/spatial_svd_channel_pruning", "Examples/torch/quantization/AMP", "Examples/torch/quantization/adaround", "Examples/torch/quantization/autoquant", "Examples/torch/quantization/bn_reestimation", "Examples/torch/quantization/cle_bc", "Examples/torch/quantization/qat", "Examples/torch/quantization/qat_range_learning", "Examples/torch/quantization/quant_analyzer", "api_docs/index", "api_docs/keras", "api_docs/keras_adaround", "api_docs/keras_batchnorm_re_estimation", "api_docs/keras_compression", "api_docs/keras_cross_layer_equalization", "api_docs/keras_layer_output_generation", "api_docs/keras_mixed_precision", "api_docs/keras_model_guidelines", "api_docs/keras_model_preparer", "api_docs/keras_primitive_apis_cle", "api_docs/keras_quant_analyzer", "api_docs/keras_quantization", "api_docs/keras_quantsim", "api_docs/onnx", "api_docs/onnx_adaround", "api_docs/onnx_auto_quant", "api_docs/onnx_cross_layer_equalization", "api_docs/onnx_layer_output_generation", "api_docs/onnx_mixed_precision", "api_docs/onnx_quant_analyzer", "api_docs/onnx_quantization", "api_docs/onnx_quantsim", "api_docs/quantization_encoding_specification", "api_docs/torch", "api_docs/torch_adaround", "api_docs/torch_architecture_checker", "api_docs/torch_auto_quant", "api_docs/torch_batchnorm_re_estimation", "api_docs/torch_bias_correction", "api_docs/torch_compress", "api_docs/torch_cross_layer_equalization", "api_docs/torch_layer_output_generation", "api_docs/torch_mixed_precision", "api_docs/torch_model_guidelines", "api_docs/torch_model_preparer", "api_docs/torch_model_validator", "api_docs/torch_multi_gpu", "api_docs/torch_peft_lora", "api_docs/torch_primitive_apis_cle", "api_docs/torch_quant_analyzer", "api_docs/torch_quantization", "api_docs/torch_quantsim", "api_docs/torch_spconv_custom_onnx_export", "api_docs/torch_visualization_compression", "api_docs/torch_visualization_quantization", "api_docs/v2_migrgation_guide", "install/index", "install/install_docker", "install/install_host", "toplevelhidden", "torch_docs/api/nn.quantization_mixin", "torch_docs/api/quantization/affine/index", "torch_docs/api/quantization/float/FloatQuantizeDequantize", "torch_docs/api/quantization/float/index", "torch_docs/api/quantization/tensor", "torch_docs/api/visualization_tools", "torch_docs/blockwise_quantization", "torch_docs/encoding_analyzer", "torch_docs/examples/ptq", "torch_docs/gptvq", "torch_docs/index", "torch_docs/quantized_modules", "torch_docs/quantizer", "torch_docs/tutorials/quickstart_guide", "user_guide/adaround", "user_guide/auto_quant", "user_guide/bn_reestimation", "user_guide/channel_pruning", "user_guide/compression_feature_guidebook", "user_guide/examples", "user_guide/greedy_compression_ratio_selection", "user_guide/index", "user_guide/known_issues", "user_guide/model_compression", "user_guide/model_guidelines", "user_guide/model_quantization", "user_guide/post_training_quant_techniques", "user_guide/quant_analyzer", "user_guide/quantization_aware_training", "user_guide/quantization_configuration", "user_guide/quantization_feature_guidebook", "user_guide/quantization_sim", "user_guide/release_notes", "user_guide/spatial_svd", "user_guide/visualization_compression", "user_guide/visualization_quant", "user_guide/weight_svd", "user_guide/winnowing"], "filenames": ["Examples/onnx/quantization/AMP.ipynb", "Examples/onnx/quantization/adaround.ipynb", "Examples/onnx/quantization/cle.ipynb", "Examples/onnx/quantization/quantsim.ipynb", "Examples/tensorflow/quantization/keras/KerasAMP.ipynb", "Examples/tensorflow/quantization/keras/adaround.ipynb", "Examples/tensorflow/quantization/keras/autoquant.ipynb", "Examples/tensorflow/quantization/keras/bn_reestimation.ipynb", "Examples/tensorflow/quantization/keras/keras_transformer_qat.ipynb", "Examples/tensorflow/quantization/keras/model_preparer.ipynb", "Examples/tensorflow/quantization/keras/qat.ipynb", "Examples/tensorflow/quantization/keras/qat_range_learning.ipynb", "Examples/tensorflow/quantization/keras/quant_analyzer.ipynb", "Examples/tensorflow/quantization/keras/quantsim_adaround_pcq.ipynb", "Examples/tensorflow/quantization/keras/quantsim_cle.ipynb", "Examples/torch/compression/channel_pruning.ipynb", "Examples/torch/compression/spatial_svd.ipynb", "Examples/torch/compression/spatial_svd_channel_pruning.ipynb", "Examples/torch/quantization/AMP.ipynb", "Examples/torch/quantization/adaround.ipynb", "Examples/torch/quantization/autoquant.ipynb", "Examples/torch/quantization/bn_reestimation.ipynb", "Examples/torch/quantization/cle_bc.ipynb", "Examples/torch/quantization/qat.ipynb", "Examples/torch/quantization/qat_range_learning.ipynb", "Examples/torch/quantization/quant_analyzer.ipynb", "api_docs/index.rst", "api_docs/keras.rst", "api_docs/keras_adaround.rst", "api_docs/keras_batchnorm_re_estimation.rst", "api_docs/keras_compression.rst", "api_docs/keras_cross_layer_equalization.rst", "api_docs/keras_layer_output_generation.rst", "api_docs/keras_mixed_precision.rst", "api_docs/keras_model_guidelines.rst", "api_docs/keras_model_preparer.rst", "api_docs/keras_primitive_apis_cle.rst", "api_docs/keras_quant_analyzer.rst", "api_docs/keras_quantization.rst", "api_docs/keras_quantsim.rst", "api_docs/onnx.rst", "api_docs/onnx_adaround.rst", "api_docs/onnx_auto_quant.rst", "api_docs/onnx_cross_layer_equalization.rst", "api_docs/onnx_layer_output_generation.rst", "api_docs/onnx_mixed_precision.rst", "api_docs/onnx_quant_analyzer.rst", "api_docs/onnx_quantization.rst", "api_docs/onnx_quantsim.rst", "api_docs/quantization_encoding_specification.rst", "api_docs/torch.rst", "api_docs/torch_adaround.rst", "api_docs/torch_architecture_checker.rst", "api_docs/torch_auto_quant.rst", "api_docs/torch_batchnorm_re_estimation.rst", "api_docs/torch_bias_correction.rst", "api_docs/torch_compress.rst", "api_docs/torch_cross_layer_equalization.rst", "api_docs/torch_layer_output_generation.rst", "api_docs/torch_mixed_precision.rst", "api_docs/torch_model_guidelines.rst", "api_docs/torch_model_preparer.rst", "api_docs/torch_model_validator.rst", "api_docs/torch_multi_gpu.rst", "api_docs/torch_peft_lora.rst", "api_docs/torch_primitive_apis_cle.rst", "api_docs/torch_quant_analyzer.rst", "api_docs/torch_quantization.rst", "api_docs/torch_quantsim.rst", "api_docs/torch_spconv_custom_onnx_export.rst", "api_docs/torch_visualization_compression.rst", "api_docs/torch_visualization_quantization.rst", "api_docs/v2_migrgation_guide.rst", "install/index.rst", "install/install_docker.rst", "install/install_host.rst", "toplevelhidden.rst", "torch_docs/api/nn.quantization_mixin.rst", "torch_docs/api/quantization/affine/index.rst", "torch_docs/api/quantization/float/FloatQuantizeDequantize.rst", "torch_docs/api/quantization/float/index.rst", "torch_docs/api/quantization/tensor.rst", "torch_docs/api/visualization_tools.rst", "torch_docs/blockwise_quantization.rst", "torch_docs/encoding_analyzer.rst", "torch_docs/examples/ptq.rst", "torch_docs/gptvq.rst", "torch_docs/index.rst", "torch_docs/quantized_modules.rst", "torch_docs/quantizer.rst", "torch_docs/tutorials/quickstart_guide.rst", "user_guide/adaround.rst", "user_guide/auto_quant.rst", "user_guide/bn_reestimation.rst", "user_guide/channel_pruning.rst", "user_guide/compression_feature_guidebook.rst", "user_guide/examples.rst", "user_guide/greedy_compression_ratio_selection.rst", "user_guide/index.rst", "user_guide/known_issues.rst", "user_guide/model_compression.rst", "user_guide/model_guidelines.rst", "user_guide/model_quantization.rst", "user_guide/post_training_quant_techniques.rst", "user_guide/quant_analyzer.rst", "user_guide/quantization_aware_training.rst", "user_guide/quantization_configuration.rst", "user_guide/quantization_feature_guidebook.rst", "user_guide/quantization_sim.rst", "user_guide/release_notes.rst", "user_guide/spatial_svd.rst", "user_guide/visualization_compression.rst", "user_guide/visualization_quant.rst", "user_guide/weight_svd.rst", "user_guide/winnowing.rst"], "titles": ["Automatic Mixed-Precision (AMP)", "Adaptive Rounding (AdaRound)", "Cross-Layer Equalization", "Quantization simulation", "Automatic Mixed-Precision (AMP)", "Adaptive Rounding (AdaRound)", "AutoQuant", "Quantization-Aware Training with BatchNorm Re-estimation", "Quantization-Aware Training with a Keras Transformer Model", "Keras Model Preparer", "Quantization-aware training", "Quantization-Aware training with range learning", "Quant Analyzer", "Quantsim and Adaround - Per Channel Quantization (PCQ)", "Cross-Layer Equalization with QuantSim", "Model compression using channel pruning", "Model compression using spatial SVD", "Model compression using spatial SVD and channel pruning", "Automatic Mixed-Precision (AMP)", "Adaptive Rounding (AdaRound)", "AutoQuant", "Quantization-Aware Training with BatchNorm Re-estimation", "Cross-Layer Equalization and Bias Correction", "Quantization-aware training", "Quantization-aware training with range learning", "Quant Analyzer", "Welcome to AI Model Efficiency Toolkit API Docs!", "AIMET TensorFlow APIs", "AIMET TensorFlow AdaRound API", "AIMET TensorFlow BatchNorm Re-estimation APIs", "AIMET TensorFlow Compression API", "AIMET TensorFlow Cross Layer Equalization APIs", "AIMET TensorFlow Layer Output Generation API", "AIMET TensorFlow Mixed Precision API", "TensorFlow Model Guidelines", "TensorFlow Model Preparer API", "AIMET TensorFlow Cross Layer Equalization Primitive API", "AIMET TensorFlow Quant Analyzer API", "AIMET TensorFlow Quantization APIs", "AIMET TensorFlow Quantization SIM API", "AIMET ONNX APIs", "AIMET ONNX AdaRound API", "AIMET ONNX AutoQuant API", "AIMET ONNX Cross Layer Equalization APIs", "AIMET ONNX Layer Output Generation API", "AIMET ONNX Mixed Precision API", "AIMET ONNX Quant Analyzer API", "AIMET ONNX Quantization APIs", "AIMET ONNX Quantization SIM API", "Encoding Format Specification", "AIMET PyTorch APIs", "AIMET PyTorch AdaRound API", "Architecture Checker API", "AIMET PyTorch AutoQuant API", "AIMET PyTorch BatchNorm Re-estimation APIs", "AIMET PyTorch Bias Correction API", "AIMET PyTorch Compression API", "AIMET PyTorch Cross Layer Equalization APIs", "AIMET PyTorch Layer Output Generation API", "AIMET PyTorch Mixed Precision API", "PyTorch Model Guidelines", "Model Preparer API", "Model Validator Utility", "PyTorch Multi-GPU support", "PEFT LoRA", "AIMET PyTorch Cross Layer Equalization Primitive API", "AIMET PyTorch Quant Analyzer API", "AIMET PyTorch Quantization APIs", "AIMET PyTorch Quantization SIM API", "AIMET Torch SparseConvolution custom onnx export", "AIMET Visualization Compression API", "AIMET Visualization for Quantization API", "Migrate to aimet_torch.v2", "AIMET Installation", "AIMET Installation in Docker", "AIMET Installation and Setup", "&lt;no title&gt;", "QuantizationMixin", "quantization.affine", "FloatQuantizeDequantize", "quantization.float", "quantization.tensor", "Visualization Tools", "Blockwise Quantization", "Encoding Analyzers", "Post-Training Quantization", "GPTVQ", "AIMET: AI Model Efficiency Toolkit Documentation", "Quantized Modules", "Quantizers", "Quickstart Guide", "AIMET AdaRound", "AIMET AutoQuant", "AIMET Batch Norm Re-estimation", "AIMET channel pruning", "AIMET Compression Features Guidebook", "AIMET examples", "AIMET greedy compression ratio selection", "AI Model Efficiency Toolkit User Guide", "AIMET Known Issues", "AIMET model compression", "Model Guidelines for PyTorch", "AIMET model quantization", "AIMET post-training quantization techniques", "AIMET QuantAnalyzer", "AIMET quantization aware training", "Quantization simulation configuration", "AIMET quantization diagnostics", "AIMET quantization simulation", "AIMET Release Notes", "AIMET spatial SVD", "AIMET visualization", "AIMET visualization for quantization", "AIMET weight SVD", "AIMET winnowing"], "terms": {"show": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 29, 31, 41, 45, 51, 52, 53, 54, 57, 59, 62, 64, 66, 68, 71, 83, 86, 87, 90, 93, 97, 98, 103, 107], "work": [0, 1, 3, 4, 5, 6, 7, 8, 10, 11, 12, 15, 16, 17, 18, 19, 20, 21, 23, 24, 25, 26, 33, 39, 41, 48, 51, 62, 63, 68, 83, 96, 100, 103], "code": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 18, 19, 20, 21, 22, 23, 24, 25, 83, 90, 91], "how": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 29, 31, 33, 41, 45, 48, 49, 51, 52, 53, 54, 55, 57, 59, 62, 64, 66, 67, 68, 69, 72, 83, 86, 88, 90, 96, 100, 102, 103, 104, 106, 107, 108, 110, 113], "us": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 18, 19, 20, 21, 22, 23, 24, 25, 26, 28, 29, 30, 31, 32, 33, 34, 35, 37, 38, 39, 41, 42, 43, 44, 45, 46, 48, 49, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 72, 73, 75, 77, 78, 81, 82, 83, 84, 86, 87, 88, 89, 90, 93, 95, 96, 98, 101, 103, 104, 105, 106, 107, 108, 109, 111, 112], "aimet": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 34, 35, 49, 52, 60, 61, 62, 63, 64, 72, 77, 86, 88, 90, 98, 101, 106], "perform": [0, 1, 2, 3, 4, 5, 6, 8, 12, 13, 14, 15, 16, 17, 18, 19, 20, 22, 25, 28, 29, 31, 33, 37, 41, 42, 43, 45, 46, 49, 51, 52, 54, 55, 56, 57, 59, 63, 64, 65, 66, 67, 68, 71, 77, 78, 83, 86, 88, 89, 90, 92, 93, 94, 95, 97, 100, 102, 103, 104, 105, 107], "auto": [0, 4, 15, 16, 17, 18, 26, 30, 31, 36, 42, 43, 45, 48, 49, 56, 57, 59, 65, 70], "techniqu": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 23, 24, 28, 30, 31, 38, 41, 42, 43, 47, 51, 53, 55, 56, 57, 66, 67, 87, 90, 92, 94, 95, 96, 98, 102, 104, 105, 107, 108, 109, 110, 113], "where": [0, 1, 2, 3, 4, 5, 6, 7, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 30, 33, 39, 41, 45, 49, 51, 56, 59, 60, 61, 64, 68, 78, 79, 80, 86, 89, 90, 93, 97, 104, 110, 111, 113, 114], "given": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 30, 31, 33, 36, 39, 42, 43, 45, 48, 49, 51, 53, 54, 56, 57, 59, 65, 68, 69, 77, 82, 83, 84, 88, 92, 97, 100, 103], "target": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 30, 32, 35, 39, 42, 44, 48, 49, 51, 54, 56, 58, 59, 64, 68, 87, 93, 95, 97, 98, 100, 102, 107, 108, 109], "find": [0, 1, 5, 6, 7, 8, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 22, 23, 24, 33, 36, 45, 51, 55, 59, 62, 65, 68, 71, 97, 102, 104, 105, 108], "bit": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 33, 41, 45, 46, 49, 51, 59, 66, 73, 79, 80, 83, 90, 91, 93, 102, 107, 108, 109], "per": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 30, 37, 45, 46, 49, 54, 56, 58, 59, 64, 66, 68, 83, 86, 88, 93, 103, 104, 106, 107, 108, 109, 111], "meet": [0, 4, 18, 42, 53, 59, 73, 92, 95, 97], "while": [0, 1, 2, 3, 4, 5, 8, 10, 11, 13, 14, 15, 16, 17, 18, 19, 22, 23, 24, 30, 51, 56, 64, 83, 88, 91, 97, 101, 105, 107], "try": [0, 1, 2, 3, 4, 13, 15, 16, 17, 18, 30, 52, 56, 70, 92, 94, 95, 100, 102, 107], "optim": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 30, 33, 37, 38, 39, 41, 42, 45, 47, 48, 51, 52, 53, 56, 59, 67, 68, 70, 71, 83, 86, 90, 91, 92, 98, 100, 102, 105, 108, 109, 111], "infer": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 30, 33, 38, 39, 41, 42, 46, 47, 48, 49, 51, 67, 68, 69, 83, 86, 87, 90, 93, 95, 98, 103, 105, 108, 109], "speed": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 30, 51, 56, 64, 91, 100, 103, 105, 109], "As": [0, 2, 4, 7, 8, 10, 11, 13, 14, 15, 16, 17, 18, 21, 22, 23, 24, 60, 68, 77, 83, 86, 92, 95, 97, 103, 104, 108], "sai": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 61, 95], "particular": [0, 4, 18, 83, 102, 106], "desir": [0, 4, 15, 16, 17, 18, 30, 39, 46, 56, 66, 68, 74, 83, 90, 95, 100, 102, 107], "when": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 30, 33, 34, 35, 37, 38, 39, 42, 43, 45, 46, 49, 56, 57, 59, 60, 61, 66, 67, 68, 77, 83, 86, 87, 88, 90, 91, 100, 102, 103, 104, 105, 106, 107, 108, 111, 112, 114], "int8": [0, 1, 2, 3, 4, 13, 18, 19, 22, 23, 24, 51, 81, 105, 108, 112], "The": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 28, 29, 30, 32, 33, 35, 36, 37, 39, 41, 43, 44, 45, 46, 48, 49, 51, 52, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 68, 69, 72, 73, 74, 75, 77, 78, 79, 80, 81, 82, 83, 84, 86, 87, 88, 90, 91, 92, 93, 94, 95, 96, 97, 98, 100, 101, 102, 103, 104, 105, 106, 107, 108, 110, 111, 112, 113, 114], "featur": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 34, 35, 36, 38, 43, 49, 51, 57, 60, 61, 62, 63, 65, 67, 68, 69, 72, 82, 83, 86, 91, 92, 93, 96, 100, 103, 104, 107, 108, 109, 111, 112], "minim": [0, 3, 4, 10, 11, 18, 23, 24, 28, 51, 68, 87, 98, 102, 108], "set": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 30, 33, 35, 36, 41, 42, 45, 46, 48, 49, 51, 53, 56, 59, 61, 62, 64, 65, 66, 68, 72, 75, 77, 82, 83, 86, 88, 89, 91, 95, 96, 97, 100, 101, 103, 104, 105, 106, 107], "need": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 30, 32, 33, 34, 35, 36, 39, 41, 46, 49, 51, 55, 56, 58, 63, 64, 65, 66, 67, 68, 69, 72, 73, 74, 75, 83, 86, 90, 102, 103, 105, 106, 108, 109, 112], "int16": [0, 4, 18], "get": [0, 1, 2, 3, 4, 7, 8, 9, 12, 30, 32, 33, 36, 44, 45, 52, 56, 58, 59, 61, 64, 68, 71, 73, 74, 75, 86, 100, 112], "It": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 18, 19, 22, 23, 24, 25, 30, 31, 33, 35, 36, 37, 41, 42, 43, 44, 45, 46, 48, 49, 51, 56, 61, 65, 66, 68, 90, 93, 94, 97, 105, 114], "should": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 30, 33, 34, 35, 37, 38, 39, 41, 42, 46, 48, 49, 51, 53, 56, 58, 60, 61, 64, 66, 67, 68, 72, 77, 83, 86, 88, 90, 95], "note": [0, 1, 2, 3, 4, 5, 6, 7, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 33, 35, 36, 37, 39, 41, 42, 43, 44, 45, 46, 48, 53, 56, 57, 59, 63, 64, 65, 66, 68, 69, 72, 74, 75, 83, 86, 90, 98, 111], "choos": [0, 4, 15, 16, 17, 18, 48, 68, 71, 83, 94, 95, 100], "higher": [0, 4, 15, 16, 17, 18, 41, 51, 56, 59, 83, 84, 93, 97, 105, 107], "some": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 22, 23, 24, 25, 30, 35, 36, 38, 39, 51, 56, 61, 65, 67, 68, 71, 74, 75, 88, 90, 91, 95, 97, 101, 102, 103, 105, 107, 108, 114], "necessarili": [0, 4, 18], "involv": [0, 4, 18, 33, 45, 59, 72, 84, 90, 102, 107], "trade": [0, 4, 18, 28, 33, 41, 51], "off": [0, 4, 18, 28, 39, 41, 51, 68, 103], "lower": [0, 4, 13, 18, 33, 41, 51, 72, 83, 97, 102, 107], "sec": [0, 4, 13, 18], "vice": [0, 4, 18, 64, 97, 107, 108], "versa": [0, 4, 18, 64, 97, 107, 108], "altern": [0, 4, 15, 16, 17, 18, 75, 83], "can": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 28, 30, 31, 32, 33, 34, 35, 36, 38, 39, 41, 44, 45, 46, 48, 49, 51, 52, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 74, 78, 81, 83, 86, 87, 88, 89, 90, 92, 93, 95, 97, 98, 100, 102, 103, 104, 105, 106, 107, 108, 111, 112, 114], "gener": [0, 4, 8, 18, 20, 26, 33, 39, 45, 48, 49, 52, 59, 64, 69, 77, 78, 83, 86, 89, 90, 96, 100, 102, 104, 105, 106, 107, 108], "pareto": [0, 4, 18, 33, 45, 59], "curv": [0, 4, 18, 33, 45, 59, 97], "v": [0, 4, 12, 18, 25, 28, 33, 41, 45, 51, 59, 74, 83], "op": [0, 1, 2, 3, 5, 7, 8, 10, 11, 13, 14, 15, 17, 18, 19, 20, 21, 22, 23, 24, 28, 30, 33, 36, 39, 41, 42, 45, 48, 51, 52, 59, 62, 68, 90, 106, 108, 109], "guid": [0, 4, 6, 18, 19, 20, 22, 23, 24, 25, 30, 56, 67, 72, 87, 95, 103, 107, 109], "user": [0, 1, 2, 3, 4, 5, 6, 7, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 29, 30, 33, 34, 35, 36, 37, 38, 45, 46, 48, 49, 54, 56, 59, 60, 61, 63, 65, 67, 70, 71, 72, 74, 77, 83, 86, 87, 91, 95, 100, 104, 107, 109], "decid": [0, 1, 2, 3, 4, 5, 13, 15, 16, 17, 18, 19, 22, 23, 24, 25, 91, 111], "right": [0, 4, 6, 8, 18, 20, 77, 78, 79, 80, 88, 89, 114], "oper": [0, 3, 4, 9, 10, 11, 18, 23, 24, 30, 35, 60, 61, 62, 72, 77, 88, 90, 101, 102, 103, 106, 107], "point": [0, 1, 2, 4, 5, 6, 7, 8, 10, 11, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 33, 35, 36, 37, 38, 45, 46, 47, 49, 55, 59, 64, 65, 66, 67, 68, 72, 77, 81, 83, 87, 98, 102, 104, 107, 108, 112], "tradeoff": [0, 4, 18], "specif": [0, 1, 4, 5, 7, 9, 13, 18, 19, 21, 30, 33, 35, 39, 56, 68, 77, 83, 88, 90, 92, 93, 98, 101, 102, 103, 106, 109], "abov": [0, 4, 12, 13, 15, 16, 17, 18, 25, 28, 37, 46, 51, 56, 61, 63, 66, 68, 74, 75, 83, 86, 87, 100, 103, 108, 111, 114], "cover": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 18, 19, 21, 22, 23, 24, 25, 51, 68, 83, 108], "follow": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 30, 31, 32, 33, 34, 35, 36, 38, 39, 43, 44, 46, 47, 48, 49, 51, 52, 53, 54, 55, 56, 57, 58, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 72, 73, 74, 75, 77, 83, 86, 88, 91, 93, 94, 95, 96, 97, 98, 100, 101, 102, 104, 105, 106, 107, 108, 110, 113, 114], "instanti": [0, 12, 13, 18, 21, 25, 60, 63, 64, 83, 86, 90, 111], "": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 28, 30, 31, 33, 34, 35, 36, 37, 39, 41, 42, 45, 46, 48, 49, 51, 54, 55, 56, 59, 61, 65, 66, 68, 69, 71, 75, 77, 83, 87, 88, 89, 90, 94, 95, 97, 99, 100, 102, 103, 104, 105, 107, 108, 112, 114], "fake": [0, 1, 2, 3, 5, 7, 8, 10, 11, 13, 14, 18, 19, 20, 21, 22, 23, 24, 51, 59, 68, 78, 79, 80, 89, 90], "insert": [0, 1, 2, 3, 5, 7, 8, 10, 11, 13, 14, 15, 17, 18, 19, 21, 22, 23, 24, 51, 61, 68, 102, 108], "design": [0, 4, 9, 12, 13, 18, 25, 26, 62, 67, 103], "state": [0, 1, 2, 3, 4, 5, 6, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 22, 23, 24, 25, 33, 69, 90], "art": [0, 1, 2, 3, 4, 5, 6, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 22, 23, 24, 25, 90], "result": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 30, 33, 35, 37, 42, 45, 46, 51, 53, 56, 59, 66, 68, 77, 81, 83, 84, 86, 91, 92, 94, 95, 98, 100, 103, 104, 105, 106, 108], "For": [0, 4, 7, 8, 9, 12, 13, 18, 21, 25, 28, 29, 30, 31, 32, 34, 35, 44, 46, 48, 51, 53, 54, 56, 57, 58, 60, 61, 62, 63, 64, 66, 67, 68, 71, 72, 73, 74, 75, 77, 83, 86, 87, 88, 90, 91, 94, 95, 96, 97, 98, 99, 100, 102, 104, 106, 108], "rel": [0, 1, 2, 3, 4, 5, 6, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 22, 23, 24, 25, 30, 33, 56, 71, 95, 107, 112], "friendli": [0, 1, 2, 3, 4, 5, 6, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 22, 23, 24, 25, 67, 92, 102, 103], "like": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 29, 31, 35, 36, 45, 51, 57, 59, 65, 68, 72, 83, 86, 87, 90, 92, 98, 100, 102, 104, 105, 106], "resnet18": [0, 1, 2, 3, 5, 6, 10, 11, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 51, 53, 54, 57, 65, 66, 68, 70, 71], "also": [0, 1, 2, 3, 4, 5, 6, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 22, 23, 24, 25, 28, 37, 39, 41, 46, 49, 51, 53, 60, 61, 66, 68, 74, 75, 83, 94, 100, 102, 104, 106, 108, 109, 112, 114], "number": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 28, 29, 30, 33, 35, 37, 39, 41, 45, 46, 48, 51, 54, 55, 56, 59, 61, 66, 68, 74, 77, 78, 79, 80, 83, 84, 88, 91, 97, 98, 100, 105, 108, 109, 111, 114], "sampl": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 30, 33, 36, 37, 39, 41, 45, 46, 48, 49, 51, 53, 55, 59, 66, 68, 82, 87, 88, 90, 94, 103, 104, 105, 108], "ar": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 41, 44, 45, 46, 48, 51, 52, 54, 55, 56, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 72, 73, 74, 75, 77, 78, 79, 80, 83, 84, 86, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 100, 101, 102, 103, 104, 105, 106, 107, 108, 111, 112, 114], "deliber": [0, 4, 12, 13, 18, 25], "chosen": [0, 1, 2, 3, 4, 5, 6, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 22, 23, 24, 25, 96], "have": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 35, 43, 46, 49, 51, 52, 57, 58, 61, 62, 66, 68, 71, 72, 75, 77, 82, 83, 90, 100, 103, 104, 107], "execut": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 33, 42, 45, 51, 53, 59, 61, 70, 75, 90, 96, 111], "more": [0, 4, 7, 8, 9, 12, 13, 18, 21, 25, 28, 30, 31, 36, 37, 39, 41, 42, 43, 46, 48, 49, 51, 52, 53, 55, 56, 57, 59, 62, 65, 66, 67, 68, 72, 73, 83, 86, 87, 88, 90, 94, 95, 97, 100, 102, 103, 104, 106, 107, 108, 111], "quickli": [0, 4, 12, 13, 18, 25], "reli": [0, 1, 2, 3, 4, 7, 8, 12, 13, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 72], "imagenet": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 30, 33, 48, 51, 54, 55, 68, 96], "task": [0, 1, 2, 3, 4, 5, 6, 7, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 49, 111, 112], "imag": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 33, 37, 46, 53, 55, 66, 73, 91, 96, 104], "classif": [0, 1, 2, 3, 4, 5, 6, 7, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 35, 100], "If": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 30, 31, 33, 34, 35, 36, 39, 41, 42, 45, 46, 48, 49, 51, 53, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 70, 71, 72, 74, 75, 77, 78, 79, 80, 83, 86, 88, 89, 90, 91, 92, 95, 97, 101, 102, 103, 104, 106, 107, 111, 112, 114], "you": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 30, 51, 56, 61, 63, 67, 68, 74, 75, 77, 86, 91, 92, 95, 96, 98, 100, 101, 102, 104, 105, 106, 107, 108, 111, 112], "alreadi": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 57, 65, 68, 74, 77, 107], "version": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 44, 51, 61, 67, 68, 72, 73, 74, 75, 77, 82, 83, 86, 88, 90, 96, 98, 105], "readili": [0, 4, 7, 12, 13, 18, 21, 25], "avail": [0, 1, 2, 3, 4, 7, 12, 13, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 31, 51, 53, 61, 66, 68, 73, 90, 101, 104, 106, 107], "pleas": [0, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 18, 21, 25, 26, 28, 29, 30, 31, 37, 39, 41, 42, 43, 46, 51, 53, 54, 55, 56, 57, 62, 64, 66, 67, 68, 69, 72, 73, 75, 87, 90, 103], "els": [0, 1, 2, 3, 4, 5, 7, 10, 11, 12, 13, 14, 18, 19, 21, 22, 23, 24, 25, 30, 33, 36, 42, 45, 54, 59, 61, 62, 90, 103], "download": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 73, 74, 75, 90], "from": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 28, 29, 30, 31, 32, 33, 35, 36, 37, 39, 41, 42, 43, 44, 45, 46, 48, 49, 51, 52, 53, 54, 55, 56, 57, 58, 59, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 73, 77, 78, 79, 80, 81, 83, 84, 86, 88, 89, 90, 91, 94, 95, 96, 97, 98, 100, 101, 102, 103, 104, 105, 106, 107, 108, 114], "appropri": [0, 4, 7, 8, 12, 13, 18, 21, 25, 30, 33, 51, 56, 59, 68, 73, 75, 77, 83, 86, 88, 97, 107], "locat": [0, 4, 7, 12, 13, 18, 21, 25], "e": [0, 4, 7, 12, 13, 18, 21, 25, 28, 33, 37, 38, 39, 41, 45, 46, 48, 49, 51, 55, 59, 66, 68, 90, 93], "g": [0, 4, 7, 12, 13, 18, 21, 25, 28, 33, 37, 39, 41, 46, 48, 49, 51, 66, 68, 74, 90, 93], "http": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 61, 73, 74, 75, 96, 103, 109, 111], "net": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 96], "org": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 61, 73, 74, 75, 96, 103], "challeng": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25], "lsvrc": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25], "2012": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25], "index": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 46, 53, 66, 69, 86, 88, 109], "php": [0, 4, 7, 12, 13, 18, 21, 25, 96], "note1": [0, 18, 21, 25], "typic": [0, 1, 5, 6, 7, 8, 10, 11, 13, 15, 17, 18, 19, 20, 21, 22, 23, 24, 25, 35, 51, 68, 77, 83, 88, 90, 95, 102, 104, 105, 108], "ha": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 35, 36, 37, 41, 43, 46, 51, 52, 56, 57, 59, 61, 62, 64, 65, 66, 68, 71, 72, 77, 81, 83, 86, 90, 95, 97, 102, 103, 105, 108, 111, 114], "characterist": [0, 18, 21, 25], "dataload": [0, 1, 2, 3, 4, 5, 6, 7, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 33, 41, 42, 45, 46, 48, 51, 53, 54, 59, 66, 86, 90, 96, 104], "provid": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 30, 33, 35, 36, 37, 38, 41, 45, 46, 47, 48, 49, 51, 52, 53, 59, 62, 64, 66, 67, 68, 70, 72, 74, 75, 77, 79, 80, 83, 86, 87, 90, 91, 95, 96, 97, 100, 102, 103, 104, 106, 107, 108, 111, 112], "subfold": [0, 1, 2, 3, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25], "train": [0, 4, 9, 18, 20, 26, 28, 29, 30, 35, 37, 38, 42, 46, 47, 48, 51, 53, 54, 56, 63, 66, 67, 73, 87, 91, 92, 93, 96, 98, 100, 104, 107, 108, 109], "val": [0, 1, 2, 3, 10, 11, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25], "valid": [0, 4, 7, 8, 10, 11, 12, 13, 18, 20, 21, 25, 30, 33, 37, 45, 46, 48, 51, 55, 56, 59, 66, 67, 68, 83, 92, 102, 109], "see": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 28, 29, 30, 31, 35, 39, 41, 42, 43, 51, 53, 54, 55, 56, 57, 66, 67, 68, 73, 78, 88, 89, 90, 91, 92, 93, 94, 96, 98, 100, 102, 104, 106, 107, 108, 111, 112], "descript": [0, 1, 2, 3, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 88, 91, 101], "detail": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 51, 61, 67, 68, 73, 74, 75, 88, 97, 107, 108, 111, 112], "A": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 29, 30, 33, 36, 37, 39, 41, 42, 45, 46, 48, 51, 52, 53, 54, 55, 56, 57, 59, 63, 64, 65, 66, 68, 70, 71, 83, 91, 95, 97, 100, 102, 104, 105, 108], "subdirectori": [0, 1, 2, 3, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25], "class": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 30, 32, 33, 34, 35, 36, 37, 39, 41, 42, 44, 45, 46, 48, 51, 52, 53, 55, 56, 58, 59, 60, 61, 62, 64, 65, 66, 68, 69, 70, 72, 77, 79, 83, 84, 86, 89, 90], "file": [0, 1, 2, 3, 6, 8, 12, 13, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 30, 33, 37, 39, 41, 42, 45, 46, 48, 51, 52, 53, 55, 56, 59, 64, 66, 68, 70, 73, 74, 75, 83, 86, 90, 102, 104, 105, 108, 109, 112], "each": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 28, 30, 33, 35, 36, 41, 45, 46, 48, 49, 51, 52, 55, 56, 59, 62, 65, 66, 68, 70, 71, 74, 75, 77, 82, 83, 88, 89, 90, 93, 94, 95, 97, 100, 102, 103, 104, 105, 106, 107, 108, 112], "note2": [0, 18, 21, 25], "To": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 30, 31, 33, 35, 39, 41, 42, 43, 45, 51, 53, 55, 56, 57, 59, 64, 66, 68, 72, 73, 77, 86, 88, 90, 93, 96, 97, 101, 102, 104, 106, 107, 108, 111, 112], "up": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 30, 35, 37, 39, 41, 46, 48, 51, 56, 64, 66, 68, 75, 83, 91, 96, 100, 106, 114], "mai": [0, 2, 4, 7, 8, 12, 13, 14, 18, 21, 22, 25, 35, 42, 45, 49, 51, 53, 59, 61, 64, 68, 73, 74, 75, 77, 81, 82, 83, 86, 88, 91, 100, 102, 103, 104], "reduc": [0, 1, 2, 3, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 51, 64, 83, 86, 88, 100, 102, 103, 105, 107, 109, 114], "subset": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 36, 37, 46, 66, 83, 91, 93, 104, 114], "entir": [0, 1, 2, 3, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 37, 46, 56, 64, 66, 83, 90, 100], "ilsvrc2012": [0, 1, 2, 3, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25], "1000": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 33, 37, 46, 48, 51, 53, 55, 56, 66, 68, 90, 91, 103, 104], "50": [0, 1, 2, 3, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 30, 45, 56, 59, 95], "But": [0, 7, 8, 12, 13, 18, 21, 25, 51, 61, 68, 100], "purpos": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 51, 68, 83], "could": [0, 1, 2, 3, 5, 7, 10, 11, 12, 13, 14, 18, 19, 21, 22, 23, 24, 25, 28, 37, 39, 41, 46, 48, 49, 51, 60, 66, 68, 72, 90, 114], "perhap": [0, 7, 12, 13, 18, 21, 25], "exercis": [0, 7, 12, 13, 18, 21, 25], "left": [0, 1, 2, 3, 5, 7, 8, 10, 11, 12, 13, 14, 18, 19, 21, 22, 23, 24, 25, 78, 79, 80, 89, 97, 114], "upto": [0, 7, 12, 13, 18, 21, 25, 33], "reader": [0, 7, 12, 13, 18, 21, 25], "necessari": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 18, 19, 20, 21, 22, 23, 24, 25, 37, 46, 51, 53, 56, 66, 68, 81, 83, 90, 96, 111], "edit": [0, 1, 2, 3, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 48, 49, 51, 68], "cell": [0, 1, 2, 3, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25], "below": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 31, 32, 33, 34, 35, 36, 43, 44, 49, 51, 57, 58, 60, 64, 67, 72, 74, 75, 77, 78, 83, 86, 88, 89, 90, 93, 94, 96, 97, 100, 102, 103, 104, 106, 107, 108, 111], "specifi": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 30, 33, 39, 41, 45, 46, 49, 51, 56, 59, 66, 68, 71, 74, 75, 78, 79, 80, 83, 89, 90, 92, 94, 95, 97, 100, 106, 108, 111], "directori": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 30, 32, 33, 37, 42, 44, 45, 46, 48, 53, 56, 58, 59, 64, 66, 71, 96], "save": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 30, 32, 33, 36, 37, 39, 41, 42, 44, 45, 46, 48, 51, 53, 56, 58, 59, 64, 65, 66, 68, 71, 82, 86, 90, 108, 112], "dataset_dir": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 30, 33], "path": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 30, 32, 33, 37, 39, 41, 42, 44, 45, 46, 48, 51, 53, 55, 56, 58, 59, 61, 64, 66, 68, 69, 70, 75, 82, 86, 96], "replac": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 36, 48, 51, 54, 55, 61, 64, 65, 67, 68, 72, 74, 83, 88, 90, 103, 108], "real": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 53, 81, 111], "loop": [0, 1, 2, 3, 5, 6, 7, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 61, 90, 107], "doe": [0, 1, 2, 3, 5, 6, 7, 9, 10, 11, 12, 13, 14, 15, 16, 17, 19, 20, 21, 22, 23, 24, 25, 28, 35, 37, 43, 46, 56, 57, 59, 60, 61, 66, 72, 77, 90, 94, 97, 99, 102, 107, 108], "ani": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 30, 33, 34, 35, 36, 37, 38, 39, 45, 46, 51, 54, 56, 59, 60, 61, 62, 65, 66, 67, 68, 69, 72, 74, 77, 83, 86, 90, 106, 109], "limit": [0, 1, 2, 3, 5, 6, 7, 8, 12, 13, 14, 15, 16, 17, 19, 21, 22, 23, 24, 25, 72, 99], "written": [0, 1, 2, 3, 4, 5, 6, 7, 8, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 101, 102], "Not": [0, 7, 12, 13, 21, 25, 46, 63, 64, 66, 91, 97], "realli": [0, 7, 12, 13, 21, 25], "we": [0, 1, 4, 5, 6, 7, 8, 9, 12, 13, 15, 17, 18, 19, 20, 21, 25, 29, 30, 32, 33, 35, 41, 44, 45, 46, 51, 52, 54, 55, 58, 59, 61, 62, 64, 66, 68, 71, 72, 74, 75, 83, 86, 88, 90, 91, 95, 100, 102, 103, 107], "later": [0, 7, 8, 12, 13, 21, 25, 68, 73, 86, 90], "modifi": [0, 1, 2, 3, 5, 6, 7, 8, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 36, 39, 44, 61, 64, 65, 68, 74, 75, 102, 108, 109, 114], "quantizationsim": [0, 1, 2, 3, 5, 6, 8, 10, 11, 12, 13, 14, 15, 16, 17, 19, 21, 22, 23, 24, 25, 51, 63], "session": [0, 1, 2, 3, 28, 30, 42, 44, 45, 46, 48, 70], "act": [0, 45, 46, 59, 66], "regular": [0, 8, 28, 39, 41, 51, 68, 77, 88, 91, 102, 108], "onnxruntim": [0, 1, 2, 3, 42, 44, 46], "howev": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 22, 23, 24, 25, 34, 35, 51, 56, 68, 72, 102, 103], "recommend": [0, 1, 2, 3, 4, 5, 6, 9, 13, 19, 20, 30, 35, 37, 41, 42, 43, 45, 46, 48, 51, 52, 56, 66, 73, 83, 91, 93, 95, 102, 107], "onli": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 30, 32, 33, 34, 39, 41, 44, 45, 46, 48, 51, 52, 55, 58, 59, 60, 61, 63, 65, 66, 68, 69, 73, 74, 75, 78, 81, 82, 83, 88, 90, 93, 99, 100, 102, 104, 105, 106, 109, 111, 114], "quantizationsimmodel": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 18, 19, 20, 21, 22, 23, 24, 25, 28, 29, 32, 33, 36, 39, 41, 42, 44, 45, 46, 48, 51, 54, 58, 59, 64, 66, 67, 68, 69, 77, 82, 83, 86, 87, 90, 91, 93], "regist": [0, 77, 89], "requir": [0, 1, 4, 9, 12, 15, 16, 17, 18, 19, 22, 23, 24, 25, 28, 29, 30, 31, 33, 35, 36, 37, 39, 41, 43, 45, 46, 48, 49, 51, 54, 55, 56, 57, 58, 59, 60, 61, 64, 65, 66, 68, 70, 71, 74, 75, 77, 83, 86, 90, 93, 95, 100, 102, 103, 106, 107, 111], "custom": [0, 6, 8, 20, 35, 39, 41, 48, 49, 61, 67, 77, 88, 107, 108], "import": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 39, 41, 42, 43, 44, 45, 46, 48, 51, 52, 53, 54, 55, 56, 57, 58, 59, 61, 62, 64, 65, 66, 67, 68, 69, 70, 71, 75, 77, 78, 79, 80, 81, 83, 84, 86, 87, 88, 89, 90, 93, 94], "torch": [0, 1, 2, 3, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 51, 52, 53, 54, 56, 58, 59, 60, 62, 63, 64, 65, 66, 68, 70, 71, 72, 73, 74, 77, 78, 79, 80, 81, 83, 84, 86, 87, 88, 89, 90, 96, 101, 109], "ort": [0, 1, 2, 3, 42], "common": [0, 1, 2, 3, 5, 6, 7, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 64, 68, 72, 74, 83, 107, 112], "image_net_config": [0, 1, 2, 3, 5, 6, 7, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25], "util": [0, 1, 2, 3, 5, 6, 7, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 35, 36, 37, 39, 44, 52, 53, 64, 65, 68, 70, 72, 83, 90, 93, 102], "image_net_evalu": [0, 1, 2, 3, 5, 6, 7, 13, 14, 15, 16, 17, 19, 21, 22, 23, 24, 25], "imagenetevalu": [0, 1, 2, 3, 5, 6, 7, 13, 14, 15, 16, 17, 19, 21, 22, 23, 24, 25], "image_net_data_load": [0, 1, 2, 3, 15, 17, 19, 21, 22, 23, 24, 25], "imagenetdataload": [0, 1, 2, 3, 12, 15, 17, 19, 21, 22, 23, 24, 25], "imagenetdatapipelin": [0, 1, 2, 3, 5, 6, 7, 12, 13, 14, 15, 16, 17, 19, 21, 22, 23, 24, 25, 51, 54, 55, 68], "staticmethod": [0, 1, 2, 3, 5, 6, 7, 12, 13, 14, 15, 16, 17, 19, 21, 22, 23, 24, 25, 61], "def": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 30, 31, 33, 34, 35, 36, 37, 39, 41, 42, 43, 45, 46, 48, 51, 52, 53, 54, 55, 56, 57, 59, 60, 61, 62, 65, 66, 68, 69, 70, 71, 72, 77, 86, 90], "get_val_dataload": [0, 1, 2, 3, 15, 17, 18, 19, 21, 22, 23, 24, 25, 51, 55, 68], "data": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 29, 30, 33, 36, 37, 39, 41, 42, 45, 46, 48, 51, 53, 54, 55, 56, 59, 61, 63, 64, 66, 68, 70, 72, 81, 82, 83, 84, 86, 87, 90, 91, 93, 99, 103, 104, 105, 107, 108], "return": [0, 1, 2, 3, 4, 5, 6, 7, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 41, 42, 44, 45, 46, 48, 51, 52, 53, 54, 55, 56, 58, 59, 60, 61, 62, 64, 65, 66, 68, 69, 70, 71, 77, 81, 82, 83, 84, 86, 87, 89, 90, 92, 97, 98, 104, 108], "data_load": [0, 1, 2, 3, 5, 6, 7, 13, 14, 15, 17, 18, 19, 20, 21, 22, 23, 24, 25, 41, 42, 45, 48, 51, 53, 55, 56, 59, 68, 82, 86, 87, 90], "image_s": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 30, 33, 53], "batch_siz": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 29, 30, 33, 37, 41, 42, 46, 48, 51, 53, 56, 66, 68, 90], "is_train": [0, 1, 2, 3, 4, 15, 17, 19, 21, 22, 23, 24, 25, 33], "fals": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 13, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 30, 33, 35, 39, 42, 44, 45, 48, 49, 52, 53, 55, 56, 59, 61, 62, 64, 68, 69, 72, 77, 78, 81, 83, 84, 86, 88, 89, 90, 101, 106], "num_work": [0, 1, 2, 3, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25], "sess": [0, 1, 2, 3, 30], "inferencesess": [0, 1, 2, 3, 42, 44, 46], "float": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 30, 33, 37, 39, 41, 42, 45, 46, 48, 49, 51, 53, 55, 56, 59, 66, 67, 68, 77, 79, 81, 83, 84, 87, 102, 104, 107, 108, 112], "its": [0, 1, 2, 3, 5, 6, 7, 9, 13, 14, 15, 16, 17, 19, 21, 22, 23, 24, 25, 30, 33, 35, 45, 46, 59, 77, 81, 86, 87, 88, 90, 94, 96, 98, 104, 108, 114], "top": [0, 1, 2, 3, 4, 5, 6, 7, 8, 13, 14, 15, 16, 17, 19, 21, 22, 23, 24, 25, 77, 94, 111], "param": [0, 1, 2, 3, 5, 6, 7, 13, 14, 15, 16, 17, 19, 21, 22, 23, 24, 25, 28, 30, 31, 33, 36, 37, 39, 41, 42, 45, 46, 48, 51, 53, 56, 59, 64, 66, 68, 69, 70, 77, 83, 88, 89, 106], "iter": [0, 1, 2, 3, 4, 5, 6, 7, 13, 14, 15, 16, 17, 19, 21, 22, 23, 24, 25, 28, 30, 33, 37, 41, 42, 46, 51, 53, 56, 66, 90, 91, 103], "none": [0, 1, 2, 3, 4, 5, 6, 7, 8, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 30, 32, 33, 35, 36, 37, 39, 41, 42, 44, 45, 46, 48, 51, 52, 53, 54, 55, 56, 57, 58, 59, 61, 64, 65, 66, 68, 70, 71, 72, 77, 78, 79, 80, 82, 83, 86, 88, 90, 111], "go": [0, 4, 7, 8, 12, 13, 18, 21, 25, 35, 51, 54, 68, 74, 75, 86, 90], "load": [0, 1, 2, 3, 8, 32, 33, 36, 39, 44, 45, 51, 54, 55, 56, 58, 59, 61, 62, 64, 68, 69, 86, 100], "pretrain": [0, 1, 2, 3, 4, 5, 10, 11, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 33, 51, 53, 54, 57, 65, 66, 68, 70, 71, 86, 105, 108], "torchvis": [0, 1, 2, 3, 5, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 51, 53, 54, 57, 65, 66, 68, 70, 71, 90], "similarli": [0, 4, 12, 13, 18, 21, 25, 51, 68, 83, 86, 107], "instead": [0, 1, 2, 3, 4, 5, 6, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 30, 34, 51, 60, 61, 62, 68, 83, 86, 102, 103, 114], "input_shap": [0, 1, 2, 3, 4, 5, 9, 13, 14, 15, 16, 17, 18, 19, 22, 23, 24, 31, 33, 34, 37, 42, 46, 48, 51, 53, 55, 56, 57, 61, 65, 66, 68, 70, 90], "224": [0, 1, 2, 3, 4, 7, 10, 11, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 30, 31, 37, 39, 42, 45, 46, 48, 51, 53, 55, 57, 58, 65, 66, 68, 70, 71], "shape": [0, 1, 2, 3, 7, 8, 9, 13, 18, 19, 21, 22, 23, 24, 25, 33, 34, 35, 52, 56, 57, 61, 62, 64, 65, 69, 72, 78, 79, 80, 81, 83, 84, 88, 89, 90, 104], "channel": [0, 1, 2, 3, 14, 16, 18, 19, 21, 22, 23, 24, 25, 30, 46, 49, 52, 54, 64, 66, 71, 83, 86, 88, 93, 95, 96, 97, 99, 100, 103, 104, 106, 107, 108, 109, 110, 112, 113, 114], "x": [0, 1, 2, 3, 4, 5, 8, 9, 12, 13, 18, 19, 21, 22, 23, 24, 25, 30, 33, 34, 35, 39, 52, 60, 61, 62, 73, 79, 80, 81, 88, 90, 95, 101, 104], "height": [0, 1, 2, 3, 8, 18, 19, 21, 22, 23, 24, 25, 110, 113, 114], "width": [0, 1, 2, 3, 13, 18, 19, 21, 22, 23, 24, 25, 46, 49, 66, 91, 107, 108, 110, 113, 114], "dummy_input": [0, 1, 2, 3, 18, 19, 20, 21, 22, 23, 24, 25, 29, 32, 42, 44, 45, 46, 48, 51, 52, 53, 57, 58, 59, 60, 64, 65, 66, 68, 69, 82, 83, 86, 90], "randn": [0, 1, 2, 3, 20, 39, 42, 46, 48, 51, 53, 59, 61, 62, 66, 68, 69, 77, 78, 81, 84, 88, 89], "filenam": [0, 1, 2, 3, 28, 39, 41, 48, 51, 64, 68, 86], "resnet": [0, 1, 2, 3, 4, 5, 6, 10, 11, 12, 13, 14, 30, 33, 95], "18": [0, 1, 2, 3], "pt_model": [0, 1, 2, 3], "true": [0, 1, 2, 3, 4, 5, 7, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 30, 33, 36, 39, 41, 42, 45, 48, 49, 51, 52, 53, 54, 55, 56, 57, 59, 61, 62, 64, 65, 66, 68, 69, 70, 71, 72, 77, 78, 79, 80, 81, 83, 84, 88, 89, 90, 101, 106], "export": [0, 1, 2, 3, 4, 5, 8, 10, 11, 13, 14, 18, 19, 20, 22, 23, 24, 32, 33, 37, 39, 44, 45, 46, 48, 49, 51, 54, 58, 59, 60, 64, 66, 68, 72, 74, 75, 86, 87, 93, 96, 98, 100, 101, 102, 105, 108, 109], "eval": [0, 1, 2, 3, 4, 7, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 30, 33, 37, 42, 45, 46, 51, 53, 55, 56, 57, 59, 61, 63, 65, 66, 68, 70, 71, 90, 97, 100, 111], "trainingmod": [0, 3], "export_param": [0, 1, 2, 3], "do_constant_fold": [0, 1, 2, 3], "input_nam": [0, 1, 2, 3, 68], "input": [0, 1, 2, 3, 5, 7, 8, 9, 10, 11, 12, 13, 14, 18, 21, 25, 30, 32, 33, 34, 35, 37, 42, 44, 45, 46, 48, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 68, 69, 72, 77, 78, 79, 80, 82, 83, 84, 86, 88, 89, 90, 94, 97, 100, 104, 106, 108, 110, 113, 114], "output_nam": [0, 1, 2, 3, 68], "output": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 29, 30, 33, 34, 35, 37, 42, 45, 46, 48, 49, 51, 52, 53, 55, 59, 60, 61, 62, 64, 66, 67, 68, 69, 71, 72, 77, 78, 83, 88, 89, 90, 94, 100, 103, 104, 106, 108, 109, 110, 113, 114], "dynamic_ax": [0, 1, 2, 3], "0": [0, 1, 2, 3, 5, 6, 8, 9, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 29, 30, 35, 39, 41, 42, 44, 45, 48, 51, 52, 53, 55, 56, 59, 61, 62, 64, 65, 68, 69, 70, 72, 73, 74, 75, 77, 78, 79, 80, 81, 83, 84, 86, 88, 89, 90, 91, 95, 97, 101, 106], "load_model": [0, 1, 2, 3, 32], "befor": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 32, 34, 35, 36, 38, 41, 42, 43, 44, 45, 46, 48, 51, 53, 58, 65, 67, 68, 71, 72, 77, 82, 88, 90, 91, 92, 93, 100, 102, 104, 105, 108, 112], "onnxsim": [0, 1, 2, 3, 41, 42, 43, 44, 45, 46, 48], "_": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 18, 19, 20, 22, 23, 24, 25, 28, 32, 33, 35, 36, 37, 41, 42, 43, 44, 45, 46, 48, 53, 58, 66, 77, 78, 82, 87, 88, 89, 90, 102], "except": [0, 1, 2, 3, 9, 12, 25, 35, 83], "print": [0, 1, 2, 3, 7, 8, 9, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 30, 33, 42, 45, 51, 52, 53, 56, 59, 61, 62, 68, 72, 75, 77, 78, 88, 90, 104], "fail": [0, 1, 2, 3, 52, 61, 62, 92, 101, 102], "proceed": [0, 1, 2, 3], "unsimplifi": [0, 1, 2, 3], "whether": [0, 1, 2, 3, 5, 13, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 32, 38, 44, 58, 61, 62, 67, 91, 97, 105], "cpu": [0, 1, 2, 3, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 51, 53, 54, 57, 58, 61, 65, 68, 69, 71, 73, 74, 90, 102, 109], "cuda": [0, 1, 2, 3, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 41, 42, 44, 48, 53, 54, 55, 56, 59, 66, 68, 70, 73, 74, 75, 90], "devic": [0, 1, 2, 3, 7, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 32, 41, 42, 44, 48, 51, 53, 54, 55, 58, 59, 61, 64, 65, 68, 70, 71, 86, 87, 90, 108], "your": [0, 1, 2, 3, 5, 6, 7, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 42, 48, 51, 54, 55, 61, 62, 68, 72, 73, 74, 75, 77, 87, 91, 92, 95, 96, 100, 101, 102, 105, 108, 111], "environ": [0, 4, 6, 7, 10, 11, 18, 25, 33, 73, 96], "chang": [0, 1, 2, 3, 4, 7, 8, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 33, 38, 45, 49, 51, 53, 59, 60, 61, 64, 67, 68, 71, 82, 83, 86, 90, 91, 100, 104, 105, 106, 108, 112, 114], "logic": [0, 1, 2, 3, 15, 16, 17, 18, 19, 22, 23, 24, 25, 33, 45, 59, 77, 88, 109], "forc": [0, 1, 2, 3, 15, 16, 17, 18, 19, 22, 23, 24, 25], "placement": [0, 1, 2, 3, 15, 16, 17, 18, 19, 22, 23, 24, 25, 106], "cudnn_conv_algo_search": [0, 1, 2, 3], "fix": [0, 1, 2, 3, 49, 62, 87, 98, 102, 107, 108, 109], "default": [0, 1, 2, 3, 4, 5, 6, 7, 8, 12, 13, 15, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 30, 33, 35, 37, 39, 41, 42, 45, 46, 48, 51, 53, 55, 56, 59, 61, 66, 68, 74, 75, 77, 78, 82, 86, 88, 89, 91, 97, 100, 106, 108, 109, 111], "avoid": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 18, 19, 22, 23, 24, 25, 34, 39, 46, 51, 60, 66, 68, 91, 95], "everi": [0, 1, 2, 3, 4, 7, 8, 10, 11, 12, 13, 15, 16, 17, 18, 21, 23, 24, 25, 28, 32, 37, 41, 44, 46, 51, 58, 66, 68, 90, 97, 100, 105, 112], "cudaexecutionprovid": [0, 1, 2, 3], "get_available_provid": [0, 1, 2, 3], "cpuexecutionprovid": [0, 1, 2, 3], "use_cuda": [0, 1, 2, 3, 4, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 30, 41, 42, 44, 48, 51, 54, 56, 68], "let": [0, 4, 7, 8, 13, 18, 51, 61, 68, 90], "determin": [0, 8, 18, 20, 28, 30, 37, 39, 41, 46, 48, 49, 51, 56, 66, 68, 79, 80, 83, 88, 90, 92, 102, 103, 104, 112], "32": [0, 1, 2, 4, 5, 6, 8, 9, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 22, 23, 24, 28, 33, 34, 35, 37, 42, 49, 51, 52, 61, 62, 68, 74, 75, 78, 86, 89, 107], "routin": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 51, 68], "serializetostr": [0, 1, 2, 3, 44], "batchnorm": [0, 1, 2, 3, 5, 10, 11, 13, 14, 18, 19, 22, 23, 24, 31, 35, 36, 38, 42, 43, 52, 53, 55, 57, 65, 71, 92, 103, 114], "bn": [0, 1, 2, 3, 5, 7, 10, 11, 13, 14, 18, 19, 22, 23, 24, 29, 36, 55, 65, 67, 102, 104, 109], "These": [0, 2, 6, 8, 13, 18, 20, 22, 28, 39, 41, 42, 48, 53, 67, 68, 72, 75, 88, 90, 92, 93, 94, 95, 101, 102, 103, 104, 107, 108], "adjac": [0, 1, 2, 3, 5, 10, 11, 13, 14, 18, 19, 22, 23, 24, 90, 106], "convolut": [0, 1, 2, 3, 5, 9, 10, 11, 13, 14, 15, 17, 18, 19, 22, 23, 24, 30, 35, 36, 52, 83, 90, 93, 94, 95, 100, 107, 110, 113, 114], "cannot": [0, 1, 2, 3, 5, 10, 11, 13, 14, 18, 19, 22, 23, 24, 52, 61, 62, 78, 89], "thei": [0, 1, 2, 3, 5, 8, 9, 10, 11, 12, 13, 14, 18, 19, 22, 23, 24, 25, 34, 36, 61, 65, 67, 83, 107, 111], "why": [0, 13, 18, 107], "do": [0, 1, 2, 3, 4, 5, 6, 7, 9, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 29, 33, 35, 39, 41, 51, 61, 63, 64, 71, 74, 75, 90, 100, 104, 107, 108], "On": [0, 13, 18, 49, 73], "runtim": [0, 1, 2, 3, 5, 10, 11, 13, 14, 18, 19, 22, 23, 24, 39, 48, 49, 51, 56, 68, 69, 77, 83, 86, 87, 90, 95, 98, 100, 102, 104, 106, 108, 109], "tflite": [0, 13, 18], "snapdragon": [0, 13, 18], "neural": [0, 6, 13, 18, 20, 87, 90, 92, 95, 98, 100, 102, 105, 107, 108, 113], "process": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 13, 14, 18, 19, 22, 23, 24, 30, 32, 44, 51, 58, 68, 70, 83, 84, 87, 90, 92, 94, 97, 98, 100, 103, 108], "sdk": [0, 13, 18, 87, 90, 98], "etc": [0, 4, 7, 8, 13, 18, 49, 51, 68, 74, 95, 102], "practic": [0, 4, 6, 7, 8, 12, 13, 15, 16, 17, 18, 20, 25, 51, 68, 90, 100], "so": [0, 1, 4, 5, 7, 8, 9, 10, 11, 12, 13, 15, 16, 17, 18, 19, 21, 23, 24, 25, 28, 29, 37, 39, 41, 46, 48, 51, 56, 61, 62, 63, 66, 68, 72, 75, 88, 97, 101, 104], "speedup": [0, 13, 18], "sinc": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 18, 19, 22, 23, 24, 25, 48, 51, 64, 68, 83, 93, 95, 108], "unnecessari": [0, 13, 18, 90, 114], "now": [0, 1, 2, 3, 4, 7, 8, 9, 10, 11, 13, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 30, 35, 51, 61, 62, 68, 69, 86, 90, 109], "perspect": [0, 13, 18], "mathemat": [0, 13, 18, 60], "equival": [0, 13, 18, 19, 22, 23, 24, 25, 51, 59, 60, 67, 68, 77, 78, 79, 80, 83, 90], "produc": [0, 12, 13, 18, 25, 42, 49, 53, 61, 81, 82, 83, 84, 97, 104], "same": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 13, 15, 16, 17, 18, 19, 21, 22, 23, 24, 28, 32, 35, 44, 51, 53, 58, 61, 62, 64, 66, 68, 69, 72, 77, 81, 83, 88, 89, 93, 103, 106, 112], "increas": [0, 13, 18, 30, 56, 71, 83, 97, 103], "rang": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 13, 14, 18, 19, 20, 21, 22, 23, 35, 37, 46, 51, 53, 54, 61, 66, 68, 71, 78, 82, 84, 90, 91, 93, 96, 97, 102, 103, 104, 105, 107, 108, 109, 112], "tensor": [0, 2, 9, 12, 13, 14, 18, 22, 23, 24, 25, 28, 32, 35, 38, 39, 45, 47, 48, 49, 51, 52, 53, 56, 57, 58, 59, 60, 61, 64, 65, 66, 67, 68, 69, 77, 78, 79, 80, 83, 84, 86, 88, 89, 90, 91, 94, 101, 102, 104, 106, 107, 108, 109], "valu": [0, 1, 2, 4, 5, 6, 7, 8, 9, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 25, 28, 30, 33, 36, 37, 41, 45, 46, 49, 51, 55, 56, 58, 59, 61, 64, 65, 66, 68, 77, 78, 79, 80, 81, 82, 83, 84, 86, 89, 90, 91, 94, 95, 97, 100, 102, 103, 104, 105, 106, 108, 110, 112, 113], "weight": [0, 1, 2, 3, 4, 5, 6, 9, 10, 11, 12, 13, 14, 18, 19, 20, 22, 23, 24, 25, 28, 30, 33, 35, 36, 37, 38, 39, 41, 45, 46, 47, 49, 51, 55, 59, 62, 64, 65, 66, 67, 68, 71, 72, 77, 82, 83, 84, 86, 88, 90, 91, 93, 95, 100, 102, 103, 104, 105, 106, 107, 108, 112], "And": [0, 13, 18, 36, 65], "neg": [0, 7, 8, 13, 18, 78, 83], "impact": [0, 13, 18, 90, 97, 107], "especi": [0, 13, 18, 73, 102, 105, 107], "want": [0, 4, 7, 8, 12, 13, 18, 25, 32, 33, 36, 39, 44, 45, 48, 51, 58, 59, 61, 65, 67, 68, 74, 77], "behavior": [0, 13, 18, 19, 22, 23, 24, 61, 72, 88, 90, 98], "here": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 15, 17, 18, 19, 21, 22, 23, 24, 25, 28, 29, 30, 31, 41, 51, 53, 54, 57, 61, 64, 66, 68, 69, 72, 86, 90, 102, 105, 106], "place": [0, 1, 2, 3, 5, 6, 7, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 33, 39, 43, 45, 51, 55, 57, 59, 65, 68, 83, 86, 106], "aimet_onnx": [0, 1, 2, 3, 41, 42, 43, 44, 45, 46, 48, 73, 75], "batch_norm_fold": [0, 1, 2, 3, 4, 5, 7, 10, 11, 13, 14, 18, 19, 21, 22, 23, 24, 29, 36, 54, 65, 71, 90], "fold_all_batch_norms_to_weight": [0, 1, 2, 3], "basic": [0, 4, 7, 8, 18, 21, 51, 68, 75, 87, 90], "mean": [0, 4, 7, 8, 9, 12, 13, 15, 16, 17, 18, 20, 21, 22, 25, 38, 51, 54, 68, 71, 88, 90, 104, 106, 108], "graph": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 13, 14, 15, 17, 18, 19, 21, 22, 23, 24, 25, 30, 35, 49, 51, 52, 61, 68, 70, 86, 101, 102, 108, 111], "configur": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 14, 18, 19, 21, 22, 23, 24, 28, 37, 41, 42, 46, 48, 49, 51, 53, 55, 64, 66, 68, 83, 86, 90, 99, 109], "them": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 18, 19, 21, 22, 23, 24, 25, 35, 39, 42, 46, 51, 61, 62, 64, 66, 68, 72, 88, 90, 100], "few": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 51, 68, 90, 95], "explain": [0, 4, 7, 8, 12, 18, 21, 25, 51, 68, 94, 100, 103, 108], "quant_schem": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 18, 19, 21, 22, 23, 24, 25, 28, 37, 39, 42, 46, 48, 49, 51, 53, 55, 66, 68, 69, 82, 86], "quantschem": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 18, 19, 21, 22, 23, 24, 25, 28, 37, 39, 41, 42, 46, 48, 51, 53, 54, 55, 66, 68, 69, 72, 82, 86, 92], "post_training_tf_enhanc": [0, 1, 2, 3, 4, 7, 8, 12, 18, 19, 21, 22, 23, 25, 28, 37, 39, 41, 42, 46, 48, 49, 51, 53, 55, 66, 68], "support": [0, 4, 7, 8, 9, 18, 21, 23, 24, 26, 28, 30, 31, 33, 34, 35, 37, 39, 41, 45, 46, 48, 51, 55, 56, 59, 60, 61, 66, 67, 68, 69, 73, 77, 83, 86, 94, 95, 98, 99, 100, 101, 102, 103, 106, 107, 108, 109, 113], "option": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 30, 33, 36, 37, 39, 41, 42, 45, 46, 48, 51, 52, 53, 54, 55, 56, 59, 61, 64, 65, 66, 68, 71, 75, 77, 78, 83, 86, 87, 89, 90, 91, 104, 106, 108], "tf_enhanc": [0, 4, 7, 8, 18, 21, 39, 55], "tf": [0, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 18, 21, 25, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 39, 45, 46, 48, 55, 66, 74, 104, 108, 109], "quant": [0, 1, 4, 5, 7, 8, 10, 11, 13, 14, 18, 19, 20, 21, 22, 23, 24, 28, 38, 39, 41, 42, 45, 48, 51, 55, 59, 67, 68, 93], "scheme": [0, 4, 7, 8, 12, 15, 16, 17, 18, 21, 25, 28, 30, 37, 39, 41, 42, 46, 48, 51, 53, 55, 56, 58, 66, 68, 83, 84, 92, 93, 100, 104], "enum": [0, 4, 7, 8, 18, 21, 30, 33, 41, 45, 55, 56, 59], "post_training_tf": [0, 4, 5, 7, 8, 10, 13, 14, 18, 21, 22, 28, 37, 39, 41, 46, 48, 49, 51, 55, 66, 68, 69, 82, 86], "default_output_bw": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 18, 19, 21, 22, 23, 24, 25, 28, 37, 39, 45, 48, 51, 59, 66, 68, 86, 90], "8": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 16, 17, 18, 19, 21, 22, 23, 24, 25, 28, 33, 36, 37, 39, 41, 42, 45, 46, 48, 49, 51, 53, 55, 56, 59, 61, 62, 64, 66, 68, 70, 72, 73, 75, 77, 78, 79, 80, 81, 83, 84, 86, 88, 89, 90, 102, 107, 114], "essenti": [0, 4, 7, 8, 18, 21, 83, 87], "ask": [0, 4, 7, 8, 12, 18, 21, 25, 77], "all": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 18, 19, 21, 22, 23, 24, 25, 29, 31, 33, 34, 35, 36, 39, 41, 45, 46, 48, 49, 51, 54, 55, 56, 59, 61, 62, 64, 65, 66, 67, 68, 71, 72, 73, 74, 77, 82, 83, 86, 88, 90, 94, 97, 100, 103, 104, 106, 107], "activ": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 18, 19, 21, 22, 23, 24, 25, 33, 34, 35, 36, 37, 39, 45, 46, 48, 49, 51, 52, 55, 59, 60, 61, 64, 65, 66, 68, 69, 82, 83, 86, 88, 90, 102, 104, 105, 106, 107, 108], "integ": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 18, 19, 21, 22, 23, 24, 25, 28, 37, 39, 41, 46, 48, 49, 66, 68, 78, 83, 91, 102, 104], "default_param_bw": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 18, 19, 21, 22, 23, 24, 25, 28, 37, 39, 41, 45, 46, 48, 51, 59, 66, 68, 86, 90], "There": [0, 1, 4, 5, 7, 8, 12, 13, 14, 18, 19, 21, 22, 23, 24, 25, 58, 62, 68, 72, 73, 101, 103, 105, 112], "other": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 36, 60, 61, 65, 67, 68, 69, 72, 73, 83, 86, 97, 99, 102, 104, 107, 108, 109], "check": [0, 4, 7, 8, 12, 18, 21, 25, 32, 35, 37, 38, 44, 46, 52, 58, 60, 61, 62, 66, 67, 68, 92, 102, 105, 107], "document": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 14, 18, 19, 20, 21, 22, 23, 24, 25, 26, 33, 64, 70, 73, 75, 98, 109, 111], "refer": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 45, 49, 51, 55, 58, 59, 64, 68, 72, 83, 86, 88, 91, 96, 108], "aimet_common": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114], "quantsim": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 18, 19, 21, 22, 23, 24, 28, 32, 39, 41, 44, 45, 46, 48, 51, 53, 54, 55, 58, 59, 64, 66, 67, 68, 69, 72, 82, 83, 86, 87, 96, 102, 105, 106, 109], "default_activation_bw": [0, 1, 2, 3, 41, 46, 48], "even": [0, 4, 7, 8, 13, 18, 51, 68, 77], "though": [0, 4, 7, 8, 13, 18, 51, 68, 77, 83, 106], "ad": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 13, 14, 15, 16, 17, 18, 19, 22, 23, 24, 48, 49, 51, 62, 64, 68, 69, 90, 99, 106, 109], "node": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 13, 14, 18, 19, 22, 23, 24, 39, 51, 52, 59, 60, 61, 68, 90, 105, 108], "readi": [0, 1, 2, 3, 4, 7, 8, 10, 11, 13, 15, 16, 17, 18, 19, 22, 23, 24, 25, 39, 51, 68, 90, 107], "yet": [0, 4, 7, 8, 13, 18, 51, 68], "scale": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 18, 19, 20, 22, 23, 24, 25, 29, 31, 36, 43, 49, 51, 54, 57, 64, 65, 68, 77, 78, 79, 80, 81, 83, 86, 89, 93, 102, 103, 104, 105, 108], "offset": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 18, 19, 20, 22, 23, 24, 25, 37, 46, 49, 51, 66, 68, 77, 78, 83, 84, 86, 89, 102, 104, 105, 108], "pass": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 28, 30, 32, 33, 35, 36, 37, 39, 41, 42, 44, 45, 46, 48, 51, 52, 54, 55, 56, 58, 59, 60, 61, 62, 63, 64, 65, 66, 68, 72, 77, 83, 86, 87, 88, 90, 98, 101, 103, 104, 105, 107, 108, 109, 111], "unlabel": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 17, 18, 19, 20, 22, 23, 24, 25, 42, 46, 48, 51, 53, 66, 68, 91, 102, 104], "through": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 18, 19, 21, 22, 23, 24, 25, 35, 45, 51, 55, 59, 61, 66, 68, 71, 72, 86, 88, 90, 103, 104, 108], "collect": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 13, 14, 18, 19, 22, 23, 24, 42, 46, 51, 53, 66, 68, 82, 83, 97, 104], "statist": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 13, 14, 15, 16, 17, 18, 19, 22, 23, 24, 29, 30, 37, 38, 46, 51, 54, 56, 66, 67, 68, 71, 78, 79, 80, 82, 84, 88, 89, 90, 93, 102, 104, 112], "which": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 28, 30, 32, 33, 35, 36, 38, 41, 44, 45, 46, 49, 51, 52, 55, 56, 58, 59, 61, 62, 64, 65, 67, 68, 71, 74, 75, 77, 78, 81, 83, 84, 86, 87, 88, 89, 90, 93, 95, 97, 100, 102, 103, 104, 106, 108, 109, 111, 114], "calcul": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 22, 23, 24, 25, 28, 33, 39, 42, 45, 48, 51, 53, 59, 65, 68, 84, 88, 97, 103, 104, 105, 108], "sometim": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 13, 14, 18, 19, 22, 23, 24, 51, 68, 94, 100, 103, 104], "calibr": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 18, 19, 22, 23, 24, 25, 37, 41, 46, 48, 51, 66, 68, 78, 82, 83, 84, 86, 87, 88, 89, 90, 102, 104, 105, 107, 108], "simpli": [0, 4, 7, 8, 13, 18, 21, 28, 37, 39, 41, 46, 48, 51, 61, 66, 68], "benefici": [0, 4, 7, 8, 12, 13, 18, 25, 51, 68, 104], "forward": [0, 3, 4, 7, 8, 9, 10, 11, 12, 18, 19, 21, 22, 23, 24, 25, 33, 35, 37, 39, 45, 46, 48, 51, 52, 54, 59, 60, 61, 62, 63, 65, 66, 68, 69, 74, 77, 78, 88, 89, 90, 101, 104, 107, 109], "well": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 18, 19, 20, 22, 23, 24, 25, 33, 46, 51, 52, 62, 64, 66, 68, 81, 83, 86, 100, 103, 104], "distribut": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 18, 19, 22, 23, 24, 25, 30, 51, 56, 68, 103, 107, 108], "doesn": [0, 1, 2, 3, 5, 6, 14, 15, 16, 17, 18, 19, 22, 23, 24, 63, 77, 105], "t": [0, 4, 7, 8, 12, 13, 18, 21, 25, 33, 45, 51, 59, 61, 63, 64, 67, 68, 74, 77, 91, 104, 105], "look": [0, 4, 7, 8, 9, 12, 13, 18, 25, 35, 45, 51, 59, 68, 90, 92], "definit": [0, 4, 7, 8, 12, 13, 18, 19, 22, 23, 24, 25, 34, 38, 60, 61, 64, 67, 72, 77, 90, 102], "extrem": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 18, 19, 22, 23, 24, 25, 51, 68, 108], "bias": [0, 2, 14, 18, 22, 102], "origin": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 30, 32, 33, 35, 44, 56, 58, 61, 68, 72, 77, 88, 90, 94, 95, 97, 102, 103, 104, 108, 111], "consist": [0, 18, 58, 72, 83, 97, 108], "dark": [0, 1, 2, 3, 4, 5, 10, 11, 12, 13, 14, 18, 19, 22, 23, 24, 25, 51, 68], "light": [0, 1, 2, 3, 4, 5, 10, 11, 12, 13, 14, 18, 19, 22, 23, 24, 25, 51, 68], "mani": [0, 4, 7, 8, 12, 13, 15, 16, 17, 18, 25, 61, 91, 95, 103], "differ": [0, 4, 7, 8, 13, 15, 16, 17, 18, 23, 24, 30, 51, 53, 56, 61, 64, 66, 68, 69, 72, 74, 75, 83, 94, 97, 100, 102, 103, 105, 107, 108], "wai": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 18, 19, 22, 23, 24, 25, 30, 56, 58, 68, 72, 73, 83, 90, 101], "just": [0, 4, 7, 8, 12, 13, 18, 23, 24, 25, 51, 68, 108, 114], "pass_calibration_data": [0, 1, 2, 3, 5, 10, 11, 12, 13, 14, 18, 19, 21, 22, 23, 24, 25, 41, 48, 51, 68], "get_input": [0, 1, 2, 3], "name": [0, 1, 2, 3, 7, 9, 12, 25, 30, 32, 33, 35, 41, 44, 45, 46, 49, 55, 58, 59, 64, 66, 68, 74, 75, 77, 82, 86, 88, 89, 103, 108, 109, 111], "batch_cntr": [0, 1, 2, 3, 5, 10, 11, 13, 14, 19, 21, 22, 23, 24, 25, 42], "input_data": [0, 1, 2, 3, 18, 19, 21, 22, 23, 24, 25, 28, 42, 48, 51, 68], "target_data": [0, 1, 2, 3, 18, 19, 21, 22, 23, 24, 25, 51, 68], "inputs_batch": [0, 1, 2, 3, 18, 19, 21, 22, 23, 24, 25, 51, 68], "numpi": [0, 1, 2, 3, 9, 28, 30, 33, 37, 39, 42, 45, 46, 48], "break": [0, 1, 2, 3, 4, 5, 10, 11, 13, 14, 19, 21, 22, 23, 24, 25, 30, 33, 42, 48, 51, 68, 90], "subsequ": [0, 2, 13, 14, 18, 51, 68, 81, 86, 101, 103, 106], "compute_encod": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 13, 14, 18, 19, 21, 22, 23, 24, 28, 39, 45, 48, 51, 59, 68, 69, 72, 77, 78, 79, 80, 81, 82, 84, 86, 87, 88, 89, 90], "forward_pass_callback": [0, 1, 2, 3, 5, 10, 11, 12, 13, 14, 18, 19, 21, 22, 23, 24, 25, 28, 33, 37, 39, 41, 45, 46, 48, 59, 66, 68], "forward_pass_callback_arg": [0, 1, 2, 3, 4, 5, 7, 10, 11, 13, 14, 18, 19, 21, 22, 23, 24, 39, 41, 45, 48, 51, 59, 68], "10000": [0, 1, 5, 13, 18, 19, 28, 51, 91], "initi": [0, 1, 5, 11, 12, 13, 18, 19, 23, 24, 25, 28, 44, 51, 68, 69, 77, 78, 79, 80, 88, 89, 91, 105, 108], "phase": [0, 4, 18, 33, 45, 59, 100], "compris": [0, 4, 18, 97], "sensit": [0, 2, 4, 14, 18, 22, 33, 37, 38, 45, 46, 47, 59, 66, 67, 97, 102, 104, 107, 108, 109], "greedili": [0, 4, 18], "select": [0, 4, 18, 28, 42, 51, 68, 71, 73, 74, 75, 92, 95, 104, 108, 111, 114], "bitwidth": [0, 1, 4, 5, 13, 18, 19, 28, 33, 37, 39, 41, 42, 45, 46, 48, 49, 51, 53, 55, 59, 64, 66, 68, 72, 78, 79, 80, 81, 83, 86, 88, 89, 90, 93, 102, 107, 108], "base": [0, 1, 4, 5, 6, 7, 13, 18, 19, 20, 21, 28, 29, 41, 45, 46, 48, 51, 59, 64, 66, 68, 69, 72, 74, 77, 78, 79, 80, 83, 84, 88, 89, 94, 95, 97, 102, 111], "three": [0, 15, 16, 17, 18, 31, 61, 92, 95, 112], "eval_callback_for_phase1": [0, 18, 33, 45, 59], "eval_callback_for_phase2": [0, 18, 33, 45, 59], "callbackfunc": [0, 4, 12, 18, 25, 37, 46, 66], "object": [0, 6, 7, 12, 18, 19, 20, 22, 23, 24, 25, 28, 32, 33, 37, 39, 41, 42, 44, 45, 46, 48, 53, 56, 58, 59, 64, 66, 68, 77, 81, 82, 83, 86, 88, 89, 90, 93, 102, 105, 108], "In": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 30, 34, 35, 37, 38, 42, 46, 49, 51, 52, 53, 56, 59, 60, 61, 62, 66, 67, 68, 72, 77, 83, 88, 90, 91, 95, 97, 100, 102, 103, 105, 106, 108, 111, 112, 114], "reus": [0, 18, 34, 60, 61, 62], "previou": [0, 4, 18, 22, 30, 33, 36, 45, 56, 59, 65, 67, 90, 95, 107], "snippet": [0, 18, 49, 61, 83, 86], "func_callback_arg": [0, 18, 33, 45, 46, 59, 66], "measur": [0, 15, 16, 17, 18, 30, 33, 45, 46, 56, 59, 66], "score": [0, 1, 2, 3, 4, 6, 7, 20, 21, 30, 33, 42, 45, 46, 51, 53, 56, 59, 66, 70, 97, 100, 111], "respecit": [0, 18], "both": [0, 4, 11, 17, 18, 23, 24, 35, 49, 51, 61, 66, 68, 69, 72, 73, 78, 83, 86, 87, 88, 100, 102, 103, 105, 106, 107, 108, 110, 111, 114], "qualiti": [0, 18], "slightli": [0, 18], "goal": [0, 18, 37, 42, 46, 53, 66, 92], "rough": [0, 18], "wherea": [0, 18, 59, 90, 108], "callbak": [0, 18], "impli": [0, 18, 45, 59], "flexibl": [0, 18], "than": [0, 1, 5, 7, 8, 18, 19, 21, 29, 30, 36, 41, 49, 51, 52, 56, 59, 61, 62, 65, 68, 72, 83, 86, 90, 95, 99, 105, 106], "smaller": [0, 13, 18, 33, 41, 45, 51, 52, 59, 98, 107, 110, 113], "indirect": [0, 18], "sqnr": [0, 4, 18, 45, 59, 84, 108], "between": [0, 13, 18, 28, 30, 36, 41, 45, 46, 51, 53, 56, 58, 59, 65, 66, 68, 72, 75, 83, 88, 103, 104, 106, 108], "faster": [0, 6, 7, 13, 18, 20, 33, 84, 98], "correl": [0, 18], "metric": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 22, 23, 24, 25, 30, 37, 39, 51, 56, 68, 104, 108], "aimet_torch": [0, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 51, 52, 53, 54, 55, 56, 57, 58, 59, 61, 62, 64, 65, 66, 68, 69, 70, 71, 73, 74, 75, 77, 78, 79, 80, 81, 82, 83, 84, 86, 87, 88, 89, 90, 101], "mixed_precision_algo": [0, 4, 18, 45, 59], "evalcallbackfactori": [0, 18, 45, 59], "forward_one_batch": [0, 18], "label": [0, 4, 5, 6, 7, 10, 11, 13, 18, 20, 30, 33, 37, 46, 51, 53, 66, 68, 104, 105], "eval_callback_factori": [0, 18], "forward_fn": [0, 1, 7, 18, 21, 41, 45, 51, 54, 59, 86], "small": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 18, 19, 20, 22, 23, 24, 25, 51, 68, 93, 98, 102], "hand": [0, 18, 102], "miou": [0, 18], "full": [0, 1, 2, 3, 4, 5, 7, 10, 11, 14, 18, 19, 21, 22, 23, 24, 30, 33, 34, 38, 60, 67, 88], "appli": [0, 7, 8, 15, 16, 17, 18, 20, 21, 28, 30, 31, 36, 38, 41, 42, 43, 45, 46, 51, 53, 55, 56, 62, 65, 67, 69, 71, 73, 77, 78, 83, 86, 88, 89, 90, 91, 92, 93, 96, 100, 102, 103, 105, 106, 107, 108, 109, 111, 112], "dummi": [0, 12, 18, 25, 28, 39, 41, 42, 46, 48, 51, 52, 53, 57, 58, 59, 65, 66, 68, 86, 104], "one": [0, 1, 2, 3, 4, 5, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 22, 23, 24, 25, 36, 49, 51, 52, 59, 61, 62, 64, 65, 68, 74, 83, 86, 90, 94, 96, 100, 105, 109, 110, 111, 113], "tupl": [0, 4, 12, 18, 25, 28, 29, 30, 32, 33, 36, 37, 39, 41, 42, 44, 45, 46, 48, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 65, 66, 68, 78, 83, 84, 86, 89], "expect": [0, 7, 15, 16, 17, 18, 21, 30, 34, 36, 37, 39, 41, 45, 46, 48, 51, 52, 56, 59, 61, 62, 66, 68, 82, 84, 86, 90, 100, 102, 104], "group": [0, 18, 36, 74, 83, 106, 108], "list": [0, 4, 7, 9, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 29, 30, 31, 32, 33, 35, 36, 41, 42, 44, 45, 48, 51, 54, 55, 56, 57, 58, 59, 61, 65, 66, 68, 71, 78, 83, 86, 88, 89, 97, 99, 101, 106], "modul": [0, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 30, 33, 34, 41, 45, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 71, 73, 77, 82, 83, 86, 87, 90, 102, 109, 114], "therefor": [0, 4, 7, 8, 9, 18, 33, 45, 59, 64, 90, 95, 103], "might": [0, 1, 4, 5, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 22, 23, 24, 25, 33, 45, 49, 51, 59, 68, 91, 104, 107], "front": [0, 4, 18, 33, 45, 59], "candid": [0, 4, 18, 30, 31, 33, 42, 45, 56, 59, 97, 100], "possibl": [0, 4, 6, 9, 18, 20, 33, 34, 35, 39, 42, 45, 48, 53, 59, 60, 62, 68, 83, 90, 97, 104, 106, 107], "suppos": [0, 4, 18, 33, 45, 59], "combin": [0, 4, 18, 33, 45, 55, 59, 61, 83, 92, 95, 100, 102, 103], "type": [0, 4, 6, 7, 9, 12, 15, 16, 17, 18, 20, 23, 24, 28, 29, 30, 31, 33, 36, 37, 39, 41, 42, 45, 46, 48, 51, 52, 53, 54, 55, 56, 59, 61, 64, 65, 66, 68, 71, 72, 77, 81, 82, 83, 86, 88, 89, 100, 102, 104, 106, 108, 111], "int": [0, 4, 6, 7, 12, 15, 16, 17, 18, 20, 28, 29, 30, 33, 37, 39, 41, 42, 44, 45, 46, 48, 49, 51, 53, 54, 55, 56, 59, 64, 66, 68, 69, 72, 78, 79, 80, 83, 84, 89], "16": [0, 4, 7, 18, 22, 28, 30, 33, 39, 45, 48, 49, 51, 59, 61, 64, 68, 69, 73, 77, 78, 79, 80, 83, 84, 86, 88, 89], "quantizationdatatyp": [0, 4, 18, 33, 39, 45, 48, 59, 68, 72], "allowed_accuracy_drop": [0, 4, 6, 18, 20, 33, 42, 45, 53, 59], "maximum": [0, 4, 5, 6, 7, 12, 13, 14, 18, 25, 28, 33, 42, 45, 51, 59, 68, 78, 79, 80, 84], "allow": [0, 4, 6, 8, 18, 20, 30, 32, 33, 35, 38, 39, 42, 44, 45, 47, 49, 56, 58, 59, 60, 61, 67, 68, 81, 83, 92, 100, 107, 108, 109, 111], "drop": [0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 33, 42, 45, 59, 67, 68, 88, 92, 95, 100, 103, 104, 105, 107, 108], "plot": [0, 4, 12, 18, 25, 33, 45, 59, 71, 82, 104], "till": [0, 4, 18, 33, 45, 59], "met": [0, 4, 18, 33, 45, 59], "complet": [0, 4, 15, 16, 17, 18, 30, 33, 45, 59, 90, 93, 107], "pick": [0, 4, 18, 30, 33, 35, 36, 45, 56, 59, 95, 97], "results_dir": [0, 4, 12, 18, 25, 33, 37, 42, 45, 46, 53, 59, 66, 71], "cach": [0, 4, 18, 33, 42, 45, 53, 59, 75], "intermedi": [0, 4, 18, 32, 33, 44, 45, 52, 58, 59, 68, 108], "clean_start": [0, 4, 18, 33, 45, 59], "inform": [0, 4, 18, 21, 33, 36, 45, 49, 55, 59, 62, 65, 67, 72, 81, 86, 102], "delet": [0, 4, 18, 33, 45, 59, 104], "prior": [0, 4, 18, 19, 22, 23, 24, 33, 45, 59], "start": [0, 4, 7, 8, 9, 10, 11, 12, 13, 15, 16, 17, 18, 21, 23, 24, 25, 28, 30, 33, 35, 41, 45, 51, 56, 59, 61, 62, 68, 78, 90, 91, 95, 96, 106, 108], "analysi": [0, 4, 8, 15, 16, 17, 18, 30, 33, 37, 45, 46, 56, 59, 66, 100, 107], "applic": [0, 1, 4, 5, 6, 10, 11, 12, 13, 14, 18, 19, 22, 30, 31, 33, 36, 37, 39, 45, 49, 59, 65, 101], "respons": [0, 4, 18, 33, 45, 59, 100], "flag": [0, 4, 18, 33, 36, 42, 45, 53, 59, 61, 68, 72, 82, 89], "anyth": [0, 4, 12, 18, 25, 33, 45, 59], "compar": [0, 4, 7, 8, 9, 12, 18, 21, 25, 33, 45, 52, 59, 61, 71, 83, 86, 90, 102, 104, 105, 112], "use_all_amp_candid": [0, 18, 45, 59], "supported_kernel": [0, 18, 45, 59], "field": [0, 18, 45, 49, 59], "config": [0, 13, 18, 39, 45, 46, 59, 66, 106, 109], "under": [0, 18, 31, 33, 45, 59, 72, 82, 83, 86, 104, 106], "op_typ": [0, 7, 18, 45, 59, 106], "section": [0, 7, 18, 20, 45, 52, 59, 62, 74, 75, 83, 93, 102, 108], "ignor": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 22, 23, 24, 25, 30, 45, 51, 55, 56, 59, 61, 68, 90], "continu": [0, 18, 35, 45, 59, 62, 68, 102, 103, 105, 107], "amp_search_algo": [0, 18, 33, 45, 59], "ampsearchalgo": [0, 18, 33, 45, 59], "search": [0, 7, 8, 10, 11, 15, 16, 17, 18, 21, 23, 24, 26, 28, 33, 42, 45, 51, 59, 68, 84, 105, 106], "binari": [0, 18, 33, 45, 59], "interpol": [0, 18, 33, 97], "bruteforc": [0, 18, 33], "phase1_optim": [0, 18, 33, 45, 59], "implement": [0, 18, 32, 37, 39, 42, 44, 46, 53, 58, 66, 68, 69, 77, 101, 102, 107], "either": [0, 5, 13, 15, 16, 17, 18, 26, 30, 36, 51, 56, 60, 64, 83, 91, 114], "optmiz": [0, 18], "phase1": [0, 18, 33, 45, 59], "001": [0, 18, 39], "p": [0, 18, 74, 84], "store": [0, 4, 18, 28, 39, 41, 51, 64, 68, 81, 83, 86], "final": [0, 4, 7, 8, 12, 18, 21, 25, 30, 35, 45, 56, 59, 62, 70, 75, 83, 94, 95, 97, 105, 107], "after": [0, 1, 2, 4, 5, 7, 8, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 28, 29, 36, 42, 46, 51, 53, 54, 61, 62, 65, 66, 68, 71, 77, 84, 86, 88, 90, 91, 92, 93, 95, 96, 100, 102, 107, 111, 112], "multipli": [0, 18, 88, 95, 100], "mac": [0, 15, 16, 17, 18, 30, 56, 70, 95, 100, 110, 113], "therebi": [0, 18], "lesser": [0, 18], "re": [0, 9, 18, 33, 38, 45, 59, 67, 90, 96, 102], "mixed_precis": [0, 4, 18, 33, 45, 59], "choose_mixed_precis": [0, 4, 18, 33, 45, 59], "pareto_front_list": [0, 18, 45, 59], "next": [0, 2, 4, 7, 8, 13, 18, 21, 36, 51, 64, 65, 68, 74, 90, 105, 107, 108], "step": [0, 2, 3, 4, 6, 7, 8, 12, 13, 18, 21, 25, 33, 36, 42, 46, 51, 53, 54, 61, 64, 66, 68, 78, 84, 86, 87, 90, 91, 92, 93, 94, 95, 96, 97, 100, 102, 103, 105, 107], "would": [0, 4, 7, 12, 13, 18, 21, 25, 30, 31, 35, 51, 57, 68, 72, 83, 84, 106, 109], "actual": [0, 4, 7, 9, 18, 21, 32, 37, 42, 44, 46, 51, 53, 58, 63, 66, 68, 83], "take": [0, 4, 6, 7, 9, 12, 13, 14, 15, 16, 17, 18, 21, 25, 33, 36, 45, 51, 56, 59, 65, 68, 77, 83, 90, 97, 100, 102, 103, 105, 107, 114], "o": [0, 1, 4, 5, 6, 7, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 33, 56], "makedir": [0, 1, 4, 5, 7, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24], "exist_ok": [0, 1, 4, 5, 7, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24], "filename_prefix": [0, 1, 4, 5, 7, 13, 14, 18, 19, 20, 21, 22, 23, 24, 28, 33, 39, 41, 48, 51, 64, 68], "resnet18_mixed_precis": [0, 18], "hope": [0, 4, 7, 8, 13, 18, 21], "wa": [0, 1, 4, 5, 7, 8, 9, 13, 15, 17, 18, 19, 21, 30, 32, 44, 49, 51, 56, 58, 64, 81, 100], "understand": [0, 4, 7, 8, 9, 12, 13, 18, 21, 25, 72, 102, 112], "qat": [0, 3, 8, 13, 18, 28, 29, 41, 48, 51, 54, 63, 67, 86, 90, 91, 93, 96, 98, 102, 107, 108, 109], "learn": [0, 1, 2, 3, 5, 6, 7, 8, 9, 10, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 28, 29, 30, 31, 39, 41, 42, 43, 51, 53, 54, 55, 56, 57, 66, 68, 72, 93, 96, 100, 102, 105, 108, 109], "addit": [0, 7, 8, 9, 12, 13, 18, 21, 25, 49, 68, 73, 77, 83, 86, 102, 105, 106, 109], "resourc": [0, 7, 8, 9, 13, 18, 21], "doc": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 61, 64, 104], "know": [0, 7, 8, 13, 18, 21, 77], "thi": [1, 2, 3, 5, 6, 7, 8, 9, 10, 11, 14, 15, 16, 17, 19, 20, 22, 23, 24, 26, 28, 30, 31, 32, 33, 34, 35, 36, 37, 39, 41, 42, 43, 44, 45, 46, 48, 49, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 68, 69, 71, 72, 73, 74, 75, 77, 78, 79, 80, 81, 82, 83, 84, 86, 88, 89, 90, 91, 92, 94, 95, 97, 98, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 111, 114], "notebook": [1, 2, 3, 5, 6, 7, 8, 9, 10, 11, 14, 15, 16, 17, 19, 20, 22, 23, 24], "contain": [1, 2, 3, 5, 6, 10, 11, 12, 14, 15, 16, 17, 19, 20, 22, 23, 24, 25, 33, 36, 45, 46, 49, 52, 56, 59, 61, 62, 66, 73, 77, 81, 82, 86, 88, 90, 102, 104, 105, 106, 108], "nearest": [1, 4, 5, 8, 10, 11, 13, 14, 19, 22, 37, 39, 42, 48, 53, 55, 68, 91], "achiev": [1, 5, 13, 19, 30, 56, 74, 83, 91, 95], "i": [1, 2, 3, 5, 6, 7, 8, 9, 10, 11, 14, 15, 16, 17, 19, 20, 22, 23, 24, 26, 28, 30, 31, 33, 34, 35, 36, 37, 38, 39, 41, 42, 43, 44, 45, 46, 48, 49, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 77, 78, 79, 80, 82, 83, 84, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 97, 98, 100, 101, 102, 103, 104, 105, 106, 107, 108, 110, 111, 112, 113, 114], "loss": [1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 13, 14, 19, 22, 23, 24, 28, 37, 39, 41, 46, 51, 66, 68, 81, 87, 90, 91, 98, 100, 102, 104, 108], "function": [1, 2, 4, 5, 8, 12, 13, 14, 15, 16, 17, 19, 21, 22, 23, 24, 25, 28, 29, 30, 31, 33, 34, 35, 36, 37, 38, 39, 41, 42, 43, 45, 46, 47, 48, 51, 52, 53, 54, 55, 56, 57, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 72, 77, 81, 82, 83, 88, 90, 91, 97, 100, 101, 104, 108, 109, 111, 112], "closer": [1, 5, 13, 19, 91], "farther": [1, 5, 19], "high": [1, 2, 3, 5, 10, 11, 14, 15, 16, 17, 19, 22, 23, 24, 31, 33, 36, 43, 45, 57, 59, 65, 72, 87, 91, 95, 97, 98, 103, 109, 112], "level": [1, 3, 4, 5, 8, 10, 11, 15, 16, 17, 19, 23, 24, 31, 43, 57, 72, 87, 95, 97, 98, 102, 107, 111], "simuat": [1, 2, 5, 10, 11, 13, 14, 19, 22, 23, 24], "post": [1, 2, 3, 5, 6, 7, 8, 10, 11, 13, 14, 15, 16, 17, 19, 20, 21, 22, 23, 24, 38, 42, 47, 48, 49, 53, 67, 87, 90, 91, 92, 98, 100, 105, 108, 109], "finetun": [1, 2, 5, 6, 7, 13, 14, 15, 16, 17, 19, 21, 23, 24, 48, 68], "paramet": [1, 2, 3, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 19, 20, 21, 22, 23, 24, 25, 29, 32, 33, 35, 36, 37, 38, 39, 42, 43, 44, 45, 46, 47, 48, 49, 52, 53, 54, 55, 57, 58, 59, 61, 62, 64, 65, 66, 67, 68, 70, 71, 72, 77, 78, 79, 80, 81, 82, 83, 84, 88, 89, 90, 93, 94, 100, 101, 102, 103, 104, 105, 106, 112], "fine": [1, 2, 3, 5, 6, 8, 10, 11, 14, 19, 20, 22, 23, 24, 26, 30, 39, 56, 64, 68, 87, 95, 98, 102, 105, 108], "tune": [1, 2, 3, 5, 6, 8, 10, 11, 14, 19, 20, 22, 23, 24, 26, 30, 39, 56, 64, 68, 87, 95, 98, 102, 105, 108], "epoch": [1, 2, 3, 5, 6, 7, 8, 10, 11, 14, 15, 16, 17, 19, 20, 21, 22, 23, 24, 39, 54, 56, 68, 90, 98, 100, 105], "improv": [1, 2, 3, 5, 6, 7, 8, 10, 11, 14, 15, 16, 17, 19, 20, 21, 22, 23, 24, 26, 51, 68, 83, 90, 95, 100, 102, 105, 107, 112], "otherwis": [1, 2, 3, 5, 6, 10, 11, 14, 15, 16, 17, 19, 20, 22, 23, 24, 42, 48, 62, 64, 68, 74, 75, 78, 83, 89, 107], "One": [1, 2, 3, 4, 12, 15, 16, 17, 18, 19, 20, 22, 23, 24, 25, 37, 39, 90], "run": [1, 2, 3, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 19, 21, 22, 23, 24, 25, 30, 32, 33, 35, 37, 38, 39, 41, 42, 44, 45, 48, 49, 52, 53, 54, 56, 58, 59, 61, 62, 68, 72, 74, 75, 78, 83, 88, 89, 93, 98, 100, 102, 103, 104, 108, 109, 111], "two": [1, 2, 3, 4, 5, 6, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 19, 20, 22, 23, 24, 25, 30, 33, 35, 36, 56, 59, 61, 62, 65, 72, 73, 83, 90, 97, 98, 100, 102, 103, 104, 105, 108, 110, 112, 113], "thing": [1, 2, 3, 5, 6, 13, 14, 15, 16, 17, 19, 22, 23, 24], "put": [1, 2, 3, 5, 6, 7, 12, 13, 14, 15, 16, 17, 19, 21, 22, 23, 24, 25, 59, 102], "still": [1, 2, 3, 5, 6, 7, 12, 13, 14, 15, 16, 17, 19, 21, 22, 23, 24, 25, 34, 67, 83, 102, 107], "interfac": [1, 2, 3, 5, 6, 7, 12, 13, 14, 15, 16, 17, 19, 21, 22, 23, 24, 25, 67, 73], "method": [1, 2, 3, 5, 6, 7, 8, 9, 12, 13, 14, 15, 16, 17, 19, 21, 22, 23, 24, 25, 32, 33, 39, 42, 44, 55, 58, 59, 61, 68, 72, 77, 83, 86, 88, 90, 97, 100, 102, 107, 108], "abl": [1, 2, 3, 5, 6, 7, 9, 12, 13, 14, 15, 16, 17, 19, 21, 22, 23, 24, 25, 35, 46, 61, 62, 66, 81, 90], "exist": [1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 19, 21, 22, 23, 24, 25, 45, 51, 59, 68, 74, 77, 83, 88, 108], "degrad": [1, 2, 3, 5, 10, 11, 14, 19, 22, 23, 24], "platform": [1, 2, 3, 5, 10, 11, 14, 19, 22, 23, 24, 73, 91, 102, 108], "call": [1, 2, 3, 5, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 19, 22, 23, 24, 25, 29, 30, 31, 33, 34, 35, 36, 42, 45, 46, 49, 51, 56, 57, 59, 61, 65, 66, 68, 77, 79, 80, 81, 83, 88, 90, 102, 104, 106, 108, 109, 110, 113], "kei": [1, 2, 3, 5, 9, 10, 11, 14, 15, 16, 17, 19, 22, 23, 24, 36, 49, 65], "precis": [1, 2, 3, 5, 7, 8, 10, 11, 12, 13, 14, 19, 21, 22, 23, 24, 25, 49, 51, 78, 79, 80, 87, 89, 102], "api": [1, 2, 3, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 19, 20, 21, 22, 23, 24, 25, 34, 60, 63, 72, 74, 82, 90, 96, 98, 101, 102, 106, 109, 111], "explan": [1, 2, 3, 5, 10, 11, 14, 19, 22, 23, 24], "copi": [1, 18, 19, 22, 23, 24, 35, 39, 68, 71, 96, 108], "deepcopi": [1, 71], "must": [1, 2, 3, 5, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 19, 22, 23, 24, 25, 35, 51, 83, 86, 88, 92, 93, 95, 98, 99, 102, 104, 106, 114], "comput": [1, 2, 3, 5, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 19, 22, 23, 24, 25, 28, 30, 32, 33, 37, 39, 41, 42, 44, 45, 46, 48, 49, 51, 53, 56, 58, 59, 63, 64, 66, 68, 69, 73, 75, 77, 79, 80, 83, 84, 86, 90, 91, 100, 101, 103, 104, 108, 111, 114], "encod": [1, 2, 3, 5, 6, 7, 8, 10, 11, 13, 14, 19, 20, 22, 23, 24, 28, 32, 33, 37, 39, 41, 42, 44, 45, 46, 48, 51, 53, 54, 58, 59, 63, 64, 66, 67, 68, 69, 72, 77, 78, 81, 83, 86, 87, 89, 90, 91, 93, 102, 104, 105, 109], "write": [1, 2, 3, 5, 10, 11, 14, 19, 22, 23, 24, 41, 48, 51, 68, 83, 86], "loader": [1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 15, 17, 19, 21, 22, 23, 24, 25, 33, 37, 41, 45, 46, 48, 51, 54, 55, 59, 66, 68, 90, 91], "extract": [1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 19, 22, 23, 24, 25, 51, 68, 103], "regard": [1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 19, 22, 23, 24, 25, 33, 45, 51, 59, 68], "veri": [1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 14, 19, 20, 22, 23, 24, 25, 51, 68, 69, 95, 100, 104, 112], "percentag": [1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 19, 22, 23, 24, 25, 51, 68], "1m": [1, 2, 3, 4, 5, 10, 11, 12, 13, 14, 19, 22, 23, 24, 25, 51, 68], "500": [1, 2, 3, 4, 5, 10, 11, 12, 13, 14, 19, 20, 22, 23, 24, 25, 33, 42, 51, 56, 68, 90, 91, 103, 104], "suffic": [1, 2, 3, 5, 10, 11, 14, 19, 22, 23, 24], "reason": [1, 2, 3, 5, 10, 11, 14, 19, 22, 23, 24, 62], "scenario": [1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 19, 22, 23, 24, 25, 51, 68, 93, 114], "That": [1, 2, 3, 5, 10, 11, 14, 19, 22, 23, 24, 114], "pictur": [1, 2, 3, 4, 5, 10, 11, 12, 13, 14, 19, 22, 23, 24, 25, 51, 68, 87], "captur": [1, 2, 3, 4, 5, 10, 11, 12, 13, 14, 19, 22, 23, 24, 25, 32, 44, 51, 58, 61, 68], "night": [1, 2, 3, 4, 5, 10, 11, 12, 13, 14, 19, 22, 23, 24, 25, 51, 68], "skew": [1, 2, 3, 5, 10, 11, 14, 19, 22, 23, 24], "5": [1, 2, 3, 4, 5, 8, 10, 11, 13, 14, 15, 16, 17, 19, 22, 23, 24, 30, 41, 42, 45, 53, 54, 56, 59, 61, 64, 68, 69, 70, 72, 73, 78, 79, 80, 83, 88, 89, 95, 105, 107], "comparison": [1, 2, 3, 19, 22, 23, 24, 32, 44, 58], "order": [1, 7, 8, 9, 10, 11, 12, 15, 16, 17, 19, 21, 23, 24, 25, 34, 36, 38, 60, 62, 65, 67, 68, 74, 75, 77, 83, 88, 90, 93, 94, 102, 105, 106], "vector": [1, 5, 13, 19, 51, 86], "num_batch": [1, 2, 5, 6, 7, 12, 13, 19, 20, 21, 22, 25, 28, 37, 41, 42, 46, 51, 53, 54, 66], "2000": [1, 5, 6, 13, 19, 20, 22, 41, 42, 51, 53, 78, 81], "size": [1, 5, 6, 7, 8, 9, 13, 19, 33, 35, 39, 46, 48, 51, 52, 53, 62, 66, 68, 77, 78, 83, 86, 88, 89, 91, 101, 110, 113], "default_num_iter": [1, 5, 13, 19, 20, 28, 41, 51], "strongli": [1, 5, 13, 19, 35, 51, 61], "least": [1, 5, 19, 59], "adaround_weight": [1, 5, 6, 13, 19, 20, 28, 41, 42, 51, 53, 67, 72], "adaroundparamet": [1, 5, 6, 13, 19, 20, 28, 41, 42, 51, 53, 67], "satisfi": [1, 6, 20, 61, 83, 90, 92], "signatur": [1, 15, 16, 17, 28, 30, 37, 42, 46, 56, 66, 77, 78], "deriv": [1, 4, 18, 49, 78, 89, 108], "form": [1, 12, 25, 35, 69], "arrai": [1, 83], "__init__": [1, 9, 20, 34, 35, 42, 52, 53, 56, 60, 61, 62, 69, 77, 88, 90], "self": [1, 9, 20, 34, 35, 52, 53, 56, 60, 61, 62, 69, 77, 81, 90], "_torch_data_load": 1, "_iter": 1, "__iter__": 1, "__next__": 1, "__len__": [1, 20, 46, 53, 66], "len": [1, 4, 8, 18, 20, 30, 33, 41, 42, 51, 53, 61], "ada_model": [1, 5, 13, 19], "apply_adaround": [1, 5, 13, 19, 28, 41, 51], "default_quant_schem": [1, 5, 13, 19, 28, 41, 51], "about": [1, 2, 3, 4, 5, 6, 9, 10, 11, 14, 15, 16, 17, 19, 20, 21, 22, 23, 24, 28, 30, 31, 36, 39, 41, 42, 43, 49, 51, 53, 55, 56, 57, 65, 66, 67, 68, 81, 90, 98, 104], "biwidth": [1, 5, 13, 19], "freez": [1, 5, 13, 19, 28, 51, 64, 72, 91], "set_and_freeze_param_encod": [1, 5, 13, 19, 28, 41, 51], "dure": [1, 3, 5, 7, 10, 11, 12, 13, 14, 15, 16, 17, 19, 21, 23, 24, 25, 28, 29, 30, 33, 35, 41, 42, 45, 51, 56, 59, 68, 70, 77, 82, 86, 88, 90, 91, 98, 100, 102, 105, 106, 108, 111, 112], "intern": [1, 5, 8, 9, 13, 19, 35, 42, 48, 51, 53, 68, 69, 72, 84, 100, 103, 106], "maintain": [1, 5, 19, 42, 97, 100], "alter": [1, 5, 13, 19, 51], "negat": [1, 5, 19], "encoding_path": [1, 5, 6, 13, 19, 20, 28, 42, 51, 53], "join": [1, 5, 10, 11, 13, 18, 19, 20, 56, 70], "littl": [1, 5, 10, 11, 14, 15, 16, 17, 19, 22, 23, 24, 100], "gain": [1, 5, 10, 11, 13, 14, 15, 16, 17, 19, 22, 23, 24, 94, 95, 100], "experi": [1, 5, 10, 11, 14, 15, 16, 17, 19, 22, 23, 24, 30, 56, 83, 100], "hyper": [1, 5, 7, 8, 10, 11, 14, 15, 16, 17, 19, 21, 22, 23, 24, 68, 105], "better": [1, 5, 10, 11, 13, 14, 15, 16, 17, 19, 21, 22, 23, 24, 52, 71, 83, 91, 92, 100, 102, 103, 105], "updat": [1, 3, 5, 9, 10, 11, 13, 14, 19, 20, 22, 23, 24, 49, 51, 52, 68, 70, 72, 75, 84, 89, 96, 102, 103, 105, 108, 109, 111], "without": [1, 5, 6, 8, 10, 11, 13, 14, 19, 20, 22, 23, 24, 39, 51, 64, 68, 79, 80, 81, 82, 83, 86, 92, 102, 105, 108, 114], "resnet18_after_adaround": 1, "bia": [2, 7, 14, 31, 36, 43, 52, 57, 61, 62, 64, 65, 67, 69, 72, 77, 79, 80, 88, 90, 91, 94, 102, 103, 106, 107, 109], "correct": [2, 13, 14, 20, 25, 36, 51, 53, 65, 67, 75, 90, 91, 102, 103, 107], "bc": [2, 91], "help": [2, 12, 14, 22, 25, 52, 62, 64, 68, 71, 91, 97, 100, 102, 103, 104, 105, 107, 112], "recov": [2, 14, 15, 16, 17, 22, 87, 98, 107, 108], "oppos": [2, 14, 22], "conv": [2, 7, 14, 22, 28, 29, 36, 41, 51, 54, 55, 61, 65, 71, 83, 99, 106, 109, 110, 113, 114], "immedi": [2, 6, 14, 20, 22], "consecut": [2, 14, 22, 36, 64, 65, 102, 103], "five": [2, 22], "sake": [2, 22, 32, 44, 58], "procedur": [2, 14, 15, 17, 22, 97, 111], "cl": [2, 14, 22, 36, 65, 77, 109], "skip": [2, 14, 22, 31, 33, 41, 51, 53, 55, 74, 94], "absorpt": [2, 14, 22], "hba": [2, 14, 22], "again": [2, 13, 14, 15, 16, 17, 22, 104, 105], "cross_layer_equ": [2, 14, 22, 31, 36, 43, 57, 65, 71, 72, 101], "equalize_model": [2, 14, 22, 31, 43, 57, 71, 72, 101], "free": [2, 7, 8, 14, 21, 22, 68, 74, 103], "iccv": [2, 14, 22, 100, 103], "2019": [2, 14, 22, 103], "add": [3, 7, 10, 11, 15, 16, 17, 23, 24, 34, 35, 39, 49, 60, 61, 62, 64, 68, 74, 77, 88, 90, 106, 108, 109, 114], "ml": [3, 8, 10, 11, 23, 24, 26, 68, 100, 102, 103], "standard": [3, 8, 10, 11, 23, 24, 33, 61, 68, 71, 79, 80, 88], "acceler": [3, 8, 10, 11, 23, 24, 56, 68, 73, 87, 98, 100], "min": [3, 10, 11, 13, 37, 46, 49, 64, 66, 71, 72, 78, 82, 84, 89, 90, 104, 108], "max": [3, 10, 11, 13, 37, 46, 49, 64, 66, 71, 72, 78, 79, 80, 82, 84, 89, 90, 100, 103, 104, 108], "onc": [3, 8, 10, 11, 15, 16, 17, 22, 23, 24, 34, 60, 62, 64, 68, 77, 93, 94, 100, 104, 105, 108], "effect": [3, 8, 10, 11, 23, 24, 28, 29, 39, 41, 51, 54, 64, 68, 83, 88, 90, 93, 102, 104, 108], "keep": [3, 10, 61, 68, 106], "constant": [3, 10, 23, 24, 42, 53, 61, 68, 97, 102], "4": [3, 8, 12, 15, 16, 17, 20, 25, 28, 29, 36, 37, 41, 42, 45, 46, 51, 53, 54, 55, 56, 61, 64, 65, 66, 68, 69, 72, 78, 81, 83, 90, 93, 97, 102, 107, 114], "layer": [4, 8, 15, 16, 17, 28, 29, 30, 33, 34, 35, 37, 38, 39, 41, 42, 46, 47, 48, 51, 52, 53, 54, 55, 56, 60, 62, 63, 64, 66, 67, 68, 69, 70, 71, 77, 82, 83, 86, 88, 90, 91, 92, 93, 94, 95, 96, 99, 101, 102, 104, 106, 107, 108, 109, 110, 111, 112, 113, 114], "an": [4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 29, 30, 31, 33, 34, 35, 37, 39, 41, 42, 45, 46, 48, 49, 51, 53, 54, 55, 56, 57, 59, 60, 61, 62, 66, 68, 69, 72, 73, 77, 81, 82, 83, 87, 88, 89, 90, 91, 92, 94, 95, 97, 98, 100, 101, 102, 104, 105, 106, 107, 108, 112, 114], "resnet50": [4, 5, 6, 10, 11, 12, 13, 14, 30, 31, 33, 36, 37, 39], "disabl": [4, 15, 17, 37, 45, 46, 64, 66, 68, 72, 88, 97, 100, 104, 106, 108], "log": [4, 7, 8, 10, 11, 28, 33, 62, 104], "info": [4, 36, 52, 55, 62, 65, 90, 109], "verbos": 4, "displai": [4, 8, 96, 104, 111, 112], "erorr": 4, "tensorflow": [4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 25, 26, 73, 74, 93, 96, 98, 99, 102, 106, 108, 109], "messag": 4, "error": [4, 33, 35, 42, 53, 61, 77, 92, 102, 104, 105, 107, 108], "critic": 4, "tf_cpp_min_log_level": [4, 6, 7, 10, 11, 33], "compat": [4, 7, 8, 33, 49, 60, 73, 83, 90], "v1": [4, 18, 19, 20, 21, 22, 23, 24, 25, 33, 51, 53, 55, 58, 59, 66, 67, 68, 69, 72], "set_verbos": [4, 33], "evlauat": 4, "kera": [4, 5, 6, 10, 11, 12, 13, 14, 26, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 91, 93, 96, 98, 102, 103, 104, 106, 108, 109], "preprocess_input": [4, 5, 10, 11, 13, 14, 30, 33], "decode_predict": [4, 30, 33], "center_crop": [4, 33], "img_height": 4, "256": [4, 18, 33, 37, 46, 66, 86, 90, 104], "img_width": 4, "crop_length": 4, "start_x": 4, "start_i": 4, "cropped_imag": 4, "get_eval_func": [4, 30, 33], "num_iter": [4, 30, 33], "50000": [4, 30, 33], "debug": [4, 26, 27, 28, 32, 40, 44, 49, 50, 58, 72, 90, 107], "get_top5_acc": 4, "func_wrapp": [4, 30, 33], "validation_d": [4, 30, 33], "preprocess": [4, 5, 8, 10, 11, 13, 30, 33], "image_dataset_from_directori": [4, 5, 10, 11, 13, 30, 33], "label_mod": [4, 5, 10, 11, 13, 30, 33], "categor": [4, 5, 10, 11, 13, 30, 33], "shuffl": [4, 5, 10, 11, 13, 30, 33, 56, 90], "top1": [4, 20, 30, 33], "top5": 4, "total": [4, 9, 30, 33, 90, 97, 108], "img": [4, 30, 33], "pred": [4, 18, 30, 33, 42], "predict": [4, 12, 30, 32, 33, 37, 53], "np": [4, 9, 28, 30, 33, 35, 37, 39, 42, 45, 46, 48], "class_nam": [4, 9, 30, 33], "cnt": [4, 30, 33], "sum": [4, 18, 20, 30, 33, 53, 90], "b": [4, 30, 33, 54, 64, 77, 78, 89], "zip": [4, 30, 33, 37], "str": [4, 9, 28, 30, 32, 33, 37, 39, 41, 42, 44, 45, 46, 48, 51, 53, 55, 58, 59, 60, 61, 64, 66, 68, 71, 82, 86], "eval_func": [4, 12, 30, 33, 70], "aimet_tensorflow": [4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 28, 29, 30, 31, 32, 33, 35, 36, 37, 39, 73, 75], "fold_all_batch_norm": [4, 5, 10, 11, 13, 14, 18, 19, 22, 23, 24, 33, 36, 65, 71, 90], "get_model": [4, 33, 34], "include_top": [4, 5, 13, 14, 33], "input_tensor": [4, 5, 13, 14, 33, 35, 48, 59, 61, 84], "pool": [4, 5, 7, 13, 14, 33], "batch": [4, 6, 7, 15, 16, 17, 21, 28, 29, 30, 32, 33, 36, 37, 41, 44, 45, 46, 48, 51, 52, 54, 58, 59, 65, 66, 68, 91, 102, 103, 104], "norm": [4, 14, 33, 36, 52, 54, 65, 91, 102, 103, 104], "fold": [4, 29, 31, 33, 36, 42, 43, 52, 53, 54, 57, 65, 67, 71, 88, 91, 92, 93, 102, 103, 104, 109], "acccuraci": 4, "fp32_acccuraci": 4, "sim": [4, 7, 8, 13, 20, 28, 29, 33, 41, 42, 45, 46, 51, 53, 54, 55, 59, 63, 64, 66, 72, 82, 83, 86, 87, 90, 105, 108], "rounding_mod": [4, 5, 8, 10, 11, 13, 14, 37, 39, 42, 48, 53, 68], "solut": [4, 18, 97, 105, 107], "less": [4, 18, 52, 83, 84, 94, 97, 106], "convert": [4, 18, 34, 35, 36, 45, 59, 61, 69, 81, 90, 92, 102, 112], "overhead": [4, 15, 17, 18], "fairli": [4, 7, 8, 12, 13, 25, 51, 68], "simpl": [4, 7, 8, 12, 13, 25, 28, 37, 46, 51, 56, 61, 66, 68, 90], "don": [4, 7, 8, 12, 13, 25, 51, 61, 64, 68, 77, 91, 104], "pointer": [4, 7, 8, 12, 13, 25, 51, 68], "done": [4, 9, 13, 21, 34, 74, 78, 89, 100, 106, 108], "defin": [4, 9, 12, 13, 15, 16, 17, 19, 22, 23, 24, 25, 28, 33, 34, 35, 37, 38, 42, 45, 46, 49, 51, 53, 56, 59, 60, 61, 62, 66, 67, 68, 77, 83, 88, 90, 102, 104, 106, 108], "separ": [4, 28, 35, 36, 39, 41, 51, 61, 62, 65, 68, 72, 86, 93, 104, 107, 109], "larg": [4, 64, 95, 105, 110, 113], "enough": [4, 15, 16, 17, 52], "meaning": 4, "give": [4, 8, 12, 13, 15, 16, 17, 25, 33, 51, 68, 69, 100], "ideal": [4, 12, 13, 25, 51, 68], "opt": [4, 86], "01": [4, 6, 20, 28, 41, 42, 51, 53, 78, 91], "discuss": [4, 15, 16, 17, 90, 95, 96, 108], "eval_callback_phase1": 4, "eval_callback_phase2": 4, "forward_pass_call_back": [4, 33, 45, 59], "greedymixedprecisionalgo": [4, 18, 33, 59], "enabl": [4, 11, 13, 15, 17, 18, 24, 26, 30, 33, 37, 45, 46, 54, 56, 59, 64, 66, 72, 73, 74, 83, 87, 93, 98, 102, 104, 106, 108, 109, 111], "enable_convert_op_reduct": [4, 18, 33, 59], "acuraci": [4, 33], "time": [4, 6, 12, 20, 22, 25, 30, 36, 49, 56, 61, 62, 73, 83, 86, 90, 92, 100, 101, 105, 106, 111], "wrapper": [4, 8, 18, 19, 22, 23, 24, 28, 33, 37, 46, 56, 66], "callback": [4, 6, 8, 10, 11, 12, 15, 16, 17, 25, 30, 33, 37, 39, 42, 45, 46, 48, 53, 56, 59, 66, 68, 104, 108], "get_data_loader_wrapp": [4, 33], "dataloader_wrapp": [4, 33], "map": [4, 5, 6, 7, 9, 13, 33, 37, 39, 49, 62, 64, 77, 78, 81, 83, 88, 97, 104, 106], "lambda": [4, 5, 6, 7, 8, 9, 13, 33, 37, 59, 83], "y": [4, 5, 12, 13, 25, 33, 39, 61, 74, 75, 90, 104], "data_loader_wrapp": [4, 33], "choose_fast_mixed_precis": [4, 33], "resnet50_after_amp": 4, "pytorch": [5, 6, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 52, 61, 62, 69, 71, 73, 74, 77, 86, 88, 91, 92, 93, 96, 98, 103, 104, 106, 108, 109], "image_net_dataset": [5, 6, 7, 12, 13, 14], "imagenetdataset": [5, 6, 7, 12, 13, 14], "get_val_dataset": [5, 6, 7, 12, 13, 14], "10": [5, 6, 7, 8, 9, 10, 11, 13, 14, 15, 16, 17, 21, 23, 24, 28, 30, 34, 35, 36, 39, 54, 56, 61, 62, 64, 68, 69, 70, 73, 74, 75, 77, 78, 81, 83, 84, 88, 89, 90, 97, 100, 105], "new": [5, 9, 10, 11, 13, 14, 18, 25, 34, 35, 36, 45, 49, 51, 59, 60, 61, 64, 68, 72, 74, 78, 83, 86, 87, 89, 90, 102, 109], "rest": [5, 10, 11, 13, 14, 107], "progbar": [5, 10, 11, 13, 14], "sim_model": [5, 10, 11, 12, 13, 14, 19, 21, 22, 23, 24, 25, 51, 68], "tf_dataset": [5, 13, 14], "progbar_stat_upd": [5, 10, 11, 13, 14], "equal": [5, 9, 38, 42, 47, 53, 55, 63, 67, 71, 81, 83, 91, 92, 95, 96, 97, 101, 102, 104, 107, 108, 112], "data_set": [5, 13, 28], "ada_round_data": [5, 13], "image_width": [5, 13], "image_height": [5, 13], "resnet50_after_adaround": 5, "offer": [6, 20, 46, 66, 92], "suit": [6, 20, 92], "network": [6, 8, 9, 13, 20, 35, 88, 90, 92, 95, 97, 100, 102, 105, 107, 108, 111, 113], "quantiz": [6, 9, 15, 16, 17, 20, 26, 27, 28, 29, 32, 35, 37, 40, 41, 42, 44, 46, 49, 50, 51, 53, 54, 58, 60, 61, 63, 64, 66, 77, 79, 82, 84, 86, 87, 91, 92, 93, 95, 96, 98, 100, 104, 109, 111], "ptq": [6, 20, 42, 53, 98, 102, 104, 105], "success": [6, 20], "sequenc": [6, 8, 20, 52, 91, 92, 93, 101, 106], "consum": [6, 20, 49, 92, 100], "non": [6, 20, 52, 61, 108, 111], "expert": [6, 20], "effort": [6, 20, 42, 53, 92], "analyz": [6, 20, 30, 38, 47, 56, 67, 78, 87, 88, 89, 92, 94, 101, 104, 111, 112], "automat": [6, 20, 30, 36, 56, 65, 74, 75, 83, 95, 100, 102, 104, 109], "variou": [6, 12, 20, 25, 30, 45, 56, 59, 100, 102, 107, 108, 109, 112], "best": [6, 13, 20, 42, 53, 92, 95, 100, 102, 108], "heurist": [6, 20], "toler": [6, 20, 92, 95], "cumul": [6, 20], "until": [6, 20, 42, 53, 78, 89, 92], "evalu": [6, 8, 20, 28, 30, 33, 37, 39, 42, 45, 46, 48, 51, 53, 56, 59, 66, 68, 70, 90, 92, 96, 97, 100, 102, 104, 105, 108, 111], "creat": [6, 8, 12, 15, 16, 17, 20, 25, 28, 30, 33, 35, 36, 37, 39, 42, 44, 45, 46, 48, 51, 53, 54, 56, 59, 61, 63, 64, 65, 66, 68, 69, 71, 77, 82, 84, 86, 87, 88, 90, 91, 93, 96, 100, 101, 102, 105, 108], "auto_qu": [6, 20, 42, 53], "eval_dataset_s": [6, 7, 20, 42, 53], "5000": [6, 20, 42, 45, 53, 59], "been": [6, 7, 8, 13, 20, 35, 51, 62, 71, 77, 81, 82, 83, 86, 108, 114], "calibration_dataset_s": [6, 20, 42, 53], "20": [6, 7, 8, 9, 10, 11, 21, 23, 24, 28, 30, 35, 41, 49, 51, 68, 73, 91, 105], "eval_dataset": [6, 7, 37, 53], "unlabeled_dataset": [6, 7, 12, 37, 53], "prepar": [6, 29, 34, 37, 38, 42, 46, 51, 53, 60, 64, 66, 67, 68, 69, 92, 102, 109], "eval_callback": [6, 7, 12, 15, 16, 17, 20, 25, 30, 33, 37, 42, 46, 53, 56, 66, 70], "compil": [6, 7, 8, 10, 11, 12, 37, 39, 41, 48], "dictionari": [6, 7, 9, 30, 46, 56, 66, 68, 70, 97, 100, 106], "argument": [6, 7, 12, 25, 28, 32, 33, 37, 39, 41, 44, 45, 46, 48, 51, 58, 59, 61, 66, 68, 77, 79, 80, 83], "num_sampl": [6, 7, 18, 20, 37, 45, 53, 59], "whole": [6, 7, 83, 108], "sampled_dataset": [6, 7, 12], "adam": [6, 7, 8, 10, 11, 12, 37, 39, 90], "categoricalcrossentropi": [6, 7, 12, 37], "categoricalaccuraci": [6, 7, 12, 37], "acc": [6, 7, 8, 12, 37], "unlabeleddatasetwrapp": [6, 20, 53], "indic": [6, 13, 18, 20, 30, 36, 49, 53, 56, 69, 88, 95, 114], "seri": [6, 20, 68], "reach": [6, 20, 92], "furhter": [6, 20], "adaround": [6, 20, 42, 47, 53, 67, 72, 87, 92, 96, 102, 107, 109], "predefin": [6, 20], "were": [6, 13, 20, 32, 36, 44, 49, 51, 58, 64, 65, 68, 75, 86, 95, 106, 114], "empir": [6, 20, 103], "adaround_dataset_s": [6, 20, 42, 53], "adaround_dataset": 6, "adaround_param": [6, 20, 42, 53], "set_adaround_param": [6, 20, 42, 53], "correspond": [6, 13, 20, 28, 29, 32, 36, 41, 44, 45, 46, 51, 54, 58, 59, 64, 65, 66, 68, 73, 74, 75, 83, 86, 88, 94, 104, 108, 114], "counter": [7, 21, 38, 39, 68], "potenti": [7, 21, 36, 38, 52, 101, 111, 112], "instabl": [7, 21, 38], "varianc": [7, 21, 38, 103], "recalcul": [7, 21, 29], "By": [7, 18, 19, 21, 22, 23, 24, 29, 30, 35, 56, 64, 88, 91, 100, 108], "aim": [7, 15, 16, 17, 21, 29], "make": [7, 8, 9, 13, 21, 29, 34, 36, 38, 60, 63, 67, 83, 88, 101, 102], "our": [7, 8, 21, 29, 46, 64, 66, 73, 75, 90], "stabl": [7, 21, 29, 61, 69, 91], "rather": [7, 21, 29, 61, 106], "noisi": [7, 21, 29], "6": [7, 8, 9, 10, 11, 17, 19, 22, 23, 24, 28, 35, 42, 51, 53, 61, 64, 68, 78, 83, 84, 86, 105, 107], "simul": [7, 8, 15, 16, 17, 25, 32, 38, 39, 44, 47, 48, 49, 51, 55, 58, 60, 63, 64, 67, 68, 79, 80, 83, 86, 87, 88, 90, 98, 102, 105, 109], "7": [7, 16, 17, 19, 21, 22, 23, 24, 36, 53, 54, 64, 68, 74, 75, 78, 79, 80, 90, 107, 114], "dir": [7, 12, 13, 14, 48, 69, 75], "accuraci": [7, 8, 12, 20, 21, 25, 26, 28, 30, 32, 33, 39, 41, 42, 44, 45, 51, 53, 56, 58, 59, 64, 68, 83, 87, 90, 91, 92, 95, 97, 98, 100, 102, 103, 104, 105, 107, 108, 109, 112, 114], "helper": [7, 21, 33, 53, 59], "train_dataset_s": 7, "re_estimation_dataset_s": 7, "train_dataset": 7, "re_estimation_dataset": 7, "current": [7, 8, 9, 18, 25, 30, 33, 35, 39, 52, 56, 59, 62, 63, 77, 99, 113], "built": [7, 8, 45, 59, 73, 74, 77, 88], "sequenti": [7, 8, 9, 34, 35, 72, 106, 107], "subclass": [7, 8, 34, 35, 77, 84], "incompat": [7, 8, 90], "backend": [7, 28], "clear_sess": [7, 28], "conv2d": [7, 8, 13, 35, 36, 49, 52, 61, 62, 65, 72, 77, 83, 88, 90, 94, 100, 109, 114], "conv1": [7, 15, 16, 17, 35, 52, 56, 60, 61, 62, 65, 70, 90], "fuse": [7, 106, 108], "relu": [7, 8, 9, 34, 35, 36, 49, 52, 55, 60, 61, 62, 65, 69, 72, 88, 90, 103, 106, 114], "maxpooling2d": 7, "conv2": [7, 35, 49, 56, 60, 61, 65, 83, 90], "flatten": [7, 61, 88], "dens": [7, 8, 9, 34, 35, 36, 69], "functional_model": [7, 8, 9], "fp32": [7, 8, 25, 32, 33, 37, 44, 45, 46, 58, 59, 64, 66, 91, 98, 103, 104, 105, 107, 108], "baselin": [7, 8, 20, 33, 45, 59, 90, 97, 100, 105], "loss_fn": [7, 90], "fit": [7, 8, 10, 11, 21, 30, 39, 56, 68, 97], "test": [7, 8, 9, 37, 46, 52, 54, 66, 69, 75], "training_range_learning_with_tf_init": [7, 11, 21, 24, 28, 51, 68], "json": [7, 12, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114], "default_config_per_channel": 7, "is_output_quant": [7, 106], "is_quant": [7, 106], "is_symmetr": [7, 49, 84, 106], "strict_symmetr": [7, 106], "unsigned_symmetr": [7, 106], "per_channel_quant": [7, 13, 49, 88, 106], "squeez": [7, 18], "pad": [7, 35, 52, 61, 62, 90], "supergroup": [7, 106, 109], "op_list": [7, 106], "clip": [7, 84, 106, 108], "gemm": [7, 106], "model_input": [7, 62, 106], "is_input_quant": [7, 106], "model_output": [7, 106], "open": 7, "tmp": [7, 12, 25, 37, 42, 46, 53, 66, 90], "w": [7, 33, 45, 46, 59, 66, 74, 114], "f": [7, 20, 42, 53, 61, 62, 73, 74, 75, 90], "dump": 7, "qsim": [7, 29, 69], "config_fil": [7, 12, 13, 25, 28, 37, 39, 42, 46, 48, 53, 55, 66, 68], "posit": [7, 8, 9, 35, 78], "15": [7, 8, 10, 11, 21, 23, 24, 68, 78, 100, 105], "job": [7, 8, 10, 11, 15, 16, 17, 21, 23, 24, 68], "good": [7, 8, 10, 11, 15, 16, 17, 21, 23, 24, 35, 64, 67, 68, 90, 91, 100], "rate": [7, 8, 9, 10, 11, 15, 16, 17, 21, 23, 24, 35, 68, 100, 105], "end": [7, 8, 10, 11, 15, 16, 17, 21, 23, 24, 28, 29, 31, 33, 51, 53, 54, 57, 61, 62, 66, 68, 78, 89, 90, 100], "factor": [7, 8, 10, 11, 15, 16, 17, 21, 23, 24, 36, 65, 68, 83, 84, 95, 100, 103], "feel": [7, 8, 21, 68, 74], "quantized_callback": [7, 8, 10, 11], "tensorboard": [7, 8, 10, 11], "log_dir": [7, 8, 10, 11], "histori": [7, 8, 10, 11], "validation_data": [7, 8, 10, 11], "reestimate_bn_stat": [7, 21, 29, 54], "reestim": [7, 29], "100": [7, 21, 29, 33, 45, 53, 54, 59, 72, 84, 86, 90], "adapt": [7, 13, 21, 38, 54, 64, 67, 87, 90, 91, 96, 102, 104, 109], "yield": [7, 21, 45, 46, 51, 54, 59, 66, 95, 107, 108], "directli": [7, 21, 29, 42, 46, 63, 66, 72, 104, 108], "bn_reestim": [7, 21, 29, 54], "far": [7, 21, 91], "first": [7, 8, 9, 12, 13, 15, 16, 17, 21, 25, 30, 35, 38, 51, 61, 67, 69, 88, 90, 100, 102, 105, 107], "effici": [7, 21, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114], "fold_all_batch_norms_to_scal": [7, 21, 29, 54], "mnist_after_bn_re_estimation_qat_range_learn": 7, "exampl": [8, 9, 20, 34, 52, 60, 62, 63, 64, 77, 78, 79, 80, 81, 82, 83, 84, 88, 89, 90, 91, 95, 98, 102, 104, 106, 107, 108, 109, 114], "pipelin": [8, 10, 11, 32, 44, 53, 54, 58, 68, 102, 105, 107, 108], "1": [8, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 50, 51, 52, 53, 54, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 91, 92, 93, 94, 95, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 110, 111, 112, 113, 114], "dataset": [8, 28, 29, 30, 33, 37, 42, 45, 46, 48, 51, 53, 54, 55, 59, 66, 68, 90, 96, 102, 103, 108], "2": [8, 28, 30, 35, 36, 39, 41, 42, 45, 48, 51, 52, 53, 54, 56, 58, 59, 61, 62, 64, 65, 66, 68, 69, 72, 73, 74, 77, 78, 79, 80, 81, 83, 84, 86, 89, 91, 95, 97, 102, 107, 108], "3": [8, 28, 30, 31, 33, 36, 37, 39, 42, 43, 45, 46, 48, 51, 52, 53, 54, 55, 56, 57, 58, 59, 61, 62, 64, 65, 66, 68, 69, 70, 71, 72, 73, 78, 81, 83, 84, 90, 95, 102, 105, 107], "imdb": 8, "sentiment": 8, "vocab_s": [8, 9, 35], "20000": [8, 9, 35], "consid": [8, 15, 17, 52, 107, 110, 113], "20k": 8, "word": [8, 83], "maxlen": [8, 9, 35], "200": [8, 9, 20, 35, 72], "movi": 8, "review": 8, "x_train": [8, 29], "y_train": 8, "x_val": 8, "y_val": 8, "load_data": 8, "num_word": 8, "pad_sequ": 8, "embed_dim": [8, 9, 35], "embed": [8, 9, 35, 61, 68, 88, 100, 107], "token": [8, 9, 35, 107], "num_head": [8, 9, 35], "attent": [8, 9, 35], "head": [8, 9, 35], "ff_dim": [8, 9, 35], "hidden": [8, 9, 35], "feed": [8, 9, 35, 108], "insid": [8, 9, 30, 35, 61, 74, 77, 88, 90], "delta": [8, 9, 35, 37, 46, 66, 84, 108], "input_dim": [8, 9, 35], "output_dim": [8, 9, 35], "block": [8, 53, 72, 78, 83, 86, 89], "multiheadattent": [8, 9, 35, 109], "key_dim": [8, 9, 35], "dropout": [8, 9, 35, 88], "layernorm": [8, 9, 35, 88], "epsilon": [8, 9, 35], "1e": [8, 9, 35, 52, 64, 90, 105], "globalaveragepooling1d": [8, 9, 35], "softmax": [8, 9, 18, 35, 88, 90], "functional_callback": 8, "histogram_freq": 8, "sparse_categorical_crossentropi": 8, "128": [8, 10, 11, 45, 59, 61, 81, 83, 90], "wrap": [8, 12, 25, 61, 72], "visual": [8, 12, 25, 26, 30, 50, 56, 67, 74, 100, 102, 103, 104, 107, 109], "multi": [8, 67, 109], "encount": [8, 77, 90], "access": [8, 18, 19, 22, 23, 24, 67, 72, 74], "within": [8, 77, 81, 88, 95, 104, 108], "granular": [8, 15, 16, 17, 30, 56, 83, 100, 107, 108, 112], "mha": [8, 109], "accur": [8, 90], "clone_lay": 8, "u": [8, 13, 51, 74], "clone": [8, 96], "diagram": [8, 93, 98, 108], "m": [8, 73, 74, 75, 87, 96], "convert_to_pb": [8, 39], "inspect": [8, 100], "1024": [8, 48, 51, 68, 91, 101], "artifact": [8, 32, 44, 48, 58, 74, 90], "3000": [8, 81], "model_after_qat": [8, 10, 11], "anoth": [8, 64, 68, 113, 114], "most": [8, 83, 90, 106], "case": [8, 9, 12, 25, 37, 42, 46, 49, 53, 60, 61, 62, 64, 66, 72, 75, 78, 83, 88, 90, 97, 103, 106], "complex": [8, 28, 37, 39, 41, 46, 48, 66, 68], "around": [8, 13, 37, 46, 48, 51, 66, 68], "elementari": 8, "logdir": 8, "summari": [8, 71, 100], "vanilla": 8, "becaus": [9, 21, 35, 61, 69, 102], "tool": [9, 37, 66, 67, 87, 90, 103, 112, 114], "sequanti": 9, "build": [9, 35, 72], "dicuss": 9, "text": [9, 35, 78, 89], "transform": [9, 18, 19, 20, 22, 23, 24, 25, 35, 51, 53, 61, 68, 83, 86, 90, 109], "found": [9, 36, 65, 69, 72, 83, 105, 108], "tokenandpositionembed": [9, 35], "transformerblock": [9, 35], "super": [9, 35, 52, 61, 62, 69, 77, 90], "att": [9, 35], "ffn": [9, 35], "layernorm1": [9, 35], "layernorm2": [9, 35], "dropout1": [9, 35], "dropout2": [9, 35], "kwarg": [9, 35, 77, 78, 81, 88, 89], "attn_output": [9, 35], "out1": [9, 35], "ffn_output": [9, 35], "token_emb": [9, 35], "pos_emb": [9, 35], "With": [9, 12, 25, 81, 102, 105], "those": [9, 46, 66, 106], "random": [9, 20, 28, 33, 35, 37, 39, 42, 45, 46, 48, 53, 69, 94, 104], "random_input": [9, 35], "embedding_lay": [9, 35], "transformer_block": [9, 35], "token_and_position_embed": 9, "symmetr": [9, 48, 49, 64, 72, 77, 78, 81, 83, 84, 88, 89, 90, 106, 108], "model_prepar": [9, 18, 19, 21, 22, 23, 24, 25, 35, 37, 51, 54, 61, 66, 68, 69, 72, 90], "prepare_model": [9, 18, 19, 21, 22, 23, 24, 25, 35, 37, 51, 54, 61, 66, 68, 69, 72, 90], "input_lay": [9, 35], "begin": [9, 35, 52, 61, 62, 78, 89, 106], "unwrap": 9, "ident": [9, 34, 60, 90], "present": [9, 21, 26, 52, 58, 62, 64, 72, 83, 86, 90, 103], "get_weight": 9, "represent": [9, 49, 79, 80, 81], "reorder": 9, "get_original_models_weights_in_functional_model_ord": 9, "original_model": [9, 35], "ndarrai": [9, 33, 36, 42, 44, 45, 46, 48, 65], "arg": [9, 68, 77, 78, 81, 83, 86, 88, 89], "quick": [9, 13, 15, 17], "lookup": 9, "remov": [9, 29, 54, 61, 72, 74, 90, 94, 98, 108, 114], "match": [9, 28, 32, 37, 44, 46, 56, 58, 66, 68, 83, 94, 100, 104, 106, 107, 108, 114], "original_model_weight": 9, "pop": 9, "out": [9, 35, 37, 38, 39, 46, 47, 61, 64, 66, 67, 68, 78, 79, 80, 89], "weight_nam": 9, "functional_model_weight_ord": 9, "enumer": [9, 28, 30, 51, 56, 58, 68, 90], "sort": 9, "weights_in_correct_ord": 9, "item": [9, 12, 25, 42, 102], "weight_info": 9, "assert": [9, 18, 61, 72, 90], "count_param": 9, "output_shap": 9, "textclassif": 9, "what": [9, 90, 111], "architectur": [9, 67], "model_weights_in_correct_ord": 9, "assert_array_equ": 9, "modelprepar": [9, 18, 19, 22, 23, 24, 25, 29, 35, 51, 61, 68, 90], "arthmet": [9, 35], "experss": [9, 35], "tfoplambda": [9, 35], "ressembl": 9, "conv_1": [9, 35, 83], "conv_2": [9, 35], "becuas": [9, 35, 44], "rais": [9, 35, 77], "hopefulli": 9, "reflect": [10, 11, 23, 24, 102, 108], "imagenet_dir": [10, 11], "assign": [10, 11, 49, 64, 77, 78, 88, 89], "dataset_train": [10, 11], "dataset_valid": [10, 11], "respect": [10, 11, 34, 71, 88, 104], "categorical_crossentropi": [10, 11, 39], "finish": [10, 11, 23, 24], "against": [10, 11, 13, 21, 23, 24, 37, 46, 66, 71, 94], "Of": [10, 11, 13, 15, 16, 17, 23, 24, 83], "cours": [10, 11, 13, 15, 16, 17, 23, 24], "instal": [10, 11, 14, 20, 22, 23, 24, 87, 96, 98, 109, 111], "jointli": [11, 23, 24], "trainabl": [11, 24, 102], "showcas": [12, 25], "analys": [12, 25, 104], "respond": [12, 25], "repres": [12, 25, 28, 30, 33, 35, 37, 39, 41, 45, 46, 48, 49, 56, 59, 60, 64, 66, 68, 79, 80, 81, 88, 89, 90, 97, 103, 104, 105, 108], "second": [12, 25, 35, 51, 69, 83, 88, 106], "singl": [12, 13, 25, 28, 37, 45, 46, 56, 59, 61, 63, 66, 83, 91, 97, 100, 103], "val_dataset": 12, "shown": [12, 25, 36, 60, 63, 64, 72, 103, 104, 107, 114], "itself": [12, 21, 25, 44, 100, 108, 110], "amount": [12, 25, 33], "exactli": [12, 25, 77, 88, 108], "multipl": [12, 25, 30, 52, 56, 57, 58, 61, 62, 65, 68, 70, 75, 83, 88, 98, 100, 109], "demonstr": [12, 25, 33, 90, 96], "quant_analyz": [12, 25, 37, 46, 66, 67, 72], "enable_per_layer_mse_loss": [12, 25, 37, 46, 66], "choic": [12, 13, 25, 37, 49, 100, 108], "enhanc": [12, 25, 37, 46, 48, 64, 66, 104, 108], "track": [12, 25, 64, 84, 104], "minimum": [12, 25, 28, 51, 61, 68, 71, 73, 78, 84], "histogram": [12, 25, 37, 46, 66, 71, 84, 102, 104, 108, 109], "seen": [12, 25, 103, 104], "html": [12, 25, 46, 61, 66, 73, 74, 75, 82, 104, 109, 112], "folder": [12, 25, 71, 104], "structur": [12, 17, 25, 49, 61, 77, 88, 100], "per_layer_quant_en": [12, 25, 104], "per_layer_quant_dis": [12, 25, 104], "min_max_rang": [12, 25, 104], "activations_pdf": [12, 25, 104], "name_": [12, 25, 46, 66], "index_0": [12, 25], "index_1": [12, 25], "index_n": [12, 25], "weights_pdf": [12, 25, 104], "layer1": [12, 25, 36, 65], "param_name_": [12, 25, 46, 66], "channel_index_0": [12, 25], "channel_index_1": [12, 25], "channel_index_n": [12, 25], "layer2": [12, 25, 36, 65], "layern": [12, 25], "per_layer_mse_loss": [12, 25, 104], "axi": [12, 25, 49, 104], "associ": [12, 25, 28, 36, 42, 45, 53, 59, 62, 77, 88, 102], "sub": [12, 25, 52, 75, 108], "illustr": [13, 15, 16, 17, 68, 91, 94, 97, 102, 108, 110, 111, 113, 114], "round": [13, 28, 30, 37, 38, 39, 42, 47, 48, 53, 55, 56, 67, 68, 86, 87, 91, 96, 102, 104, 108], "awai": 13, "low": [13, 15, 17, 22, 67, 87, 91, 93, 100, 102, 103], "basi": [13, 49, 83], "2d": [13, 83, 94, 100, 114], "imagin": 13, "64": [13, 34, 35, 37, 46, 48, 51, 66, 68, 73, 78, 83, 84, 89, 91], "filter": [13, 35], "kernel": [13, 67, 77, 83, 94, 110, 113], "28": [13, 56, 59, 81], "entireti": [13, 35], "matrix": 13, "contrast": [13, 35, 72], "repeat": [13, 64, 90, 94], "uniqu": 13, "attribut": [13, 33, 35, 59, 61, 64, 72, 77, 88, 104], "conv2d_lay": 13, "kernel_s": [13, 35, 52, 61, 62, 69, 90], "snpe": [13, 14], "qnn": [13, 14], "describ": [13, 39, 49, 51, 61, 68, 72, 83, 96, 100, 101, 102, 103, 106, 107, 108, 111], "style": 13, "ensur": [13, 58, 74, 88, 97, 102, 107], "mismatch": 13, "togeth": [13, 83], "pcq_quantsim_config": 13, "tell": 13, "saw": 13, "fashion": [13, 83], "did": [13, 103], "translat": [13, 51], "down": [13, 49, 51], "fo": [13, 51], "r": [13, 33, 45, 46, 51, 59, 64, 66], "NOT": [13, 51], "frozen": [13, 51], "depend": [13, 61, 72, 74, 75, 81, 95, 96, 102, 106, 109], "observ": [13, 21, 71, 77, 84, 88, 89, 90, 100, 103, 104, 108], "slight": 13, "plai": 13, "resnet50_pcq_adaround": 13, "invok": [13, 28, 30, 36, 38, 41, 46, 48, 51, 56, 66, 67, 68, 77, 88, 100, 102, 111, 112], "lead": [14, 22, 37, 46, 66, 83, 91, 93, 103, 107], "shift": [14, 22, 67, 103], "adjust": [14, 22, 28, 51, 52, 68, 82, 83, 91, 93, 94, 95, 102, 103, 107], "aimet_cl": 14, "cle_applied_model": [14, 31], "resnet50_after_cl": 14, "arxiv": [14, 103], "ab": [14, 103], "1906": [14, 103], "04721": [14, 103], "memori": [15, 16, 17, 30, 56, 64, 84, 95, 100, 110, 113, 114], "restor": [15, 16, 17, 68, 107], "image_net_train": [15, 16, 17, 21, 22, 23, 24], "imagenettrain": [15, 16, 17, 21, 22, 23, 24], "nn": [15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 51, 52, 53, 56, 60, 61, 62, 63, 65, 66, 68, 69, 72, 77, 78, 82, 83, 87, 88, 89, 90, 101, 109], "bool": [15, 16, 17, 19, 21, 22, 23, 24, 25, 30, 33, 36, 39, 41, 42, 45, 48, 53, 55, 56, 59, 61, 64, 65, 68, 78, 83, 84, 89], "gpu": [15, 16, 17, 19, 21, 22, 23, 24, 25, 56, 58, 67, 69, 73, 74, 102, 109], "learning_r": [15, 16, 17, 21, 23, 24, 54, 68], "learning_rate_schedul": [15, 16, 17, 21, 23, 24, 54, 68], "schedul": [15, 16, 17, 21, 23, 24, 105], "trainer": [15, 16, 17, 21, 23, 24, 30, 56, 96], "max_epoch": [15, 16, 17, 21, 23, 24], "is_avail": [15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 54, 90], "target_comp_ratio": [15, 16, 17, 30, 56, 70], "ratio": [15, 16, 17, 30, 56, 70, 94, 95], "9": [15, 16, 17, 18, 19, 22, 23, 24, 25, 30, 33, 45, 51, 59, 61, 64, 68, 69, 75, 78, 81], "num_comp_ratio_candid": [15, 16, 17, 30, 56, 70], "tri": [15, 16, 17, 100, 102], "caus": [15, 16, 17, 35, 100, 101, 102, 106, 107], "33": [15, 16, 17, 78, 89], "66": [15, 16, 17, 78, 89, 95], "00": [15, 16, 17, 78], "longer": [15, 16, 17, 72, 102, 105], "compromis": [15, 16, 17], "modules_to_ignor": [15, 16, 17, 30, 56, 66, 70, 99], "mode": [15, 16, 17, 30, 31, 39, 42, 43, 48, 53, 55, 56, 57, 61, 63, 65, 68, 70, 84, 89, 101, 102, 106], "much": [15, 16, 17, 114], "manual": [15, 16, 17, 30, 49, 56, 65, 72, 78, 89, 92, 100], "reconstruct": [15, 17, 28, 41, 51], "num_reconstruction_sampl": [15, 17, 56], "too": [15, 17, 83], "allow_custom_downsample_op": [15, 17, 56], "downsampl": [15, 17], "cost": [15, 17, 30, 56, 83, 97, 100, 105], "suggest": [15, 17, 39, 68, 97, 100, 103], "function_nam": [15, 16, 17], "eval_iter": [15, 16, 17, 30, 56, 70], "invoc": [15, 16, 17], "compress_schem": [15, 16, 17, 30, 56, 70], "cost_metr": [15, 16, 17, 30, 56, 70], "reduct": [15, 16, 17, 95, 102], "decim": [15, 16, 17, 30, 56, 70], "greedyselectionparamet": [15, 16, 17, 30, 56, 70], "channelpruningparamet": [15, 17, 56], "compressionschem": [15, 16, 17, 30, 56, 70], "costmetr": [15, 16, 17, 30, 56, 70], "greedy_param": [15, 16, 17, 30, 56, 70], "auto_param": [15, 16, 17, 30, 56, 70], "automodeparam": [15, 16, 17, 30, 56, 70], "greedy_select_param": [15, 16, 17, 30, 56], "channel_prun": [15, 17, 30, 56], "modelcompressor": [15, 16, 17, 30, 56, 70], "compress_model": [15, 16, 17, 30, 56, 70, 111], "relev": [15, 16, 17], "compressed_model": [15, 16, 30, 56], "comp_stat": [15, 16], "fall": [15, 16, 17, 97, 106], "sharpli": [15, 16, 17], "15e": [15, 17], "finetuned_model": [15, 16], "singular": [16, 17, 100, 110, 113], "decomposit": [16, 17, 100, 110, 113], "prune": [16, 30, 95, 96, 97, 99, 100, 109, 114], "spatialsvdparamet": [16, 17, 30, 56, 70], "spatial_svd": [16, 17, 30, 56, 70], "5e": [16, 17, 21, 23, 24, 54, 68], "ssvd_compressed_model": 17, "ssvd_comp_stat": 17, "ssvd_finetuned_model": 17, "further": [17, 26, 61, 72, 78, 81, 83, 89, 90, 91, 94, 98, 100], "ssvd_cp_compressed_model": 17, "cp_comp_stat": 17, "11": [17, 36, 49, 64, 73, 74, 75, 78, 81], "ssvd_cp_finetuned_model": 17, "imagefold": [18, 20], "tqdm": [18, 20], "root": [18, 20, 74, 75, 90], "compos": [18, 20, 53], "resiz": 18, "centercrop": [18, 20], "totensor": [18, 20, 53, 90], "images_mean": 18, "std": [18, 20], "images_std": 18, "manual_se": 18, "randperm": 18, "tolist": 18, "pin_memori": [18, 61], "evaluate_accuraci": 18, "top1_accuraci": 18, "dim": [18, 53, 69, 83, 90], "no_grad": [18, 19, 20, 22, 23, 24, 25, 51, 62, 68], "logit": [18, 20], "topk": [18, 20, 42], "certain": [18, 19, 22, 23, 24, 25, 51, 60, 61, 66, 68, 83, 100, 101, 106], "guidelin": [18, 19, 22, 23, 24, 25, 38, 41, 48, 51, 61, 67, 90, 102, 105], "autom": [18, 19, 22, 23, 24, 25, 38, 51, 60, 61, 67, 68, 102], "compli": [18, 19, 22, 23, 24, 25, 51, 68], "rand": [18, 19, 21, 22, 23, 24, 25, 28, 37, 45, 52, 58, 62], "modif": [18, 19, 22, 23, 24], "made": [18, 19, 22, 23, 24, 61, 106], "overrid": [18, 19, 22, 23, 24, 61, 68], "300": 18, "verifi": [19, 22, 23, 24, 35, 61], "resnet18_after_cle_bc": [19, 20, 22], "val_transform": 20, "normal": [20, 36, 52, 69, 104], "485": 20, "456": 20, "406": 20, "229": 20, "225": 20, "imagenet_dataset": 20, "_create_sampled_data_load": [20, 53], "subsetrandomsampl": [20, 53], "in_eval_mod": 20, "get_devic": 20, "_dataset": [20, 53], "k": 20, "view_a": 20, "__getitem__": [20, 53], "unlabeled_imagenet_dataset": 20, "unlabeled_imagenet_data_load": 20, "initial_accuraci": [20, 42, 53], "run_infer": [20, 42, 53], "adaround_data_load": [20, 42, 53], "optimized_accuraci": [20, 42, 53], "batchnrom": 21, "focu": 21, "unlik": [21, 79, 80], "script": 21, "didn": [21, 67], "statatist": 21, "finetuned_accuraci": [21, 23, 24], "train_load": [21, 54, 56, 90], "images_dir": 21, "finetuned_accuracy_bn_reestim": 21, "resnet18_after_qat": [21, 23, 24], "reload": 22, "techiqu": 22, "num_quant_sampl": [22, 55], "num_bias_correct_sampl": [22, 55], "quantparam": [22, 55], "bias_correct": [22, 55], "correct_bia": [22, 55], "bc_param": 22, "weight_bw": [22, 55], "act_bw": [22, 55], "round_mod": [22, 55], "held": [23, 24, 77, 88, 90], "Then": [23, 24, 28, 46, 51, 66, 68, 100], "matter": [25, 77], "softwar": [26, 98], "compress": [26, 27, 50, 87, 94, 96, 98, 109, 110, 112, 113, 114], "dramat": 26, "lost": [26, 87, 98, 108], "due": [26, 35, 62, 67, 83, 103], "At": [26, 95, 111], "onnx": [26, 49, 58, 60, 68, 73, 74, 87, 91, 92, 96, 98, 101, 102, 103, 104, 106, 108], "framework": [26, 48, 98, 102, 106, 108], "link": [26, 73, 75, 93, 96, 103, 104], "codebas": 26, "sphinx": 26, "page": [26, 69, 74, 75, 95, 108, 109], "qualcomm": [26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114], "innov": [26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114], "center": [26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114], "inc": [26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114], "quantsim_config": [26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114], "default_config": [26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114], "35": [26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114], "model": [27, 28, 29, 30, 31, 32, 33, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 88, 89, 91, 92, 93, 94, 95, 96, 97, 99, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114], "ai": [27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114], "toolkit": [27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114], "linear": [28, 29, 36, 41, 51, 54, 61, 62, 64, 65, 71, 72, 77, 83, 88, 90, 93, 94], "format": [28, 33, 34, 36, 39, 41, 46, 51, 64, 66, 68, 83, 86, 89, 92, 99], "prefix": [28, 39, 41, 51, 64, 68, 86, 88], "31": [28, 37, 41, 46, 51, 52, 55, 66, 68, 74, 75], "default_reg_param": [28, 41, 51], "default_beta_rang": [28, 41, 51], "default_warm_start": [28, 41, 51], "sourc": [28, 29, 30, 31, 32, 33, 35, 36, 37, 39, 41, 42, 43, 44, 45, 46, 48, 51, 53, 54, 55, 56, 57, 58, 59, 61, 64, 65, 66, 68, 69, 70, 71, 74, 75, 77, 78, 79, 80, 81, 82, 83, 84, 86, 88, 89, 107], "datasetv2": [28, 29], "stop": [28, 41, 51, 92], "beta": [28, 41, 51, 91], "anneal": [28, 41, 51], "start_beta": [28, 41, 51], "end_beta": [28, 41, 51], "warm": [28, 41, 51, 91], "period": [28, 41, 51, 91], "zero": [28, 41, 51, 64, 86, 108, 109], "post_training_percentil": [28, 51, 68], "percentil": [28, 51, 68, 84], "absolut": [28, 45, 51, 56, 59, 68, 78, 89], "nois": [28, 51, 67, 68, 84, 90, 102, 103, 104, 105, 106], "training_range_learning_with_tf_enhanced_init": [28, 51, 68], "aimetlogg": 28, "test_model": 28, "keras_model": 28, "dummy_forward_pass": [28, 69], "intend": [28, 37, 46, 49, 56, 66, 90, 96], "Or": [28, 37, 39, 41, 46, 48, 58, 61, 66, 68, 100], "someth": [28, 37, 39, 41, 46, 48, 66, 68, 100], "apply_adaround_exampl": [28, 41], "set_level_for_all_area": 28, "dataset_s": 28, "possible_batch": 28, "from_tensor_slic": [28, 29, 37], "w4a8": 28, "param_bw": [28, 42, 51, 53, 64], "output_bw": [28, 42, 51, 53, 64], "adarounded_model": [28, 51], "adarounded_sess": 28, "grid": [28, 51, 83], "awar": [29, 38, 54, 63, 77, 91, 93, 96, 98, 100, 102, 107, 108], "bn_re_estimation_dataset": 29, "bn_num_batch": 29, "handl": [29, 42, 53, 54, 83], "undo": [29, 54], "upon": [29, 54, 77, 88, 90], "batch_norm": [29, 36, 54, 65], "qcquantizewrapp": [29, 54], "pair": [29, 30, 36, 54, 55, 56, 65], "got": [29, 54, 61, 65], "overal": [30, 51, 56, 68, 95, 97, 107], "algorithm": [30, 33, 45, 49, 56, 59, 95, 97, 100, 107, 114], "tweak": [30, 36, 56, 64, 65], "compressor": [30, 56], "static": [30, 35, 56, 61, 108], "visualization_url": [30, 56, 70], "callabl": [30, 33, 41, 42, 45, 51, 53, 54, 56, 59, 61, 66, 77, 83], "url": [30, 56, 70, 74, 75, 96, 111], "appear": [30, 36, 52, 56, 61, 62, 65], "compressionstat": [30, 56], "use_monotonic_fit": [30, 56], "saved_eval_scores_dict": [30, 56, 70], "variabl": [30, 35, 56, 61, 74, 75, 78, 89, 96, 97], "express": [30, 56], "comp": [30, 56], "greater": [30, 36, 56, 65, 83, 95, 97], "monoton": [30, 56, 97], "dict": [30, 36, 39, 42, 45, 46, 48, 55, 56, 58, 59, 60, 61, 64, 65, 66, 68, 69, 88, 89], "eval_scor": [30, 46, 56, 66], "pickl": [30, 56], "input_op_nam": 30, "output_op_nam": [30, 33], "union": [30, 32, 35, 36, 39, 42, 44, 46, 51, 52, 53, 55, 56, 57, 58, 59, 65, 66, 68, 83, 86], "manualmodeparam": [30, 56], "rank": [30, 56, 64, 110, 113], "noth": [30, 56, 90], "list_of_module_comp_ratio_pair": [30, 56], "modulecompratiopair": [30, 56], "space": [30, 56, 83], "weight_svd": [30, 56], "comp_ratio": [30, 56], "ivar": 30, "aimet_common_def": 30, "aimet_tensorflow_def": 30, "inp_data": 30, "aimet_spatial_svd": 30, "evalfunct": 30, "denot": [30, 114], "80": [30, 78, 84, 89], "being": [30, 33, 34, 36, 49, 56, 60, 61, 62, 65, 66, 72, 83, 94], "driver": [30, 73, 75], "stat": [30, 46, 54, 56, 82, 84], "comprehens": 31, "detect": [31, 100], "shall": [31, 49], "cle": [31, 43, 57, 63, 67, 91, 92, 96, 102, 107, 109], "rtype": [31, 35, 36, 59, 81], "cross_layer_equalization_auto": [31, 57], "individu": [31, 36, 46, 57, 66, 83, 93, 97, 102, 104, 106, 107], "accord": [32, 44, 58, 102], "amongst": [32, 44, 58], "miss": [32, 35, 44, 49, 58, 62], "issu": [32, 35, 44, 52, 58, 62, 93, 98, 101, 107, 109, 111, 112], "layer_output_util": [32, 44, 58], "layeroutpututil": [32, 44, 58], "save_dir": 32, "keraslayeroutput": 32, "constructor": [32, 36, 44, 48, 55, 58, 60, 61, 65, 68], "generate_layer_output": [32, 44, 58], "input_batch": [32, 44, 58], "disk": [32, 44, 58], "obtain": [32, 36, 44, 46, 49, 58, 65, 69, 75, 95, 104], "aimet_export_artifact": [32, 44, 58], "h5": [32, 98, 102], "simplic": [32, 44, 58], "mandatori": [32, 44, 58], "load_encodings_to_sim": [32, 44, 58], "construct": [32, 44, 52, 58, 74, 75, 90, 101], "properli": [32, 44, 58, 78, 89, 90], "pre": [32, 44, 58, 73, 74, 75, 94, 98, 103, 104], "get_pre_processed_input": [32, 44, 58], "fp32_layer_output_util": [32, 44, 58], "fp32_layer_output": [32, 44, 58], "quantsim_layer_output_util": [32, 44, 58], "quantsim_layer_output": [32, 44, 58], "bitop": [33, 45, 59], "starting_op_nam": 33, "quantizergroup": [33, 45, 59], "wrt": 33, "vari": [33, 45, 59, 95, 103, 112], "earli": [33, 45, 59], "exit": [33, 45, 59, 77, 88, 90], "forward_pass_callback_2": 33, "nupi": 33, "last": [33, 99], "kept": [33, 107], "func": [33, 45, 59, 66], "encapsul": [33, 45, 59, 66], "back": [33, 45, 51, 59, 63, 68, 81, 90, 106], "OF": 33, "SUCH": 33, "damag": 33, "spdx": 33, "licens": 33, "identifi": [33, 55, 62, 74, 75, 83, 94, 96, 104, 107, 109, 114], "bsd": 33, "claus": 33, "copyright": 33, "pylint": 33, "statement": [33, 61, 67, 72, 101], "alpha": [33, 64], "directrori": 33, "preset": 33, "parent": [33, 77, 88], "retuern": 33, "seed": [33, 56], "set_se": 33, "evalutaion": 33, "org_top1": 33, "get_quantizated_model": 33, "accept": [33, 97, 103, 107], "09": 33, "cmp_re": 33, "mixed_preision_quant_model": 33, "fast_mixed_precis": 33, "sever": [34, 38, 60, 62, 67, 83, 88, 95, 104], "encourag": [34, 35, 38, 60, 61, 67], "mix": 34, "had": [34, 60, 90], "x2": [34, 60, 61], "relu2": [34, 35, 60, 62], "manditori": 35, "submodul": [35, 60], "via": [35, 67, 87, 95, 108], "inherit": [35, 77, 88], "pure": [35, 60], "over": [35, 42, 46, 53, 56, 66, 78, 84, 88, 91, 97, 100, 112], "inputlay": 35, "portion": 35, "taken": [35, 114], "get_text_classificaiton_model": 35, "model_preparer_two_subclassed_lay": 35, "get_subclass_model_with_functional_lay": 35, "sigmoid": [35, 61, 88], "binary_classifi": 35, "myfunctionalmodel": 35, "my_functional_model": 35, "classifi": 35, "model_preparer_subclassed_model_with_functional_lay": 35, "resembl": 35, "piec": [35, 61], "python": [35, 68, 73, 74, 75], "trace": [35, 60, 82], "symbol": 35, "touch": 35, "part": [35, 37, 42, 46, 53, 63, 66, 83, 100, 103, 104], "static_patch_count": 35, "guarante": 35, "furthermor": 35, "resu": 35, "resblock": 35, "twice": 35, "bad": 35, "bn1": [35, 52, 62, 65], "bn2": 35, "relu1": [35, 60, 62, 69], "plug": [36, 65], "conv2dtranspos": 36, "depthwiseconv2d": [36, 99], "crosslayersc": [36, 65], "scale_model": [36, 65], "clssetinfo": 36, "highbiasfold": [36, 65], "bias_fold": [36, 65], "cls_set_info_list": [36, 65], "bn_layer": [36, 65], "sigma": [36, 65], "element": [36, 49, 65], "model_transform_util": 36, "replace_relu6_with_relu": 36, "cross_layer_equalization_auto_stepwis": 36, "relu6": [36, 55, 65, 88, 103], "model_for_cl": 36, "folded_pair": [36, 65], "bn_dict": [36, 65], "conv_or_linear": 36, "fold_given_batch_norm": [36, 65], "layer_pair": [36, 65], "conv_linear": 36, "is_batch_norm_second": 36, "scale_cls_set": [36, 65], "cls_set": [36, 65], "cls_pair_1": [36, 65], "cls_pair_2": [36, 65], "hold": [36, 55, 65, 81, 83, 86, 88, 106, 107], "along": [36, 64, 65, 81, 83, 90, 105, 108], "depth": [36, 65, 87, 95, 107], "wise": [36, 46, 56, 65, 66, 86, 107], "clssetlayerpairinfo": [36, 65], "scale_factor": [36, 65], "relu_activation_between_lay": [36, 65], "relat": [36, 55, 56, 65, 72, 104, 108], "whose": [36, 58, 61, 65, 72, 82, 83, 103, 106], "cross_layer_equalization_manu": [36, 65], "get_example_layer_pairs_resnet50_for_fold": 36, "consecutive_layer_list": [36, 65], "get_consecutive_layer_list_from_resnet50_for_sc": 36, "scaling_factor_list": [36, 65], "format_info_for_high_bias_fold": 36, "conv_op_1": 36, "bn_op_1": 36, "conv_op_2": 36, "bn_op_2": 36, "conv_op_3": 36, "bn_op_3": 36, "bn_op": 36, "upstream": [36, 94, 114], "downstream": [36, 49, 114], "usag": [36, 49, 62, 64, 68, 84, 87], "conv_op": 36, "bn_op_with_meta": 36, "_fold_upstream_flag": 36, "append": [36, 56], "boolean": [36, 77], "is_relu_activation_in_cls_set": 36, "fill": [36, 68], "create_cls_set_info_list": 36, "mse": [37, 46, 66, 72, 104, 108], "quantanalyz": [37, 46, 47, 66, 67, 72, 102, 109], "pdf": [37, 46, 66, 109], "scalar": [37, 46, 66], "hotspot": [37, 46, 66, 104], "stochast": [37, 39, 55, 68], "toi": [37, 45, 59], "num_class": [37, 39, 53], "ey": 37, "image_dataset": 37, "label_dataset": 37, "serv": [37, 42, 46, 53, 66, 88, 111], "own": [37, 42, 46, 48, 51, 53, 54, 55, 66, 68], "action": [37, 46, 48, 51, 54, 55, 66, 68, 114], "prepared_model": [37, 51, 61, 66, 68, 69, 90], "forward_pass_callback_fn": [37, 46, 66], "eval_callback_fn": [37, 46, 66], "approxim": [37, 46, 66, 91, 95, 103, 104], "quant_analyzer_result": [37, 46, 66], "abil": [38, 47, 67, 109], "hardwar": [38, 47, 67, 71, 98, 102, 103, 108], "cross": [38, 42, 47, 53, 55, 63, 67, 71, 91, 92, 96, 101, 102, 104, 107, 112], "estim": [38, 67, 90, 102, 103], "in_plac": [39, 68], "default_data_typ": [39, 48, 68], "mechan": [39, 61, 68], "rule": [39, 83, 106], "custom_object": 39, "pth": [39, 56, 58, 64, 68], "quantize_model": [39, 48], "dummy_x": 39, "dummy_i": 39, "randint": 39, "to_categor": 39, "lr": [39, 90], "param_bw_override_list": [41, 51], "ignore_quant_ops_list": [41, 51], "default_config_fil": [41, 51], "user_onnx_lib": [41, 48], "modelproto": [41, 42, 43, 44, 46, 48], "affect": [41, 51, 83, 93, 106], "id": [41, 42, 44, 53, 70, 74, 111], "librari": [41, 48, 64, 69, 100], "commonli": [41, 51], "among": [41, 42, 51], "ceil": [41, 42, 51], "10k": [41, 51], "15k": [41, 51], "simplifi": [41, 42, 43, 44, 45, 46, 48, 72], "ada_rounded_model": 41, "auto_quant_v2": [42, 53], "cache_id": [42, 53], "strict_valid": [42, 53], "integr": [42, 47, 53, 63, 64, 67, 102], "includ": [42, 45, 49, 53, 59, 68, 72, 82, 83, 93, 97, 104, 105, 106, 108, 109, 111], "manner": [42, 53, 92], "onnxmodel": [42, 46], "proce": [42, 53, 92], "unid": [42, 53], "unintuit": [42, 53], "explicitli": [42, 86, 114], "get_quant_scheme_candid": 42, "highest": [42, 97], "_quantschemepair": 42, "set_quant_scheme_candid": 42, "math": [42, 84, 90], "onnx_model": [42, 43, 46, 48], "dummy_data": [42, 46, 48], "astyp": [42, 45, 46, 48], "float32": [42, 45, 46, 48, 69], "Its": [42, 114], "fed": 42, "unlabelled_data_load": 42, "num_of_sampl": 42, "evaldataload": 42, "acc_top1": 42, "acc_top5": 42, "batch_avg_top_1_5": 42, "4f": [42, 53], "happen": [43, 57, 90], "dir_path": [44, 58], "wherein": [44, 58], "dummy_input_dict": 44, "amp": [45, 59], "quantizer_group": [45, 59], "parameter_quant": [45, 59], "factori": [45, 59], "activation_quant": 45, "get_activation_quant": 45, "name_to_quantizer_dict": [45, 59], "get_active_quant": [45, 59], "qcquantizeop": 45, "get_candid": [45, 59], "get_param_quant": 45, "set_quantizers_to_candid": [45, 59], "bw": [45, 59, 60, 64, 68, 83], "to_list": [45, 59], "quantizer_info": 45, "fp32_output": 45, "quantize_with_mixed_precis": [45, 59], "flow": [45, 59, 61, 63, 67, 102, 107, 108], "algo": [45, 59], "default_bitwidth": [45, 59], "eval_callback_for_phase_1": [45, 59], "eval_callback_func": [45, 59], "eval_callback_for_phase_2": [45, 59], "clean": [45, 59], "quantize_with_mixed_precision_start_from_existing_cach": [45, 59], "90": [45, 59], "number_of_sampl": [45, 59], "popul": [45, 49, 59], "perform_ev": [45, 59], "in_tensor": 45, "historgram": 46, "unlabeled_dataset_iter": [46, 53, 66], "interest": [46, 66], "create_quantsim_and_encod": 46, "check_model_sensitivity_to_quant": [46, 66], "perform_per_layer_analysis_by_enabling_quant": 46, "occurr": [46, 66, 94], "record": [46, 52, 66, 84], "layer_nam": [46, 52, 66], "perform_per_layer_analysis_by_disabling_quant": 46, "export_per_layer_encoding_min_max_rang": [46, 66], "esults_dir": [46, 66], "pcq": [46, 66, 93, 104], "param_nam": [46, 66], "export_per_layer_stats_histogram": [46, 66], "ctivations_pdf": [46, 66], "eights_pdf": [46, 66], "n": [46, 66, 83, 90, 109], "am": [46, 66], "channel_index": [46, 66], "export_per_layer_mse_loss": [46, 66], "discard": [46, 66], "unlabeled_data_load": [46, 53, 66], "_get_unlabled_data_load": [46, 66], "autoqu": [47, 67, 96, 102, 105, 109], "unifi": [47, 67], "use_symmetric_encod": [48, 72], "attempt": [48, 102, 103], "line": [48, 51, 54, 55, 68, 71], "max_batch_count": [48, 51, 68], "current_batch_count": [48, 51, 68], "forward_pass_funct": 48, "syntax": 49, "usabl": 49, "xx": 49, "yy": 49, "zz": 49, "major": [49, 100], "revis": 49, "minor": [49, 109], "patch": 49, "substanti": 49, "fulli": [49, 67, 90, 99, 100, 113], "bug": [49, 109], "backward": [49, 65, 90], "assum": [49, 53, 75, 83, 86, 97], "string": [49, 106], "activation_encod": 49, "tensor_nam": 49, "param_encod": [49, 72], "constraint": [49, 83], "depict": 49, "6086959838867188": 49, "109158515930176": 49, "114": 49, "018501389771699905": 49, "21": [49, 84], "558866932988167": 49, "12636379897594452": 49, "12": [49, 73, 74, 75, 78, 83, 84], "010530316270887852": 49, "06318144500255585": 49, "06268782913684845": 49, "127": [49, 81], "0004936049808748066": 49, "fc1": [49, 61], "05589814856648445": 49, "05546144023537636": 49, "0004367042565718293": 49, "184721499681473": 49, "10788747668266296": 49, "0089906234367221": 49, "conv2d_1": 49, "1020304188132286": 49, "10380396991968155": 49, "008650330936207491": 49, "readvariableop": 49, "1462666392326355": 49, "1451239287853241": 49, "126": 49, "0011427081098743512": 49, "08333279937505722": 49, "08268175274133682": 49, "0006510374592799766": 49, "dtype": [49, 61, 64, 72, 79, 80, 81, 83, 86], "datatyp": [49, 69], "highlight": [49, 103, 111, 112], "quantizer_arg": 49, "activation_bitwidth": 49, "param_bitwidth": 49, "broken": 49, "occur": [49, 82, 83, 86], "who": 49, "benefit": [49, 83, 91], "knowledg": 49, "experiment": [51, 52, 53, 66, 68, 72, 83, 100], "v2": [51, 53, 66, 68, 77, 78, 79, 80, 81, 82, 83, 84, 86, 87, 88, 89, 90], "namespac": [51, 53, 66, 67, 68, 72], "visit": [51, 53, 66, 68, 75, 87], "overview": [51, 53, 66, 68, 72], "pars": [51, 68, 86], "get_train_dataload": [51, 54], "emploi": [51, 68], "quantized_resnet18": [51, 68], "arch_check": 52, "archcheck": 52, "check_model_arch": 52, "result_dir": 52, "_node_check_dict": 52, "arch_checker_report": 52, "dotted_name_op": 52, "nodeerrorreportobject": 52, "archcheckerreport": 52, "condit": [52, 61, 62], "modelwithnotenoughchannel": 52, "prelu": [52, 88], "stride": [52, 61, 62, 90], "batchnorm2d": [52, 62, 65, 88, 90], "example_check_for_number_of_conv_channel": 52, "fewer": [52, 100], "logger": [52, 62], "_check_conv_channel_32_bas": 52, "_check_conv_channel_larger_than_32": 52, "modelwithprelu": 52, "prelu1": 52, "example_check_for_non_performant_activ": 52, "num_paramet": 52, "_activation_check": 52, "standalon": [52, 102], "modelwithnonfoldablebn": 52, "foldabl": 52, "avg_pool1": 52, "avgpool2d": [52, 88], "example_check_for_standalone_bn": 52, "averagepool": 52, "prevent": [52, 61, 72, 94, 101], "ep": [52, 90], "05": [52, 64, 78, 90], "momentum": [52, 90], "affin": [52, 64, 67, 77, 81, 83, 86, 87, 88, 89, 90], "track_running_stat": [52, 90], "_check_batch_norm_fold": 52, "model_prepare_requir": 53, "hen": 53, "_subset_sampl": 53, "sampler": 53, "fp32_model": 53, "fakedata": 53, "eval_data_load": 53, "num_correct_predict": 53, "argmax": [53, 90], "deprec": [53, 72, 102], "dummy_input_on_cpu": 53, "dummy_input_on_gpu": 53, "preced": [54, 114], "var": 54, "load_fp32_model": 54, "imagenetpipelin": 54, "quant_sim": [54, 68], "quant_param": 55, "conv_bn_dict": 55, "perform_only_empirical_bias_corr": 55, "layers_to_ignor": 55, "unless": [55, 75, 77, 86, 114], "remain": [55, 72, 102, 103, 108], "calc": 55, "corr": 55, "irrespect": 55, "fact": [55, 83], "elig": 55, "input_bn": 55, "output_bn": 55, "in_activation_typ": 55, "no_activ": 55, "out_activation_typ": 55, "hode": 55, "No": [55, 62], "mobilenetv2": [55, 65], "512": 55, "module_prop_dict": 55, "find_all_conv_bn_with_activ": 55, "train_model": 56, "train_flag": 56, "weightsvdparamet": 56, "rank_select_schem": 56, "select_param": 56, "rankselectschem": 56, "tar": 56, "evaluate_model": 56, "honor": 56, "obvious": 56, "spatial_svd_auto_mod": 56, "mnist": 56, "mnist_trained_on_gpu": 56, "pretti": 56, "easili": 56, "spatial_svd_manual_mod": 56, "manual_param": 56, "weight_svd_auto_mod": 56, "rank_select": 56, "weight_svd_manual_mod": 56, "channel_pruning_auto_mod": 56, "mnist_torch_model": 56, "dataloadermnist": 56, "channel_pruning_manual_mod": 56, "_layer_db": 56, "ture": 56, "batch_callback": 56, "spatial_svd_auto_mode_with_layerwise_finetun": 56, "torchscript": [58, 68, 87], "naming_schem": 58, "namingschem": 58, "onnx_export_arg": [58, 68, 69], "onnxexportapiarg": [58, 68], "numer": 58, "onnx_util": 58, "pythonpath": [58, 96], "successfulli": 58, "map_loc": 58, "model_torch": 58, "phase2_revers": 59, "phase2": 59, "input_quant": [59, 72, 77, 88, 90], "output_quant": [59, 72, 77, 88, 90], "supported_kernel_op": 59, "get_input_quantizer_modul": 59, "roughli": 59, "convers": 60, "onnx_file_nam": 60, "jit": 60, "traceabl": [60, 61], "stateless": 60, "former": 60, "retrain": [60, 102], "whenev": [60, 90], "image_rgb": 60, "rgb_output": 60, "image_bw": 60, "bw_output": 60, "rgb": 60, "elementwis": [61, 88, 109], "unrol": 61, "independ": [61, 107], "modules_to_exclud": 61, "module_classes_to_exclud": 61, "concrete_arg": 61, "instanc": [61, 62, 68, 77, 111], "duplic": 61, "exclud": [61, 62, 66, 86], "partial": 61, "special": [61, 90], "control": [61, 88, 108], "won": 61, "symbolic_trac": 61, "graphmodul": [61, 90], "modelwithfunctionalrelu": 61, "9216": 61, "fc2": 61, "model_preparer_functional_exampl": 61, "allclos": 61, "modelwithreusedrelu": 61, "model_preparer_reused_exampl": 61, "modelwithelementwiseaddop": 61, "x1": 61, "model_preparer_elementwise_add_exampl": 61, "dynam": [61, 79, 80, 103, 108, 109, 112], "branch": [61, 96, 106], "weren": 61, "traceerror": 61, "workaround": [61, 101], "problem": [61, 107], "across": [61, 64, 83, 103, 104, 112], "Such": 61, "concret": 61, "truli": 61, "scope": 61, "preserv": 61, "custom_function_not_to_be_trac": 61, "call_funct": 61, "__torch_function__": 61, "sqrt": 61, "modelwithnontorchfunct": 61, "model_transform": 61, "tracer": 61, "is_leaf_modul": 61, "leaf": [61, 86, 109], "expos": [61, 91, 104], "module_to_exclud": 61, "examin": 61, "custommodul": 61, "softplu": [61, 88], "custommodel": 61, "arang": [61, 69, 78], "traceback": 61, "typeerror": 61, "receiv": 61, "invalid": [61, 83], "proxi": 61, "layout": 61, "requires_grad": [61, 81], "problemat": [61, 107, 112], "determinist": 61, "hard": 61, "do_not_trace_m": 61, "known": [62, 83, 98], "share": [62, 69, 88], "modelwithreusednod": 62, "inplac": 62, "2592": [62, 84], "view": [62, 69, 82, 87, 90, 93, 98, 101, 103, 104, 111], "model_valid": 62, "modelvalid": 62, "validate_example_model": 62, "validate_model": 62, "validate_for_reused_modul": 62, "0x7f127685a598": 62, "resolv": 62, "warn": [62, 102], "redefin": [62, 90], "distinct": [62, 90], "rewrit": [62, 101], "modelwithoutreusednod": 62, "rerun": 62, "0x7ff577373598": 62, "validate_for_missing_modul": 62, "0x7ff5703eff28": 62, "modelwithfunctionallinear": 62, "0x7f9dd9bd90d0": 62, "matmul_8": 62, "connectedgraph": 62, "op_type_map": 62, "recogn": [62, 108], "functional_op": 62, "modelwithoutfunctionallinear": 62, "parallel": [63, 84], "dataparallel": [63, 67], "move": [63, 96, 102], "forth": 63, "huggingfac": 64, "similar": [64, 83, 103, 105, 108], "alon": 64, "loraconfig": 64, "get_peft_model": 64, "lora_config": 64, "lora_alpha": 64, "lora_dropout": 64, "target_modul": 64, "replace_lora_layers_with_quantizable_lay": 64, "meta": [64, 98, 102], "track_lora_meta_data": 64, "meta_data": 64, "tmp_dir": 64, "convinplacelinear": 64, "peftquantutil": 64, "peft_util": 64, "name_to_module_dict": 64, "disable_lora_adapt": 64, "recomput": 64, "freeze_base_model_param_quant": 64, "tmpdir": 64, "export_model": [64, 68], "filename_prefix_encod": [64, 68], "base_encod": 64, "enable_adapter_and_load_weight": 64, "lora_weights_after_adaptation_for_adapter1": 64, "safetensor": 64, "use_safetensor": 64, "lora_modul": 64, "get_quantized_lora_lay": 64, "param_quant": [64, 72, 77, 83, 88, 90], "quantizedequant": [64, 72, 78, 80, 81, 83, 88, 89, 90], "base_model": 64, "adapter1": 64, "export_adapter_weight": 64, "adapter1_weight": 64, "configr": 64, "adaptermetadata": 64, "lora_a": 64, "lora_b": 64, "replaced_module_typ": 64, "adapater_name_to_meta_data": 64, "init": 64, "track_meta_data": 64, "pt": 64, "adapter_weights_path": 64, "bin": [64, 74, 75, 84], "freeze_base_model": 64, "freeze_base_model_activation_quant": 64, "get_fp_lora_lay": 64, "quantize_lora_scale_with_fixed_rang": 64, "scale_min": 64, "scale_max": 64, "mul": 64, "set_bitwidth_for_lora_adapt": 64, "conv1d": [65, 88, 109], "convtranspose2d": [65, 88], "batchnorm1d": [65, 88], "cross_layer_equalization_auto_step_by_step": 65, "conv_bn": 65, "replace_modules_of_type1_with_type2": 65, "layer_list": 65, "clspairinfo": 65, "depthwis": [65, 93, 109], "cross_layer_equalization_depthwise_lay": 65, "perform_per_layer_analysis_by_enabling_quant_wrapp": 66, "perform_per_layer_analysis_by_disabling_quant_wrapp": 66, "wrapped_module_nam": 66, "tap": 66, "packag": [67, 86, 96, 109], "plan": 67, "upgrad": [67, 75], "flexibil": 67, "extens": [67, 74, 75, 88, 96], "futur": [67, 82, 83, 86], "releas": [67, 96, 101], "core": 67, "checker": 67, "concern": 67, "peft": 67, "lora": 67, "introduc": [67, 83, 88, 102, 106, 108], "power": [67, 107], "blockwis": [67, 86], "lpbq": [67, 86], "dispatch": 67, "carefulli": 67, "compatibil": 67, "public": 67, "seq_ms": [67, 72], "apply_seq_ms": [67, 72], "orthogon": 67, "migrat": 67, "quantizationmixin": [67, 87, 88], "save_checkpoint": 68, "file_path": 68, "checkpoint": [68, 98, 102], "load_checkpoint": 68, "quant_sim_model": 68, "propagate_encod": 68, "export_to_torchscript": 68, "use_embedded_encod": 68, "opset_vers": [68, 69], "enable_onnx_check": 68, "entri": [68, 106], "data_typ": [68, 72], "fakequ": 68, "trainingextens": 68, "src": 68, "forward_pass_arg": 68, "quatiz": 68, "unction": 68, "idea": [69, 90], "travel": 69, "sparseconvolution3d": 69, "spars": 69, "sparsetensorwrapp": 69, "sparseconvtensor": 69, "scriptmodul": 69, "scatterdens": 69, "pro": [69, 83], "spconv3d": 69, "spconvmodel": 69, "spconv_tensor": 69, "sparseconv3d": 69, "spconv1": 69, "in_channel": [69, 83, 90], "out_channel": [69, 83, 90], "spconv2": 69, "conv3d": [69, 88], "normal_conv3d": 69, "spconv_scatter_dens": 69, "coord": 69, "voxel": 69, "sp_tensor": 69, "sp_outputs1": 69, "sp_outputs2": 69, "sp_outputs2_dens": 69, "sp_output": 69, "sp_outputs_relu": 69, "dense_tensor_sp_input": 69, "ncdhw": 69, "permut": 69, "ndhwc": 69, "stack": 69, "meshgrid": 69, "ij": 69, "reshap": [69, 88], "operator_export_typ": 69, "operatorexporttyp": 69, "onnx_aten_fallback": 69, "converter_arg": 69, "input_dtyp": 69, "int32": 69, "expand_sparse_op_structur": 69, "preserve_io": 69, "exported_sp_conv_model": 69, "visualize_serialized_data": 70, "visualizecompress": [70, 111], "bokeh": [70, 71], "server": 70, "publish": [70, 71], "tabl": [70, 82, 96, 111], "display_eval_scor": [70, 111], "saved_eval_scores_dict_path": 70, "display_comp_ratio_plot": [70, 111], "comp_ratio_list_path": 70, "pkl": 70, "start_bokeh_server_sess": 70, "model_compression_with_visu": 70, "65": [70, 95], "resnet18_eval_scor": 70, "comp_ratios_file_path": 70, "greedy_selection_comp_ratios_list": 70, "eval_scores_path": 70, "compression_visu": 70, "termin": [70, 96], "visualize_model": 71, "visualize_relative_weight_ranges_to_identify_problematic_lay": 71, "selected_lay": 71, "figur": [71, 91, 94, 97, 107, 110, 111, 113, 114], "visualize_weight_rang": 71, "scatter": 71, "deviat": 71, "visualize_changes_after_optim": 71, "old_model": 71, "new_model": 71, "visualize_changes_in_model_after_and_before_cl": 71, "visualiz": 71, "model_copi": 71, "visualize_weight_ranges_model": 71, "usual": [71, 90, 100, 105, 108], "visualize_relative_weight_ranges_model": 71, "easier": [72, 83], "simpler": 72, "extend": 72, "fundament": 72, "advis": 72, "subject": 72, "interact": [72, 82], "hood": 72, "properti": 72, "compon": 72, "stai": 72, "quantizewrapp": 72, "quantizationsimmodelv1": 72, "all_quant_wrapp": 72, "quant_wrapp": 72, "staticgridquantwrapp": 72, "_module_to_wrap": 72, "in_featur": [72, 77, 88, 90], "out_featur": [72, 77, 88, 90], "quantizedlinear": [72, 77, 83, 88, 90], "quantizedconv2d": [72, 83, 88, 90], "quantizationsimmodelv2": 72, "sim2": 72, "all_q_modul": 72, "qmodul": 72, "q_modul": 72, "moduledict": [72, 77, 88, 90], "modulelist": [72, 77, 88, 90], "quantizedrelu": [72, 88, 90], "staticgridquant": 72, "learnedgridquant": 72, "tensor_quant": 72, "staticgridperchannelquant": 72, "fp_quantiz": 72, "affine_quant": 72, "affinequant": [72, 79, 80], "floatquant": [72, 79, 80], "q": [72, 77, 78, 79, 80, 81, 88, 89, 108], "affine_q": 72, "affine_qdq": 72, "fp_qdq": 72, "floatquantizedequant": [72, 80], "float16": [72, 79, 80, 83], "setup": [72, 73], "sim1": 72, "wrap_linear": 72, "qlinear": [72, 77, 88], "symmetri": 72, "is_unsigned_symmetr": 72, "use_strict_symmetr": 72, "sign": [72, 78, 108], "libpymo": 72, "tfencod": 72, "copy_": 72, "OR": 72, "_remove_input_quant": 72, "_remove_output_quant": 72, "_remove_param_quant": 72, "temporarili": 72, "_is_encoding_frozen": 72, "freeze_encod": 72, "concept": 72, "mimick": 72, "allow_overwrit": [72, 86, 89], "requires_grad_": 72, "overwritten": 72, "pypi": 73, "intel": 73, "x86": 73, "processor": 73, "linux": [73, 75], "ubuntu": [73, 75], "22": [73, 75, 84, 90], "04": [73, 75], "lt": [73, 75], "pip": [73, 74, 75, 87, 96, 111], "apt": [73, 74, 75, 87], "liblapack": [73, 74, 75, 87], "libpython3": 73, "dev": [73, 74, 75], "python3": [73, 74, 75, 87, 96], "variant": [73, 75, 91, 92, 93, 102, 103, 104, 108], "latest": [73, 74], "whl": [73, 74, 75], "host": [73, 74, 75, 109, 111], "github": [73, 74, 75, 96, 109], "com": [73, 74, 75, 96, 109], "quic": [73, 74, 75, 96, 109], "prerequisit": [73, 111], "requisit": [73, 75], "cu121": [73, 74, 75], "cp310": [73, 74, 75], "manylinux_2_34_x86_64": [73, 74, 75], "torch_stabl": [73, 74, 75], "13": [73, 74, 78, 84], "cu117": 73, "cu118": 73, "older": 73, "brows": [73, 74, 75], "bash": [73, 74], "command": [73, 74, 75, 96, 111], "shell": 73, "nvidia": [73, 74, 75], "card": 73, "capabl": [73, 88, 111], "docker": 73, "455": 73, "alwai": [73, 97], "newer": 73, "cudnn": 73, "machin": [73, 74, 100], "develop": [73, 74, 75, 82, 83, 86], "click": 73, "instruct": [74, 75, 87, 96], "variant_str": 74, "ONE": 74, "pt113": 74, "aimet_vari": 74, "workspac": [74, 96], "absolute_path_to_workspac": [74, 96], "docker_image_nam": 74, "codelinaro": 74, "docker_container_nam": 74, "any_nam": 74, "any_tag": 74, "jenkin": 74, "dockerfil": 74, "grep": 74, "kill": 74, "rm": 74, "passwd": 74, "ro": 74, "home": 74, "mnt": 74, "entrypoint": 74, "hostnam": 74, "filesystem": 74, "port": [74, 111], "port_id": 74, "project": [74, 75], "wish": [74, 75], "tip": [74, 75], "post1": [74, 75], "prepend": [74, 75, 88, 96], "sudo": [74, 75, 96], "wheel": [74, 75], "tag": [74, 75, 96, 109], "ex": [74, 75, 83], "release_tag": [74, 75, 96], "download_url": [74, 75], "wheel_file_nam": [74, 75], "find_pkg_url_str": [74, 75], "usr": [74, 75], "lib": [74, 75], "dist": [74, 75], "envsetup": [74, 75], "sh": [74, 75], "pend": 75, "pip3": 75, "h": [75, 96, 113, 114], "local": [75, 96, 111], "accordingli": 75, "ye": [75, 100], "wget": 75, "gnupg2": 75, "archiv": 75, "exact": [75, 93, 102], "date": 75, "aforement": 75, "repo": 75, "ubuntu2204": 75, "x86_64": 75, "keyring_1": 75, "1_all": 75, "deb": 75, "dpkg": 75, "cat": 75, "reqs_deb_common": 75, "txt": 75, "xarg": 75, "reqs_deb_torch_common": 75, "reqs_deb_onnx_common": 75, "reqs_deb_tf_gpu": 75, "reqs_deb_torch_gpu": 75, "reqs_deb_onnx_gpu": 75, "uninstal": 75, "onnxruntime_v": 75, "c": [75, 95], "__version__": 75, "ln": 75, "gnu": 75, "libjpeg": 75, "chose": 75, "mixin": [77, 88], "quantizerbas": [77, 88, 89], "behav": [77, 88, 107], "abstract": [77, 88, 89], "__quant_init__": [77, 88], "initializd": [77, 88], "overridden": [77, 88, 106], "length": [77, 83, 88], "set_kernel": 77, "quantizedtensor": [77, 78, 81, 89], "keyword": 77, "output_encod": 77, "context": [77, 88, 90], "underli": [77, 107], "int_multipli": 77, "enc": 77, "notimplementederror": 77, "q_output": 77, "quantized_repr": [77, 81], "dq_output": 77, "qmult": 77, "quantizedmultipli": [77, 88], "classmethod": 77, "set_default_kernel": 77, "get_kernel": 77, "enter": [77, 88, 92], "is_initi": [77, 78, 79, 80, 88, 89], "from_modul": 77, "quantized_linear": 77, "get_default_kernel": 77, "retriev": 77, "module_cl": 77, "decor": 77, "subpackag": 77, "throw": 77, "declar": 77, "maskedadd": 77, "mask": 77, "quantizedmaskedadd": 77, "input_qtzr": 77, "value_qtzr": 77, "output_qtzr": 77, "clamp": [78, 79, 80, 89, 108], "lceil": [78, 79, 80, 89], "frac": [78, 79, 80, 89], "rfloor": [78, 79, 80, 89], "qmin": [78, 89, 108], "qmax": [78, 89, 108], "learnabl": [78, 89], "theta_": [78, 89], "pmatrix": [78, 89], "b_0": [78, 89], "b_1": [78, 83, 89], "cdot": [78, 89], "b_": [78, 89], "d": [78, 89], "equat": [78, 83, 89, 108], "out_": [78, 89], "j_0": [78, 89], "j_": [78, 89], "input_": [78, 89], "scale_": [78, 89], "i_0": [78, 89], "i_": [78, 89], "offset_": [78, 89], "quad": [78, 89, 108], "forall_": [78, 89], "leq": [78, 89], "i_d": [78, 89], "lfloor": [78, 79, 80, 89], "j_d": [78, 89], "b_d": [78, 89], "asymmetr": [78, 84, 89, 106, 108], "encoding_analyz": [78, 79, 80, 84, 89], "encodinganalyz": [78, 79, 80, 84, 89], "block_siz": [78, 83, 89], "129": [78, 89, 101], "255": [78, 81, 89], "122": [78, 89], "192": [78, 89], "106": [78, 89], "94": [78, 89], "145": [78, 89], "181": [78, 89], "144": [78, 89], "194": [78, 89], "74": [78, 89], "86": [78, 89], "150": [78, 89], "103": [78, 89], "37": [78, 89], "111": [78, 89], "237": [78, 89], "218": [78, 89], "49": [78, 89], "155": [78, 89], "179": [78, 89], "89": [78, 89], "110": [78, 89], "17": [78, 84, 89], "36": [78, 89], "83": [78, 89], "grad_fn": [78, 81, 89], "aliasbackward0": [78, 81, 89], "ones_lik": [78, 89], "187": [78, 89], "186": [78, 89], "131": [78, 89], "203": [78, 89], "143": [78, 89], "152": [78, 89], "226": [78, 89], "55": [78, 89], "172": [78, 89], "207": [78, 89], "146": [78, 89], "216": [78, 89], "238": [78, 89], "141": [78, 89], "178": [78, 89], "188": [78, 89], "63": [78, 89], "59": [78, 89], "19": [78, 84, 89], "162": [78, 89], "30": [78, 89], "109": [78, 89], "dequant": [78, 81, 89], "overlin": [78, 89], "qdq": [78, 79, 80, 89], "dequantizedtensor": [78, 81, 89], "2771": [78, 89], "3038": [78, 89], "0819": [78, 89], "9700": [78, 89], "9487": [78, 89], "1307": [78, 89], "7894": [78, 89], "1709": [78, 89], "2212": [78, 89], "7741": [78, 89], "0295": [78, 89], "2265": [78, 89], "0564": [78, 89], "6177": [78, 89], "0386": [78, 89], "0176": [78, 89], "6054": [78, 89], "8836": [78, 89], "1232": [78, 89], "8229": [78, 89], "5540": [78, 89], "3992": [78, 89], "2363": [78, 89], "2546": [78, 89], "0036": [78, 89], "2355": [78, 89], "1741": [78, 89], "6079": [78, 89], "6247": [78, 89], "0115": [78, 89], "2458": [78, 89], "9157": [78, 89], "4694": [78, 89], "0639": [78, 89], "2568": [78, 89], "0680": [78, 89], "6695": [78, 89], "7932": [78, 89], "1889": [78, 89], "0158": [78, 89], "5695": [78, 89], "5220": [78, 89], "1977": [78, 89], "4475": [78, 89], "0424": [78, 89], "1128": [78, 89], "8796": [78, 89], "1060": [78, 89], "5897": [78, 89], "6196": [78, 89], "9961": [78, 89], "0549": [78, 89], "6431": [78, 89], "0039": [78, 89], "8706": [78, 89], "4706": [78, 89], "2353": [78, 89], "8078": [78, 89], "3451": [78, 89], "1176": [78, 89], "4549": [78, 89], "0471": [78, 89], "5255": [78, 89], "4157": [78, 89], "0784": [78, 89], "5333": [78, 89], "1647": [78, 89], "2118": [78, 89], "2196": [78, 89], "9176": [78, 89], "9490": [78, 89], "7765": [78, 89], "4784": [78, 89], "6039": [78, 89], "3137": [78, 89], "3216": [78, 89], "8000": [78, 89], "4392": [78, 89], "4863": [78, 89], "overload": 78, "rceil": 78, "num_step": [78, 84], "num": 78, "_step": 78, "0000e": 78, "5000e": 78, "02": 78, "1921e": 78, "08": 78, "0500e": 78, "1000e": 78, "1500e": 78, "2000e": 78, "2500e": 78, "14": [78, 90], "quantize_dequant": 78, "0000": [78, 81], "0667": 78, "1333": 78, "2667": 78, "3333": 78, "4000": [78, 81], "4667": 78, "6000": [78, 81], "6667": 78, "7333": 78, "8667": 78, "9333": 78, "exponent_bit": [79, 80, 83], "mantissa_bit": [79, 80, 83], "cast": [79, 80], "expon": [79, 80, 83], "mantissa": [79, 80, 83], "x_c": [79, 80], "log_2": [79, 80], "ieee": [79, 80, 100, 103], "_max": [79, 80], "mutual": [79, 80, 83], "exclus": [79, 80, 83], "finer": [79, 80, 83], "8998": [79, 80], "0947": [79, 80], "0891": [79, 80], "1727": [79, 80], "is_bfloat16": [79, 80], "8984": [79, 80], "0859": [79, 80], "1729": [79, 80], "minmaxencodinganalyz": [79, 80, 84], "is_float16": [79, 80], "8994": [79, 80], "0889": [79, 80], "alia": [79, 80], "encodingbas": [81, 89], "57": 81, "312": 81, "153": 81, "205": 81, "set_rang": 81, "x_q": 81, "26": 81, "23": [81, 84], "x_dq": 81, "carri": 81, "gradient": 81, "thu": 81, "autograd": 81, "backpropag": 81, "38": [81, 100], "40": 81, "39": [81, 90], "51": 81, "521": 81, "41": 81, "quant_dequ": 81, "x_qdq": 81, "52": 81, "68": 81, "97": 81, "uint8": 81, "heavi": [82, 83, 86, 111, 112], "notic": [82, 83, 86], "visualization_tool": 82, "visualize_stat": 82, "save_path": 82, "quant_stats_visu": 82, "threshold": [82, 88, 92], "exce": 82, "exceed": 82, "counterpart": [83, 88], "come": [83, 100, 105], "split": 83, "con": 83, "storag": 83, "drawback": 83, "outlier": [83, 104, 108], "dimens": [83, 86, 88, 107, 110, 113], "influenc": 83, "resid": [83, 109], "chunk": 83, "isol": 83, "favor": 83, "relationship": 83, "long": [83, 86], "b_2": 83, "b_n": 83, "s_1": 83, "s_2": 83, "s_n": 83, "evenli": 83, "divid": [83, 88, 95, 105], "divis": 83, "permit": 83, "3d": 83, "arbitrari": 83, "restrict": [83, 101], "themselv": [83, 105], "linear_1": 83, "lie": 83, "leverag": 83, "expans": [83, 100], "groupedblockquantizedequant": 83, "decompressed_bw": 83, "expand": 83, "block_group": 83, "config_util": 83, "set_blockwise_quantization_for_weight": 83, "input_channel": 83, "linear1": 83, "isinst": 83, "signific": [83, 107], "switch": 83, "docstr": 83, "4d": 83, "mention": 83, "assist": 83, "set_activation_quantizers_to_float": 83, "set_grouped_blockwise_quantization_for_weight": 83, "decompress": 83, "addition": 83, "larger": [83, 110, 113], "encoding_vers": [83, 86], "exported_model": [83, 86], "gather": 84, "reset_stat": 84, "reset": 84, "update_stat": 84, "pow": 84, "0991": 84, "3696": 84, "_minmaxrang": 84, "1721": 84, "sqnrencodinganalyz": 84, "num_bin": 84, "2048": [84, 86], "asymmetric_delta_candid": 84, "symmetric_delta_candid": 84, "101": 84, "offset_candid": 84, "max_parallel": 84, "gamma": 84, "lowest": [84, 94], "3612": 84, "8497": 84, "_histogram": 84, "bin_edg": 84, "8907": 84, "3625": 84, "8343": 84, "3061": 84, "7779": 84, "2497": 84, "2784": 84, "8066": 84, "3348": 84, "8630": 84, "3912": 84, "7080": 84, "2438": 84, "percentileencodinganalyz": 84, "largest": 84, "smallest": 84, "1188": 84, "3368": 84, "27": 84, "5710": 84, "0989": 84, "6269": 84, "1548": 84, "6827": 84, "2106": 84, "2614": 84, "7335": 84, "2056": 84, "6776": 84, "1497": 84, "gptvq_weight": 86, "apply_gptvq": 86, "gptvq_param": 86, "param_encoding_path": 86, "module_names_to_exclud": 86, "block_level_module_nam": 86, "file_name_prefix": 86, "config_file_path": 86, "gptvqparamet": 86, "dataclass": 86, "row_axi": 86, "col_axi": 86, "rows_per_block": 86, "cols_per_block": 86, "vector_dim": 86, "vector_bw": 86, "vector_strid": 86, "index_bw": 86, "num_of_kmeans_iter": 86, "assignment_chunk_s": 86, "carrier": 86, "125m": 86, "optforcausallm": 86, "from_pretrain": 86, "facebook": 86, "gptvq_applied_model": 86, "lm_head": 86, "gptvq_opt": 86, "load_encod": 86, "deploi": [87, 108], "edg": [87, 98], "incur": [87, 98, 104], "workflow": [87, 90, 95, 98], "sample_input": [87, 90], "sample_output": 87, "out_dir": 87, "quantized_model": 87, "quickstart": 87, "product": [87, 95, 98], "technologi": [87, 98], "subsidiari": [87, 98], "extra": 88, "nativ": 88, "quantizedsoftmax": [88, 90], "qmul": 88, "sens": 88, "qadd": 88, "quantizedadd": 88, "calibration_data_load": 88, "adaptiveavgpool1d": 88, "quantizedadaptiveavgpool1d": 88, "adaptiveavgpool2d": 88, "quantizedadaptiveavgpool2d": 88, "adaptiveavgpool3d": 88, "quantizedadaptiveavgpool3d": 88, "adaptivemaxpool1d": 88, "quantizedadaptivemaxpool1d": 88, "adaptivemaxpool2d": 88, "quantizedadaptivemaxpool2d": 88, "adaptivemaxpool3d": 88, "quantizedadaptivemaxpool3d": 88, "alphadropout": 88, "quantizedalphadropout": 88, "avgpool1d": 88, "quantizedavgpool1d": 88, "quantizedavgpool2d": 88, "avgpool3d": 88, "quantizedavgpool3d": 88, "quantizedbatchnorm1d": 88, "quantizedbatchnorm2d": 88, "batchnorm3d": 88, "quantizedbatchnorm3d": 88, "celu": 88, "quantizedcelu": 88, "channelshuffl": 88, "quantizedchannelshuffl": 88, "constantpad1d": 88, "quantizedconstantpad1d": 88, "constantpad2d": 88, "quantizedconstantpad2d": 88, "constantpad3d": 88, "quantizedconstantpad3d": 88, "quantizedconv1d": 88, "quantizedconv3d": 88, "convtranspose1d": [88, 109], "quantizedconvtranspose1d": 88, "quantizedconvtranspose2d": 88, "convtranspose3d": 88, "quantizedconvtranspose3d": 88, "quantizeddropout": 88, "dropout2d": 88, "quantizeddropout2d": 88, "dropout3d": 88, "quantizeddropout3d": 88, "elu": 88, "quantizedelu": 88, "featurealphadropout": 88, "quantizedfeaturealphadropout": 88, "quantizedflatten": 88, "quantizedfold": 88, "fractionalmaxpool2d": 88, "quantizedfractionalmaxpool2d": 88, "fractionalmaxpool3d": 88, "quantizedfractionalmaxpool3d": 88, "gelu": 88, "quantizedgelu": 88, "glu": 88, "quantizedglu": 88, "groupnorm": 88, "quantizedgroupnorm": 88, "hardshrink": 88, "quantizedhardshrink": 88, "hardsigmoid": 88, "quantizedhardsigmoid": 88, "hardswish": 88, "quantizedhardswish": 88, "hardtanh": 88, "quantizedhardtanh": 88, "instancenorm1d": 88, "quantizedinstancenorm1d": 88, "instancenorm2d": 88, "quantizedinstancenorm2d": 88, "instancenorm3d": 88, "quantizedinstancenorm3d": 88, "lppool1d": 88, "quantizedlppool1d": 88, "lppool2d": 88, "quantizedlppool2d": 88, "quantizedlayernorm": 88, "leakyrelu": 88, "quantizedleakyrelu": 88, "localresponsenorm": 88, "quantizedlocalresponsenorm": 88, "logsigmoid": 88, "quantizedlogsigmoid": 88, "logsoftmax": 88, "quantizedlogsoftmax": 88, "maxpool1d": 88, "quantizedmaxpool1d": 88, "maxpool2d": 88, "quantizedmaxpool2d": 88, "maxpool3d": 88, "quantizedmaxpool3d": 88, "maxunpool1d": 88, "quantizedmaxunpool1d": 88, "maxunpool2d": 88, "quantizedmaxunpool2d": 88, "maxunpool3d": 88, "quantizedmaxunpool3d": 88, "mish": 88, "quantizedmish": 88, "quantizedprelu": 88, "pixelshuffl": 88, "quantizedpixelshuffl": 88, "pixelunshuffl": 88, "quantizedpixelunshuffl": 88, "rrelu": 88, "quantizedrrelu": 88, "quantizedrelu6": 88, "reflectionpad1d": 88, "quantizedreflectionpad1d": 88, "reflectionpad2d": 88, "quantizedreflectionpad2d": 88, "replicationpad1d": 88, "quantizedreplicationpad1d": 88, "replicationpad2d": 88, "quantizedreplicationpad2d": 88, "replicationpad3d": 88, "quantizedreplicationpad3d": 88, "selu": 88, "quantizedselu": 88, "silu": 88, "quantizedsilu": 88, "quantizedsigmoid": 88, "softmax2d": 88, "quantizedsoftmax2d": 88, "softmin": 88, "quantizedsoftmin": 88, "quantizedsoftplu": 88, "softshrink": 88, "quantizedsoftshrink": 88, "softsign": 88, "quantizedsoftsign": 88, "tanh": 88, "quantizedtanh": 88, "tanhshrink": 88, "quantizedtanhshrink": 88, "quantizedthreshold": 88, "unflatten": 88, "quantizedunflatten": 88, "unfold": 88, "quantizedunfold": 88, "upsampl": [88, 101], "quantizedupsampl": 88, "upsamplingbilinear2d": 88, "quantizedupsamplingbilinear2d": 88, "upsamplingnearest2d": 88, "quantizedupsamplingnearest2d": 88, "zeropad2d": 88, "quantizedzeropad2d": 88, "bceloss": 88, "quantizedbceloss": 88, "bcewithlogitsloss": 88, "quantizedbcewithlogitsloss": 88, "bilinear": [88, 101], "quantizedbilinear": 88, "ctcloss": 88, "quantizedctcloss": 88, "cosinesimilar": 88, "quantizedcosinesimilar": 88, "crossentropyloss": [88, 90], "quantizedcrossentropyloss": 88, "hingeembeddingloss": 88, "quantizedhingeembeddingloss": 88, "huberloss": 88, "quantizedhuberloss": 88, "kldivloss": 88, "quantizedkldivloss": 88, "l1loss": 88, "quantizedl1loss": 88, "mseloss": 88, "quantizedmseloss": 88, "multilabelmarginloss": 88, "quantizedmultilabelmarginloss": 88, "multilabelsoftmarginloss": 88, "quantizedmultilabelsoftmarginloss": 88, "multimarginloss": 88, "quantizedmultimarginloss": 88, "nllloss": 88, "quantizednllloss": 88, "nllloss2d": 88, "quantizednllloss2d": 88, "pairwisedist": 88, "quantizedpairwisedist": 88, "poissonnllloss": 88, "quantizedpoissonnllloss": 88, "smoothl1loss": 88, "quantizedsmoothl1loss": 88, "softmarginloss": 88, "quantizedsoftmarginloss": 88, "cosineembeddingloss": 88, "quantizedcosineembeddingloss": 88, "gaussiannllloss": 88, "quantizedgaussiannllloss": 88, "marginrankingloss": 88, "quantizedmarginrankingloss": 88, "tripletmarginloss": 88, "quantizedtripletmarginloss": 88, "tripletmarginwithdistanceloss": 88, "quantizedtripletmarginwithdistanceloss": 88, "quantizedembed": 88, "embeddingbag": 88, "quantizedembeddingbag": 88, "gru": [88, 109], "quantizedgru": 88, "rnn": [88, 109], "quantizedrnn": 88, "grucel": 88, "quantizedgrucel": 88, "rnncell": 88, "quantizedrnncel": 88, "lstm": [88, 109], "quantizedlstm": 88, "lstmcell": 88, "quantizedlstmcel": 88, "cumsum": 88, "quantizedcumsum": 88, "sin": 88, "quantizedsin": 88, "co": 88, "quantizedco": 88, "rsqrt": 88, "quantizedrsqrt": 88, "quantizedreshap": 88, "matmul": [88, 109], "quantizedmatmul": 88, "subtract": 88, "quantizedsubtract": 88, "quantizeddivid": 88, "bmm": 88, "quantizedbmm": 88, "baddbmm": 88, "quantizedbaddbmm": 88, "addmm": 88, "quantizedaddmm": 88, "concat": [88, 109], "quantizedconcat": 88, "allow_overwit": 89, "get_encod": 89, "get_legacy_encod": 89, "register_quantization_paramet": 89, "set_legacy_encod": 89, "tutori": 90, "meant": 90, "clearli": 90, "cifar10_train_data": 90, "fashionmnist": 90, "cifar10": 90, "cifar10_test_data": 90, "test_load": 90, "bn_1": 90, "bn_2": 90, "establish": 90, "send": 90, "batch_idx": 90, "zero_grad": 90, "fp_accuraci": 90, "91": 90, "70999908447266": 90, "coupl": 90, "care": [90, 100], "conform": 90, "incorrectli": 90, "thankfulli": 90, "fp_accuracy_prepar": 90, "2024": 90, "07": 90, "747": 90, "806": 90, "module_relu": 90, "module_relu_1": 90, "module_softmax": 90, "12544": 90, "getattr_1": 90, "getitem": 90, "graph_modul": 90, "print_read": 90, "passthrough": 90, "previous": 90, "theoret": 90, "idx": 90, "quantized_accuraci": 90, "1500015258789": 90, "advanc": 90, "post_qat_accuraci": 90, "92": 90, "05333709716797": 90, "happi": 90, "export_path": 90, "model_nam": 90, "fashion_mnist_model": 90, "sent": 90, "terminologi": 91, "abbrevi": 91, "bnf": 91, "hbf": 91, "often": [91, 92, 100, 105], "16x": 91, "caution": 91, "soon": 92, "prone": 92, "preprat": 92, "preceed": 93, "decreas": 93, "main": [93, 106, 109, 112], "oscil": 93, "cp": [94, 95, 97, 114], "magnitud": 94, "connect": [94, 99, 100, 113], "residu": 94, "regress": 94, "outlin": 95, "svd": [95, 96, 97, 99, 100, 109], "spatial": [95, 96, 97, 99, 100, 109], "accumul": [95, 100], "uncompress": 95, "latenc": 95, "bandwidth": 95, "websit": 95, "half": 95, "unknown": 95, "ssvd": 95, "f0": 95, "75": 95, "2b": 95, "revisit": 95, "close": [95, 108], "jupyt": 96, "familiar": 96, "teach": 96, "viewabl": 96, "metapackag": 96, "grant": 96, "admin": 96, "privileg": 96, "ip": 96, "browser": 96, "past": 96, "mkdir": 96, "cd": 96, "repositori": 96, "git": 96, "www": 96, "navig": 96, "launch": 96, "ipynb": 96, "assess": 97, "column": 97, "unmodifi": 97, "omit": [97, 106], "account": [97, 102, 105, 107], "drastic": 97, "redund": 98, "dilat": 99, "guidebook": 100, "greedi": [100, 111], "decompos": [100, 110, 113], "fc": [100, 113], "sharp": 100, "decai": 100, "slow": 100, "searcher": 100, "wors": 100, "strike": 100, "balanc": 100, "seem": [100, 102], "xiangyu": 100, "zhang": 100, "jianhua": 100, "zou": 100, "kaim": 100, "he": 100, "jian": 100, "sun": 100, "deep": 100, "transact": 100, "pattern": 100, "intellig": 100, "vol": 100, "pp": 100, "1943": 100, "1955": 100, "oct": 100, "2016": 100, "yihui": 100, "confer": [100, 103], "vision": [100, 103], "venic": 100, "2017": 100, "1398": 100, "1406": 100, "jaderberg": 100, "andrea": 100, "vedaldi": 100, "andrew": 100, "zisserman": 100, "british": 100, "jan": 100, "2014": 100, "andrei": 100, "kuzmin": 100, "marku": [100, 103], "nagel": [100, 103], "saurabh": 100, "pitr": 100, "sandeep": 100, "pendyam": 100, "tijmen": [100, 103], "blankevoort": [100, 103], "taxonomi": 100, "primit": 101, "sure": 101, "slice": 101, "align_corn": 101, "deconvolut": 101, "dconvolut": 101, "deeplabv3": 101, "address": [101, 107, 111], "briefli": 102, "suffici": [102, 104, 105, 108], "fast": 102, "easi": 102, "robust": 102, "_aimet": 102, "prep": 102, "complainc": 102, "align": 102, "retri": 102, "ref": 102, "satisfactori": [102, 107], "onto": 102, "pb": 102, "trial": [102, 107], "diagnost": 102, "becom": 103, "paper": 103, "surround": 103, "big": 103, "discrep": 103, "wide": 103, "significantli": 103, "quantizaion": 103, "analyt": [103, 111], "bottleneck": [103, 107], "hybrid": 103, "approach": [103, 108], "mart": 103, "van": 103, "baalen": 103, "seoul": 103, "octob": 103, "area": 104, "situat": 104, "pinpoint": 104, "culprit": 104, "squar": [104, 108], "monitor": 104, "contribut": [104, 107], "read": 104, "presenc": 105, "hyperparamet": 105, "converg": 105, "six": 106, "turn": 106, "empti": 106, "outsid": 106, "strict": [106, 108], "unsign": [106, 108], "throughout": [106, 112], "convent": 106, "member": 106, "insight": [107, 111, 112], "underperform": 107, "chart": 107, "confid": 107, "toward": 107, "uneven": 107, "global": 107, "inner": 107, "bert": 107, "reveal": 107, "resort": 107, "revert": 107, "mitig": 108, "ingest": 108, "000": 108, "de": 108, "hook": 108, "intercept": 108, "four": 108, "textrm": 108, "dfrac": 108, "elimin": 108, "induc": 108, "signal": 108, "satur": 108, "erro": 108, "alongsid": 108, "settabl": 108, "slim": 109, "backslash": 109, "io": 109, "user_guid": 109, "api_doc": 109, "quantizablemultiheadattent": 109, "kyuykim": 109, "mangal": 109, "geunle": 109, "correctli": 109, "klhsieh": 109, "akhobar": 109, "ashvkuma": 109, "fp16": 109, "stand": 109, "adaptiveround": 109, "recurr": 109, "\ud835\udc5a": [110, 113], "\ud835\udc5b": [110, 113], "\u210e": [110, 113], "\ud835\udc64": [110, 113], "\ud835\udc58": [110, 113], "degre": [110, 113], "augment": 111, "progress": [111, 112], "computation": [111, 112], "arrang": 111, "websocket": 111, "listen": 111, "5006": 111, "lot": 112, "term": 113, "lose": 114, "volum": 114, "hxwx8": 114, "hxwx5": 114, "propag": 114, "green": 114, "side": 114, "pink": 114, "color": 114, "orang": 114}, "objects": {"aimet_common.bias_correction": [[55, 0, 1, "", "ConvBnInfoType"]], "aimet_common.defs": [[55, 0, 1, "", "ActivationType"], [59, 0, 1, "", "CallbackFunc"], [30, 0, 1, "", "CompressionScheme"], [30, 0, 1, "", "CostMetric"], [56, 0, 1, "", "GreedySelectionParameters"], [68, 0, 1, "", "QuantScheme"]], "aimet_common.defs.ActivationType": [[55, 1, 1, "", "no_activation"], [55, 1, 1, "", "relu"], [55, 1, 1, "", "relu6"]], "aimet_common.defs.CompressionScheme": [[30, 1, 1, "", "channel_pruning"], [30, 1, 1, "", "spatial_svd"], [30, 1, 1, "", "weight_svd"]], "aimet_common.defs.CostMetric": [[30, 1, 1, "", "mac"], [30, 1, 1, "", "memory"]], "aimet_common.defs.QuantScheme": [[68, 1, 1, "", "post_training_percentile"], [68, 1, 1, "", "post_training_tf"], [68, 1, 1, "", "post_training_tf_enhanced"], [68, 1, 1, "", "training_range_learning_with_tf_enhanced_init"], [68, 1, 1, "", "training_range_learning_with_tf_init"]], "aimet_common.utils": [[66, 0, 1, "", "CallbackFunc"]], "aimet_onnx.adaround.adaround_weight.Adaround": [[41, 2, 1, "", "apply_adaround"]], "aimet_onnx.adaround.adaround_weight": [[41, 0, 1, "", "AdaroundParameters"]], "aimet_onnx.amp.mixed_precision_algo": [[45, 0, 1, "", "EvalCallbackFactory"]], "aimet_onnx.amp.mixed_precision_algo.EvalCallbackFactory": [[45, 3, 1, "", "sqnr"]], "aimet_onnx.amp.quantizer_groups": [[45, 0, 1, "", "QuantizerGroup"]], "aimet_onnx.amp.quantizer_groups.QuantizerGroup": [[45, 3, 1, "", "get_activation_quantizers"], [45, 3, 1, "", "get_active_quantizers"], [45, 3, 1, "", "get_candidate"], [45, 3, 1, "", "get_param_quantizers"], [45, 3, 1, "", "set_quantizers_to_candidate"], [45, 3, 1, "", "to_list"]], "aimet_onnx.auto_quant_v2": [[42, 0, 1, "", "AutoQuant"]], "aimet_onnx.auto_quant_v2.AutoQuant": [[42, 3, 1, "", "get_quant_scheme_candidates"], [42, 3, 1, "", "optimize"], [42, 3, 1, "", "run_inference"], [42, 3, 1, "", "set_adaround_params"], [42, 3, 1, "", "set_quant_scheme_candidates"]], "aimet_onnx.cross_layer_equalization": [[43, 2, 1, "", "equalize_model"]], "aimet_onnx.layer_output_utils": [[44, 0, 1, "", "LayerOutputUtil"]], "aimet_onnx.layer_output_utils.LayerOutputUtil": [[44, 3, 1, "", "generate_layer_outputs"]], "aimet_onnx.mixed_precision": [[45, 2, 1, "", "choose_mixed_precision"]], "aimet_onnx.quant_analyzer": [[46, 0, 1, "", "QuantAnalyzer"]], "aimet_onnx.quant_analyzer.QuantAnalyzer": [[46, 3, 1, "", "analyze"], [46, 3, 1, "", "check_model_sensitivity_to_quantization"], [46, 3, 1, "", "create_quantsim_and_encodings"], [46, 3, 1, "", "enable_per_layer_mse_loss"], [46, 3, 1, "", "export_per_layer_encoding_min_max_range"], [46, 3, 1, "", "export_per_layer_mse_loss"], [46, 3, 1, "", "export_per_layer_stats_histogram"], [46, 3, 1, "", "perform_per_layer_analysis_by_disabling_quantizers"], [46, 3, 1, "", "perform_per_layer_analysis_by_enabling_quantizers"]], "aimet_onnx.quantsim": [[48, 0, 1, "", "QuantizationSimModel"]], "aimet_onnx.quantsim.QuantizationSimModel": [[48, 3, 1, "", "compute_encodings"], [48, 3, 1, "", "export"]], "aimet_tensorflow.keras.adaround_weight.Adaround": [[28, 2, 1, "", "apply_adaround"]], "aimet_tensorflow.keras.adaround_weight": [[28, 0, 1, "", "AdaroundParameters"]], "aimet_tensorflow.keras.batch_norm_fold": [[36, 2, 1, "", "fold_all_batch_norms"], [29, 2, 1, "", "fold_all_batch_norms_to_scale"], [36, 2, 1, "", "fold_given_batch_norms"]], "aimet_tensorflow.keras.bn_reestimation": [[29, 2, 1, "", "reestimate_bn_stats"]], "aimet_tensorflow.keras.compress": [[30, 0, 1, "", "ModelCompressor"]], "aimet_tensorflow.keras.compress.ModelCompressor": [[30, 3, 1, "", "compress_model"]], "aimet_tensorflow.keras.cross_layer_equalization": [[36, 0, 1, "", "ClsSetInfo"], [31, 2, 1, "", "equalize_model"]], "aimet_tensorflow.keras.cross_layer_equalization.ClsSetInfo": [[36, 0, 1, "", "ClsSetLayerPairInfo"]], "aimet_tensorflow.keras.cross_layer_equalization.CrossLayerScaling": [[36, 2, 1, "", "scale_cls_sets"], [36, 2, 1, "", "scale_model"]], "aimet_tensorflow.keras.cross_layer_equalization.HighBiasFold": [[36, 2, 1, "id0", "bias_fold"]], "aimet_tensorflow.keras.defs": [[30, 0, 1, "", "ModuleCompRatioPair"], [30, 0, 1, "", "SpatialSvdParameters"]], "aimet_tensorflow.keras.defs.SpatialSvdParameters": [[30, 0, 1, "", "AutoModeParams"], [30, 0, 1, "", "ManualModeParams"], [30, 0, 1, "", "Mode"]], "aimet_tensorflow.keras.defs.SpatialSvdParameters.Mode": [[30, 1, 1, "", "auto"], [30, 1, 1, "", "manual"]], "aimet_tensorflow.keras.layer_output_utils": [[32, 0, 1, "", "LayerOutputUtil"]], "aimet_tensorflow.keras.layer_output_utils.LayerOutputUtil": [[32, 3, 1, "", "generate_layer_outputs"]], "aimet_tensorflow.keras.mixed_precision": [[33, 2, 1, "", "choose_fast_mixed_precision"], [33, 2, 1, "", "choose_mixed_precision"]], "aimet_tensorflow.keras.model_preparer": [[35, 2, 1, "", "prepare_model"]], "aimet_tensorflow.keras.quant_analyzer": [[37, 0, 1, "", "QuantAnalyzer"]], "aimet_tensorflow.keras.quant_analyzer.QuantAnalyzer": [[37, 3, 1, "", "analyze"]], "aimet_tensorflow.keras.quantsim": [[39, 0, 1, "", "QuantizationSimModel"]], "aimet_tensorflow.keras.quantsim.QuantizationSimModel": [[39, 3, 1, "", "compute_encodings"], [39, 3, 1, "", "export"]], "aimet_torch.amp.mixed_precision_algo": [[59, 0, 1, "", "EvalCallbackFactory"]], "aimet_torch.amp.mixed_precision_algo.EvalCallbackFactory": [[59, 3, 1, "", "sqnr"]], "aimet_torch.amp.quantizer_groups": [[59, 0, 1, "", "QuantizerGroup"]], "aimet_torch.amp.quantizer_groups.QuantizerGroup": [[59, 3, 1, "", "get_active_quantizers"], [59, 3, 1, "", "get_candidate"], [59, 3, 1, "", "get_input_quantizer_modules"], [59, 3, 1, "", "set_quantizers_to_candidate"], [59, 3, 1, "", "to_list"]], "aimet_torch.arch_checker.arch_checker.ArchChecker": [[52, 2, 1, "", "check_model_arch"]], "aimet_torch.batch_norm_fold": [[65, 2, 1, "", "fold_all_batch_norms"], [54, 2, 1, "", "fold_all_batch_norms_to_scale"], [65, 2, 1, "", "fold_given_batch_norms"]], "aimet_torch.bias_correction": [[55, 2, 1, "", "correct_bias"]], "aimet_torch.bn_reestimation": [[54, 2, 1, "", "reestimate_bn_stats"]], "aimet_torch.compress": [[56, 0, 1, "", "ModelCompressor"]], "aimet_torch.compress.ModelCompressor": [[56, 3, 1, "", "compress_model"]], "aimet_torch.cross_layer_equalization": [[65, 0, 1, "", "ClsSetInfo"], [57, 2, 1, "", "equalize_model"]], "aimet_torch.cross_layer_equalization.ClsSetInfo": [[65, 0, 1, "", "ClsSetLayerPairInfo"]], "aimet_torch.cross_layer_equalization.CrossLayerScaling": [[65, 2, 1, "", "scale_cls_sets"], [65, 2, 1, "", "scale_model"]], "aimet_torch.cross_layer_equalization.HighBiasFold": [[65, 2, 1, "id0", "bias_fold"]], "aimet_torch.defs": [[56, 0, 1, "", "ChannelPruningParameters"], [56, 0, 1, "", "ModuleCompRatioPair"], [56, 0, 1, "", "SpatialSvdParameters"], [56, 0, 1, "", "WeightSvdParameters"]], "aimet_torch.defs.ChannelPruningParameters": [[56, 0, 1, "", "AutoModeParams"], [56, 0, 1, "", "ManualModeParams"], [56, 0, 1, "", "Mode"]], "aimet_torch.defs.ChannelPruningParameters.Mode": [[56, 1, 1, "", "auto"], [56, 1, 1, "", "manual"]], "aimet_torch.defs.SpatialSvdParameters": [[56, 0, 1, "", "AutoModeParams"], [56, 0, 1, "", "ManualModeParams"], [56, 0, 1, "", "Mode"]], "aimet_torch.defs.SpatialSvdParameters.Mode": [[56, 1, 1, "", "auto"], [56, 1, 1, "", "manual"]], "aimet_torch.defs.WeightSvdParameters": [[56, 0, 1, "", "AutoModeParams"], [56, 0, 1, "", "ManualModeParams"], [56, 0, 1, "", "Mode"]], "aimet_torch.defs.WeightSvdParameters.Mode": [[56, 1, 1, "", "auto"], [56, 1, 1, "", "manual"]], "aimet_torch.gptvq.defs": [[86, 0, 1, "", "GPTVQParameters"]], "aimet_torch.gptvq.gptvq_weight.GPTVQ": [[86, 2, 1, "", "apply_gptvq"]], "aimet_torch.layer_output_utils": [[58, 0, 1, "", "LayerOutputUtil"], [58, 0, 1, "", "NamingScheme"]], "aimet_torch.layer_output_utils.LayerOutputUtil": [[58, 3, 1, "", "generate_layer_outputs"]], "aimet_torch.layer_output_utils.NamingScheme": [[58, 1, 1, "", "ONNX"], [58, 1, 1, "", "PYTORCH"], [58, 1, 1, "", "TORCHSCRIPT"]], "aimet_torch.mixed_precision": [[59, 2, 1, "", "choose_mixed_precision"]], "aimet_torch.model_preparer": [[61, 2, 1, "", "prepare_model"]], "aimet_torch.nn.modules.custom": [[69, 0, 1, "", "ScatterDense"], [69, 0, 1, "", "SparseTensorWrapper"]], "aimet_torch.peft": [[64, 0, 1, "", "AdapterMetaData"], [64, 0, 1, "", "PeftQuantUtils"], [64, 3, 1, "", "replace_lora_layers_with_quantizable_layers"], [64, 3, 1, "", "track_lora_meta_data"]], "aimet_torch.peft.PeftQuantUtils": [[64, 3, 1, "", "disable_lora_adapters"], [64, 3, 1, "", "enable_adapter_and_load_weights"], [64, 3, 1, "", "export_adapter_weights"], [64, 3, 1, "", "freeze_base_model"], [64, 3, 1, "", "freeze_base_model_activation_quantizers"], [64, 3, 1, "", "freeze_base_model_param_quantizers"], [64, 3, 1, "", "get_fp_lora_layer"], [64, 3, 1, "", "get_quantized_lora_layer"], [64, 3, 1, "", "quantize_lora_scale_with_fixed_range"], [64, 3, 1, "", "set_bitwidth_for_lora_adapters"]], "aimet_torch.v1.adaround.adaround_weight.Adaround": [[51, 2, 1, "", "apply_adaround"]], "aimet_torch.v1.adaround.adaround_weight": [[51, 0, 1, "", "AdaroundParameters"]], "aimet_torch.v1.auto_quant": [[53, 0, 1, "", "AutoQuant"]], "aimet_torch.v1.quant_analyzer": [[66, 0, 1, "", "QuantAnalyzer"]], "aimet_torch.v1.quant_analyzer.QuantAnalyzer": [[66, 3, 1, "", "analyze"], [66, 3, 1, "", "check_model_sensitivity_to_quantization"], [66, 3, 1, "", "enable_per_layer_mse_loss"], [66, 3, 1, "", "export_per_layer_encoding_min_max_range"], [66, 3, 1, "", "export_per_layer_mse_loss"], [66, 3, 1, "", "export_per_layer_stats_histogram"], [66, 3, 1, "", "perform_per_layer_analysis_by_disabling_quant_wrappers"], [66, 3, 1, "", "perform_per_layer_analysis_by_enabling_quant_wrappers"]], "aimet_torch.v1.quantsim": [[55, 0, 1, "", "QuantParams"], [68, 0, 1, "", "QuantizationSimModel"], [68, 3, 1, "", "load_checkpoint"], [68, 3, 1, "", "save_checkpoint"]], "aimet_torch.v1.quantsim.QuantizationSimModel": [[68, 3, 1, "", "compute_encodings"], [68, 3, 1, "", "export"]], "aimet_torch.v2.nn": [[88, 0, 1, "", "QuantizationMixin"]], "aimet_torch.v2.nn.QuantizationMixin": [[88, 3, 1, "", "__quant_init__"], [88, 3, 1, "", "compute_encodings"], [88, 3, 1, "", "forward"], [77, 3, 1, "", "from_module"], [77, 3, 1, "", "get_default_kernel"], [77, 3, 1, "", "get_kernel"], [77, 3, 1, "", "implements"], [88, 1, 1, "", "input_quantizers"], [88, 1, 1, "", "output_quantizers"], [88, 1, 1, "", "param_quantizers"], [77, 3, 1, "", "set_default_kernel"], [77, 3, 1, "", "set_kernel"]], "aimet_torch.v2.quantization": [[78, 4, 0, "-", "affine"], [80, 4, 0, "-", "float"]], "aimet_torch.v2.quantization.affine": [[78, 0, 1, "", "Quantize"], [78, 0, 1, "", "QuantizeDequantize"], [78, 2, 1, "", "dequantize"], [78, 2, 1, "", "quantize"], [78, 2, 1, "", "quantize_dequantize"]], "aimet_torch.v2.quantization.affine.quantizer": [[89, 0, 1, "", "Quantize"], [89, 0, 1, "", "QuantizeDequantize"], [89, 0, 1, "", "QuantizerBase"]], "aimet_torch.v2.quantization.affine.quantizer.Quantize": [[89, 3, 1, "", "forward"]], "aimet_torch.v2.quantization.affine.quantizer.QuantizeDequantize": [[89, 3, 1, "", "forward"]], "aimet_torch.v2.quantization.affine.quantizer.QuantizerBase": [[89, 3, 1, "", "allow_overwrite"], [89, 3, 1, "", "compute_encodings"], [89, 3, 1, "", "get_encoding"], [89, 3, 1, "", "get_legacy_encodings"], [89, 3, 1, "", "is_initialized"], [89, 3, 1, "", "register_quantization_parameter"], [89, 3, 1, "", "set_legacy_encodings"]], "aimet_torch.v2.quantization.encoding_analyzer": [[84, 0, 1, "", "EncodingAnalyzer"], [84, 0, 1, "", "MinMaxEncodingAnalyzer"], [84, 0, 1, "", "PercentileEncodingAnalyzer"], [84, 0, 1, "", "SqnrEncodingAnalyzer"]], "aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer": [[84, 3, 1, "", "compute_encodings"], [84, 3, 1, "", "reset_stats"], [84, 3, 1, "", "update_stats"]], "aimet_torch.v2.quantization.float": [[80, 0, 1, "", "FloatQuantizeDequantize"], [80, 0, 1, "", "QuantizeDequantize"]], "aimet_torch.v2.quantization.tensor": [[81, 0, 1, "", "DequantizedTensor"], [81, 0, 1, "", "QuantizedTensor"]], "aimet_torch.v2.quantization.tensor.DequantizedTensor": [[81, 3, 1, "", "dequantize"], [81, 3, 1, "", "quantize"], [81, 3, 1, "", "quantized_repr"]], "aimet_torch.v2.quantization.tensor.QuantizedTensor": [[81, 3, 1, "", "dequantize"], [81, 3, 1, "", "quantize"], [81, 3, 1, "", "quantized_repr"]], "aimet_torch.v2.quantsim.config_utils": [[83, 2, 1, "", "set_activation_quantizers_to_float"], [83, 2, 1, "", "set_blockwise_quantization_for_weights"], [83, 2, 1, "", "set_grouped_blockwise_quantization_for_weights"]], "aimet_torch.v2.visualization_tools": [[82, 2, 1, "", "visualize_stats"]], "aimet_torch.visualize_model": [[71, 2, 1, "", "visualize_changes_after_optimization"], [71, 2, 1, "", "visualize_relative_weight_ranges_to_identify_problematic_layers"], [71, 2, 1, "", "visualize_weight_ranges"]], "aimet_torch.visualize_serialized_data": [[70, 0, 1, "", "VisualizeCompression"]], "aimet_torch.visualize_serialized_data.VisualizeCompression": [[70, 3, 1, "", "display_comp_ratio_plot"], [70, 3, 1, "", "display_eval_scores"]]}, "objtypes": {"0": "py:class", "1": "py:attribute", "2": "py:function", "3": "py:method", "4": "py:module"}, "objnames": {"0": ["py", "class", "Python class"], "1": ["py", "attribute", "Python attribute"], "2": ["py", "function", "Python function"], "3": ["py", "method", "Python method"], "4": ["py", "module", "Python module"]}, "titleterms": {"automat": [0, 4, 18], "mix": [0, 4, 18, 33, 45, 59], "precis": [0, 4, 18, 33, 45, 59], "amp": [0, 4, 18, 33], "overal": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 90], "flow": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 64, 90, 103], "what": [0, 4, 12, 13, 18, 21, 25, 67], "thi": [0, 4, 12, 13, 18, 21, 25], "notebook": [0, 4, 12, 13, 18, 21, 25, 28, 29, 31, 51, 53, 54, 57, 66, 68, 96], "i": [0, 4, 12, 13, 18, 21, 25], "dataset": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25], "1": [0, 1, 2, 3, 4, 5, 6, 7, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 49, 55, 75, 90, 96, 109], "exampl": [0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25, 28, 29, 30, 31, 32, 33, 35, 36, 37, 39, 41, 42, 43, 44, 45, 46, 48, 49, 51, 53, 54, 55, 56, 57, 58, 59, 61, 65, 66, 68, 69, 70, 71, 72, 86, 87, 96], "evalu": [0, 1, 2, 3, 4, 5, 7, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25], "pipelin": [0, 1, 2, 3, 5, 6, 7, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25], "2": [0, 1, 2, 3, 4, 5, 6, 7, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 33, 49, 55, 75, 90, 96, 109], "convert": [0, 1, 2, 3, 9], "an": [0, 1, 2, 3], "fp32": [0, 1, 2, 3, 4, 5, 6, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24], "pytorch": [0, 1, 2, 3, 49, 50, 51, 53, 54, 55, 56, 57, 58, 59, 60, 63, 65, 66, 67, 68, 75, 87, 90, 101, 102, 112], "model": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 34, 35, 60, 61, 62, 87, 90, 98, 100, 101, 102], "onnx": [0, 1, 2, 3, 40, 41, 42, 43, 44, 45, 46, 47, 48, 69, 75], "simplifi": [0, 1, 2, 3], "baselin": [0, 1, 2, 3, 4, 5, 6, 10, 11, 13, 14, 15, 16, 17, 18, 19, 22, 23, 24], "accuraci": [0, 1, 2, 3, 4, 5, 6, 10, 11, 13, 14, 15, 16, 17, 18, 19, 22, 23, 24], "3": [0, 1, 2, 3, 4, 5, 6, 7, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 49, 96], "creat": [0, 1, 2, 3, 4, 5, 7, 9, 10, 11, 13, 14, 18, 19, 21, 22, 23, 24], "quantiz": [0, 1, 2, 3, 4, 5, 7, 8, 10, 11, 12, 13, 14, 18, 19, 21, 22, 23, 24, 25, 33, 38, 39, 45, 47, 48, 55, 59, 67, 68, 71, 72, 78, 80, 81, 83, 85, 88, 89, 90, 102, 103, 105, 106, 107, 108, 112], "simul": [0, 1, 2, 3, 4, 5, 10, 11, 13, 14, 18, 19, 21, 22, 23, 24, 106, 108], "fold": [0, 1, 2, 3, 5, 7, 10, 11, 13, 14, 18, 19, 21, 22, 23, 24, 90], "batch": [0, 1, 2, 3, 5, 10, 11, 13, 14, 18, 19, 22, 23, 24, 93], "normal": [0, 1, 3, 5, 10, 11, 13, 14, 18, 19, 23, 24], "layer": [0, 1, 2, 3, 5, 7, 9, 10, 11, 12, 13, 14, 18, 19, 21, 22, 23, 24, 25, 31, 32, 36, 43, 44, 57, 58, 65, 97, 100, 103], "sim": [0, 1, 2, 3, 5, 10, 11, 14, 18, 19, 21, 22, 23, 24, 39, 48, 68], "comput": [0, 4, 18, 88], "encod": [0, 4, 12, 18, 25, 49, 84, 88, 108], "4": [0, 1, 2, 4, 5, 6, 7, 9, 10, 11, 13, 14, 18, 19, 21, 22, 23, 24, 49], "run": [0, 4, 18, 20, 46, 66, 96], "algorithm": [0, 4, 18], "defin": [0, 6, 7, 18, 20], "callback": [0, 7, 18], "function": [0, 6, 7, 9, 18, 20, 78], "paramet": [0, 4, 18, 28, 30, 41, 51, 56, 86, 91, 108], "call": [0, 4, 18], "api": [0, 4, 18, 26, 27, 28, 29, 30, 31, 32, 33, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 61, 64, 65, 66, 67, 68, 69, 70, 71, 83, 86, 87, 88, 89, 91, 92, 93, 103, 104, 108], "adapt": [1, 5, 19, 41, 51], "round": [1, 5, 19, 41, 51, 100], "adaround": [1, 5, 13, 19, 28, 41, 51, 91], "instanti": [1, 2, 3, 4, 5, 6, 7, 10, 11, 14, 15, 16, 17, 19, 22, 23, 24], "train": [1, 2, 3, 5, 6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 19, 21, 22, 23, 24, 25, 68, 85, 90, 102, 103, 105], "valid": [1, 2, 3, 5, 6, 14, 15, 16, 17, 19, 22, 23, 24, 62], "determin": [1, 2, 3, 5, 6, 10, 11, 13, 14, 19, 22, 23, 24, 108], "appli": [1, 2, 5, 6, 12, 13, 14, 19, 22, 25], "next": [1, 5, 10, 11, 14, 15, 16, 17, 19, 20, 22, 23, 24], "step": [1, 5, 10, 11, 14, 15, 16, 17, 19, 20, 22, 23, 24, 75], "For": [1, 2, 3, 5, 6, 10, 11, 14, 15, 16, 17, 19, 20, 22, 23, 24], "more": [1, 2, 3, 5, 6, 10, 11, 14, 15, 16, 17, 19, 20, 22, 23, 24, 98], "inform": [1, 2, 3, 5, 6, 10, 11, 14, 15, 16, 17, 19, 20, 22, 23, 24, 98], "cross": [2, 14, 22, 31, 36, 43, 57, 65, 103], "equal": [2, 14, 22, 31, 36, 43, 57, 65, 103], "norm": [2, 22, 93], "cle": [2, 14, 22, 36], "method": [4, 36], "load": [4, 5, 6, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25], "find": 4, "fake": 4, "op": 4, "insert": 4, "regular": [4, 33], "fast": [4, 33], "0": [4, 33, 49, 109], "summari": [4, 7, 9, 13, 21], "get": [5, 10, 11, 13, 14, 15, 16, 17, 18, 19, 22, 23, 24, 87], "score": [5, 10, 11, 13, 14, 15, 16, 17, 18, 19, 22, 23, 24], "autoqu": [6, 20, 42, 53, 92], "pretrain": [6, 12, 20], "constant": [6, 7, 20], "helper": [6, 20, 36], "5": [6, 7, 21, 49], "awar": [7, 8, 10, 11, 21, 23, 24, 68, 90, 105], "batchnorm": [7, 21, 29, 54, 90], "re": [7, 21, 29, 54, 93], "estim": [7, 21, 29, 54, 93], "prepar": [7, 9, 35, 61, 90], "kera": [7, 8, 9], "quantizationsim": 7, "perform": [7, 10, 11, 21, 23, 24, 36], "qat": [7, 10, 11, 21, 23, 24, 68, 105], "export": [7, 21, 69, 83, 90], "transform": 8, "subclass": 9, "show": 9, "similar": 9, "differ": 9, "between": 9, "origin": 9, "discuss": 9, "limit": [9, 29, 35, 61], "rang": [11, 12, 24, 25], "learn": [11, 24], "quant": [12, 25, 37, 46, 66], "analyz": [12, 25, 37, 46, 66, 84], "quantanalyz": [12, 25, 104], "per": [12, 13, 25, 97, 100], "analysi": [12, 25, 102, 104], "enabl": [12, 25], "disabl": [12, 25], "wrapper": [12, 25], "min": [12, 25], "max": [12, 25], "pdf": [12, 25], "statist": [12, 21, 25], "mse": [12, 25], "loss": [12, 25], "quantsim": [13, 14, 90, 108], "channel": [13, 15, 17, 56, 94], "pcq": 13, "compress": [15, 16, 17, 30, 56, 70, 95, 97, 100, 111], "us": [15, 16, 17, 36, 74, 91, 100, 102], "prune": [15, 17, 56, 94], "fine": [15, 16, 17, 90, 100], "tune": [15, 16, 17, 90, 100], "spatial": [16, 17, 30, 56, 110], "svd": [16, 17, 30, 56, 110, 113], "reestim": [21, 54], "bia": [22, 55], "correct": [22, 55], "techniqu": [22, 100, 103], "bc": 22, "welcom": 26, "ai": [26, 87, 98], "effici": [26, 87, 98], "toolkit": [26, 87, 98], "doc": 26, "indic": 26, "tabl": 26, "aimet": [27, 28, 29, 30, 31, 32, 33, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 50, 51, 53, 54, 55, 56, 57, 58, 59, 65, 66, 67, 68, 69, 70, 71, 73, 74, 75, 87, 91, 92, 93, 94, 95, 96, 97, 99, 100, 102, 103, 104, 105, 107, 108, 109, 110, 111, 112, 113, 114], "tensorflow": [27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 49, 75, 112], "user": [28, 31, 39, 41, 42, 43, 51, 53, 55, 57, 64, 66, 68, 98, 103], "guid": [28, 31, 39, 41, 42, 43, 51, 53, 55, 57, 66, 68, 90, 98], "link": [28, 29, 31, 39, 41, 42, 43, 51, 53, 54, 55, 57, 66, 68], "top": [28, 29, 30, 32, 33, 35, 37, 39, 41, 42, 44, 45, 46, 48, 51, 53, 54, 56, 58, 59, 61, 64, 66, 68, 70, 71, 83, 86, 88, 89], "level": [28, 29, 30, 32, 33, 35, 36, 37, 39, 41, 42, 44, 45, 46, 48, 51, 53, 54, 56, 58, 59, 61, 64, 65, 66, 68, 70, 71, 83, 86, 88, 89], "enum": [28, 51, 58, 68], "definit": [28, 30, 33, 45, 51, 56, 58, 59, 65, 68], "code": [28, 29, 30, 31, 32, 33, 35, 36, 37, 39, 41, 42, 43, 44, 45, 46, 48, 51, 53, 54, 55, 56, 57, 58, 59, 61, 65, 66, 68, 69, 70, 71, 72, 86, 96], "introduct": [29, 30, 31, 36, 43, 54, 56, 57, 65], "greedi": [30, 56, 97], "select": [30, 56, 94, 97, 100], "configur": [30, 56, 88, 106, 108], "primit": [31, 36, 57, 65], "output": [32, 44, 58], "gener": [32, 44, 58], "group": [33, 45, 59], "callbackfunc": [33, 45, 59], "guidelin": [34, 60, 68, 91, 101], "higher": [36, 65], "lower": [36, 65], "custom": [36, 69], "datatyp": 36, "manual": 36, "mode": [36, 105], "specif": [46, 49, 66], "util": [46, 62, 66], "format": 49, "version": 49, "up": 49, "file": [49, 106], "6": 49, "architectur": 52, "checker": 52, "html": 52, "report": 52, "content": 52, "bn": [54, 93], "convbninfotyp": 55, "activationtyp": 55, "param": 55, "empir": 55, "analyt": 55, "weight": [56, 94, 113], "torch": [61, 69, 75], "fx": 61, "symbol": 61, "trace": 61, "multi": 63, "gpu": [63, 75], "support": 63, "peft": 64, "lora": 64, "clssetinfo": 65, "aimet_torch": [67, 72], "refer": [67, 100, 103], "v2": [67, 72], "": 67, "new": 67, "backward": 67, "compat": 67, "sparseconvolut": 69, "spconv": 69, "modul": [69, 72, 88], "visual": [70, 71, 82, 111, 112], "migrat": 72, "chang": 72, "process": 72, "import": 72, "quantizationsimmodel": 72, "move": 72, "from": [72, 74, 75], "quantwrapp": 72, "staticgrid": 72, "learnedgrid": 72, "affin": [72, 78], "float": [72, 80, 90], "instal": [73, 74, 75], "quick": 73, "releas": [73, 74, 75, 98, 109], "packag": [73, 74, 75], "system": 73, "requir": [73, 104], "advanc": 73, "instruct": 73, "docker": 74, "set": 74, "variant": [74, 84], "prebuilt": 74, "imag": 74, "build": 74, "local": 74, "start": [74, 87, 111], "contain": 74, "pypi": [74, 75], "environ": [74, 75], "setup": [74, 75], "prerequisit": [75, 90], "13": [75, 109], "common": 75, "debian": 75, "replac": 75, "pillow": 75, "simd": 75, "onnxruntim": 75, "post": [75, 85, 102, 103], "quantizationmixin": 77, "class": [78, 80, 81, 88], "floatquantizedequant": 79, "quantizedequant": 79, "tensor": 81, "tool": [82, 102], "blockwis": 83, "low": 83, "power": 83, "lpbq": 83, "gptvq": 86, "document": 87, "featur": [87, 95, 98, 102], "descript": [87, 104], "quickstart": 90, "point": 90, "case": [91, 100, 102], "hyper": 91, "overview": [92, 93, 97, 98, 100, 103, 104, 105, 106, 108, 111, 112, 114], "workflow": [92, 93, 102, 105, 108], "procedur": 94, "winnow": [94, 114], "reconstruct": 94, "guidebook": 95, "brows": 96, "server": [96, 111], "download": 96, "relat": 96, "ratio": [97, 100, 111], "how": [97, 114], "work": [97, 114], "explor": 97, "toc": 98, "tree": 98, "known": 99, "issu": 99, "option": 100, "rank": 100, "note": [100, 109], "faq": [100, 103], "debug": 102, "detail": 104, "recommend": 105, "structur": 106, "modifi": 106, "section": 106, "diagnost": 107, "nois": 108, "scheme": 108, "oper": 108, "22": 109, "21": 109, "20": 109, "19": 109, "py37": 109, "18": 109, "17": 109, "16": 109, "14": 109, "design": 111, "bokeh": 111, "session": 111}, "envversion": {"sphinx.domains.c": 2, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 8, "sphinx.domains.index": 1, "sphinx.domains.javascript": 2, "sphinx.domains.math": 2, "sphinx.domains.python": 3, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "nbsphinx": 4, "sphinx.ext.intersphinx": 1, "sphinx.ext.viewcode": 1, "sphinx": 57}, "alltitles": {"Automatic Mixed-Precision (AMP)": [[0, "Automatic-Mixed-Precision-(AMP)"], [4, "Automatic-Mixed-Precision-(AMP)"], [18, "Automatic-Mixed-Precision-(AMP)"]], "Overall flow": [[0, "Overall-flow"], [1, "Overall-flow"], [2, "Overall-flow"], [3, "Overall-flow"], [4, "Overall-flow"], [5, "Overall-flow"], [6, "Overall-flow"], [7, "Overall-flow"], [8, "Overall-flow"], [9, "Overall-flow"], [10, "Overall-flow"], [11, "Overall-flow"], [12, "Overall-flow"], [13, "Overall-flow"], [14, "Overall-flow"], [15, "Overall-flow"], [16, "Overall-flow"], [17, "Overall-flow"], [18, "Overall-flow"], [19, "Overall-flow"], [20, "Overall-flow"], [21, "Overall-flow"], [22, "Overall-flow"], [23, "Overall-flow"], [24, "Overall-flow"], [25, "Overall-flow"], [90, "overall-flow"]], "What this notebook is not": [[0, "What-this-notebook-is-not"], [4, "What-this-notebook-is-not"], [12, "What-this-notebook-is-not"], [13, "What-this-notebook-is-not"], [18, "What-this-notebook-is-not"], [21, "What-this-notebook-is-not"], [25, "What-this-notebook-is-not"]], "Dataset": [[0, "Dataset"], [1, "Dataset"], [2, "Dataset"], [3, "Dataset"], [4, "Dataset"], [5, "Dataset"], [6, "Dataset"], [7, "Dataset"], [10, "Dataset"], [11, "Dataset"], [12, "Dataset"], [13, "Dataset"], [14, "Dataset"], [15, "Dataset"], [16, "Dataset"], [17, "Dataset"], [18, "Dataset"], [19, "Dataset"], [20, "Dataset"], [21, "Dataset"], [22, "Dataset"], [23, "Dataset"], [24, "Dataset"], [25, "Dataset"]], "1. Example evaluation pipeline": [[0, "1.-Example-evaluation-pipeline"], [18, "1.-Example-evaluation-pipeline"]], "2. Convert an FP32 PyTorch model to ONNX, simplify & then evaluate baseline FP32 accuracy": [[0, "2.-Convert-an-FP32-PyTorch-model-to-ONNX,-simplify-&-then-evaluate-baseline-FP32-accuracy"], [1, "2.-Convert-an-FP32-PyTorch-model-to-ONNX,-simplify-&-then-evaluate-baseline-FP32-accuracy"], [2, "2.-Convert-an-FP32-PyTorch-model-to-ONNX,-simplify-&-then-evaluate-baseline-FP32-accuracy"], [3, "2.-Convert-an-FP32-PyTorch-model-to-ONNX,-simplify-&-then-evaluate-baseline-FP32-accuracy"]], "3. Create a quantization simulation model": [[0, "3.-Create-a-quantization-simulation-model"], [18, "3.-Create-a-quantization-simulation-model"]], "Fold Batch Normalization layers": [[0, "Fold-Batch-Normalization-layers"], [1, "Fold-Batch-Normalization-layers"], [3, "Fold-Batch-Normalization-layers"], [5, "Fold-Batch-Normalization-layers"], [10, "Fold-Batch-Normalization-layers"], [11, "Fold-Batch-Normalization-layers"], [13, "Fold-Batch-Normalization-layers"], [14, "Fold-Batch-Normalization-layers"], [18, "Fold-Batch-Normalization-layers"], [19, "Fold-Batch-Normalization-layers"], [23, "Fold-Batch-Normalization-layers"], [24, "Fold-Batch-Normalization-layers"]], "Create Quantization Sim Model": [[0, "Create-Quantization-Sim-Model"], [18, "Create-Quantization-Sim-Model"], [21, "Create-Quantization-Sim-Model"]], "Compute Encodings": [[0, "Compute-Encodings"], [4, "Compute-Encodings"], [18, "Compute-Encodings"]], "4. Run AMP algorithm on the quantized model": [[0, "4.-Run-AMP-algorithm-on-the-quantized-model"], [4, "4.-Run-AMP-algorithm-on-the-quantized-model"], [18, "4.-Run-AMP-algorithm-on-the-quantized-model"]], "Define callback functions for AMP": [[0, "Define-callback-functions-for-AMP"], [18, "Define-callback-functions-for-AMP"]], "Parameters for AMP algorithm": [[0, "Parameters-for-AMP-algorithm"], [4, "Parameters-for-AMP-algorithm"], [18, "Parameters-for-AMP-algorithm"]], "Call AMP API": [[0, "Call-AMP-API"], [18, "Call-AMP-API"]], "Adaptive Rounding (AdaRound)": [[1, "Adaptive-Rounding-(AdaRound)"], [5, "Adaptive-Rounding-(AdaRound)"], [19, "Adaptive-Rounding-(AdaRound)"]], "1. Instantiate the example training and validation pipeline": [[1, "1.-Instantiate-the-example-training-and-validation-pipeline"], [2, "1.-Instantiate-the-example-training-and-validation-pipeline"], [3, "1.-Instantiate-the-example-training-and-validation-pipeline"], [5, "1.-Instantiate-the-example-training-and-validation-pipeline"], [6, "1.-Instantiate-the-example-training-and-validation-pipeline"], [14, "1.-Instantiate-the-example-training-and-validation-pipeline"], [15, "1.-Instantiate-the-example-training-and-validation-pipeline"], [16, "1.-Instantiate-the-example-training-and-validation-pipeline"], [17, "1.-Instantiate-the-example-training-and-validation-pipeline"], [19, "1.-Instantiate-the-example-training-and-validation-pipeline"], [22, "1.-Instantiate-the-example-training-and-validation-pipeline"], [23, "1.-Instantiate-the-example-training-and-validation-pipeline"], [24, "1.-Instantiate-the-example-training-and-validation-pipeline"]], "3. Create a quantization simulation model and determine quantized accuracy": [[1, "3.-Create-a-quantization-simulation-model-and-determine-quantized-accuracy"], [2, "3.-Create-a-quantization-simulation-model-and-determine-quantized-accuracy"], [3, "3.-Create-a-quantization-simulation-model-and-determine-quantized-accuracy"], [5, "3.-Create-a-quantization-simulation-model-and-determine-quantized-accuracy"], [10, "3.-Create-a-quantization-simulation-model-and-determine-quantized-accuracy"], [11, "3.-Create-a-quantization-simulation-model-and-determine-quantized-accuracy"], [13, "3.-Create-a-quantization-simulation-model-and-determine-quantized-accuracy"], [14, "3.-Create-a-quantization-simulation-model-and-determine-quantized-accuracy"], [19, "3.-Create-a-quantization-simulation-model-and-determine-quantized-accuracy"], [22, "3.-Create-a-quantization-simulation-model-and-determine-quantized-accuracy"], [23, "3.-Create-a-quantization-simulation-model-and-determine-quantized-accuracy"], [24, "3.-Create-a-quantization-simulation-model-and-determine-quantized-accuracy"]], "Create the Quantization Sim Model": [[1, "Create-the-Quantization-Sim-Model"], [2, "Create-the-Quantization-Sim-Model"], [3, "Create-the-Quantization-Sim-Model"], [5, "Create-the-Quantization-Sim-Model"], [10, "Create-the-Quantization-Sim-Model"], [11, "Create-the-Quantization-Sim-Model"], [14, "Create-the-Quantization-Sim-Model"], [19, "Create-the-Quantization-Sim-Model"], [22, "Create-the-Quantization-Sim-Model"], [23, "Create-the-Quantization-Sim-Model"], [24, "Create-the-Quantization-Sim-Model"]], "4. Apply Adaround": [[1, "4.-Apply-Adaround"], [5, "4.-Apply-Adaround"], [13, "4.-Apply-Adaround"], [19, "4.-Apply-Adaround"]], "Next steps": [[1, "Next-steps"], [5, "Next-steps"], [10, "Next-steps"], [11, "Next-steps"], [14, "Next-steps"], [15, "Next-steps"], [16, "Next-steps"], [17, "Next-steps"], [19, "Next-steps"], [20, "Next-steps"], [22, "Next-steps"], [23, "Next-steps"], [24, "Next-steps"]], "For more information": [[1, "For-more-information"], [2, "For-more-information"], [3, "For-more-information"], [5, "For-more-information"], [6, "For-more-information"], [10, "For-more-information"], [11, "For-more-information"], [14, "For-more-information"], [15, "For-more-information"], [16, "For-more-information"], [17, "For-more-information"], [19, "For-more-information"], [20, "For-more-information"], [22, "For-more-information"], [23, "For-more-information"], [24, "For-more-information"]], "Cross-Layer Equalization": [[2, "Cross-Layer-Equalization"]], "Fold Batch Norm layers": [[2, "Fold-Batch-Norm-layers"], [22, "Fold-Batch-Norm-layers"]], "4. Apply CLE": [[2, "4.-Apply-CLE"], [14, "4.-Apply-CLE"]], "Quantization simulation": [[3, "Quantization-simulation"]], "1. Instantiate the example evaluation method": [[4, "1.-Instantiate-the-example-evaluation-method"]], "2. Load the FP32 model and evaluate the model to find the baseline FP32 accuracy": [[4, "2.-Load-the-FP32-model-and-evaluate-the-model-to-find-the-baseline-FP32-accuracy"]], "3.Create a quantization simulation model (with fake quantization ops inserted)": [[4, "3.Create-a-quantization-simulation-model-(with-fake-quantization-ops-inserted)"]], "Regular AMP": [[4, "Regular-AMP"]], "API Call for Regular AMP": [[4, "API-Call-for-Regular-AMP"]], "Fast AMP (AMP 2.0)": [[4, "Fast-AMP-(AMP-2.0)"]], "Summary": [[4, "Summary"], [7, "Summary"], [9, "Summary"], [13, "Summary"], [21, "Summary"]], "2. Load the model and evaluate to get a baseline FP32 accuracy score": [[5, "2.-Load-the-model-and-evaluate-to-get-a-baseline-FP32-accuracy-score"], [10, "2.-Load-the-model-and-evaluate-to-get-a-baseline-FP32-accuracy-score"], [11, "2.-Load-the-model-and-evaluate-to-get-a-baseline-FP32-accuracy-score"], [13, "2.-Load-the-model-and-evaluate-to-get-a-baseline-FP32-accuracy-score"], [14, "2.-Load-the-model-and-evaluate-to-get-a-baseline-FP32-accuracy-score"], [15, "2.-Load-the-model-and-evaluate-to-get-a-baseline-FP32-accuracy-score"], [16, "2.-Load-the-model-and-evaluate-to-get-a-baseline-FP32-accuracy-score"], [17, "2.-Load-the-model-and-evaluate-to-get-a-baseline-FP32-accuracy-score"], [18, "2.-Load-the-model-and-evaluate-to-get-a-baseline-FP32-accuracy-score"], [19, "2.-Load-the-model-and-evaluate-to-get-a-baseline-FP32-accuracy-score"], [22, "2.-Load-the-model-and-evaluate-to-get-a-baseline-FP32-accuracy-score"], [23, "2.-Load-the-model-and-evaluate-to-get-a-baseline-FP32-accuracy-score"], [24, "2.-Load-the-model-and-evaluate-to-get-a-baseline-FP32-accuracy-score"]], "AutoQuant": [[6, "AutoQuant"], [20, "AutoQuant"]], "2. Load a pretrained FP32 model": [[6, "2.-Load-a-pretrained-FP32-model"], [12, "2.-Load-a-pretrained-FP32-model"], [20, "2.-Load-a-pretrained-FP32-model"]], "3. Determine the baseline FP32 accuracy": [[6, "3.-Determine-the-baseline-FP32-accuracy"]], "4. Define constants and helper functions": [[6, "4.-Define-constants-and-helper-functions"]], "5. Apply AutoQuant": [[6, "5.-Apply-AutoQuant"]], "Quantization-Aware Training with BatchNorm Re-estimation": [[7, "Quantization-Aware-Training-with-BatchNorm-Re-estimation"], [21, "Quantization-Aware-Training-with-BatchNorm-Re-estimation"]], "1. Instantiate the example evaluation and training pipeline": [[7, "1.-Instantiate-the-example-evaluation-and-training-pipeline"]], "2. Define Constants and Datasets Prepare": [[7, "2.-Define-Constants-and-Datasets-Prepare"]], "2. Create the model in Keras": [[7, "2.-Create-the-model-in-Keras"]], "3. Train and evaluate the model": [[7, "3.-Train-and-evaluate-the-model"]], "4. Create a QuantizationSim Model": [[7, "4.-Create-a-QuantizationSim-Model"]], "Prepare the evaluation callback function": [[7, "Prepare-the-evaluation-callback-function"]], "5. Perform QAT": [[7, "5.-Perform-QAT"]], "Fold BatchNorm Layers": [[7, "Fold-BatchNorm-Layers"], [21, "Fold-BatchNorm-Layers"]], "5. Export Model": [[7, "5.-Export-Model"], [21, "5.-Export-Model"]], "Quantization-Aware Training with a Keras Transformer Model": [[8, "Quantization-Aware-Training-with-a-Keras-Transformer-Model"]], "Keras Model Preparer": [[9, "Keras-Model-Preparer"]], "1. Creating a Keras model with subclass layers": [[9, "1.-Creating-a-Keras-model-with-subclass-layers"]], "2. Converting the Keras model with subclass layers to a Keras model with functional layers": [[9, "2.-Converting-the-Keras-model-with-subclass-layers-to-a-Keras-model-with-functional-layers"]], "3. Showing similarities and differences between the original and converted models": [[9, "3.-Showing-similarities-and-differences-between-the-original-and-converted-models"]], "4. Discussing the limitations of the Keras Model Preparer": [[9, "4.-Discussing-the-limitations-of-the-Keras-Model-Preparer"]], "Quantization-aware training": [[10, "Quantization-aware-training"], [23, "Quantization-aware-training"]], "1. Instantiate the example evaluation and training datasets": [[10, "1.-Instantiate-the-example-evaluation-and-training-datasets"], [11, "1.-Instantiate-the-example-evaluation-and-training-datasets"]], "4. Perform QAT": [[10, "4.-Perform-QAT"], [11, "4.-Perform-QAT"], [23, "4.-Perform-QAT"], [24, "4.-Perform-QAT"]], "Quantization-Aware training with range learning": [[11, "Quantization-Aware-training-with-range-learning"]], "Quant Analyzer": [[12, "Quant-Analyzer"], [25, "Quant-Analyzer"]], "1. Example evaluation and training pipeline": [[12, "1.-Example-evaluation-and-training-pipeline"], [13, "1.-Example-evaluation-and-training-pipeline"], [21, "1.-Example-evaluation-and-training-pipeline"], [25, "1.-Example-evaluation-and-training-pipeline"]], "3. Apply QuantAnalyzer to the model": [[12, "3.-Apply-QuantAnalyzer-to-the-model"], [25, "3.-Apply-QuantAnalyzer-to-the-model"]], "Per-layer analysis by enabling/disabling quantization wrappers": [[12, "Per-layer-analysis-by-enabling/disabling-quantization-wrappers"], [25, "Per-layer-analysis-by-enabling/disabling-quantization-wrappers"]], "Encoding min/max ranges": [[12, "Encoding-min/max-ranges"], [25, "Encoding-min/max-ranges"]], "PDF of statistics": [[12, "PDF-of-statistics"], [25, "PDF-of-statistics"]], "Per-layer MSE loss": [[12, "Per-layer-MSE-loss"], [25, "Per-layer-MSE-loss"]], "Quantsim and Adaround - Per Channel Quantization (PCQ)": [[13, "Quantsim-and-Adaround---Per-Channel-Quantization-(PCQ)"]], "Cross-Layer Equalization with QuantSim": [[14, "Cross-Layer-Equalization-with-QuantSim"]], "Model compression using channel pruning": [[15, "Model-compression-using-channel-pruning"]], "3. Compress the model and fine-tune": [[15, "3.-Compress-the-model-and-fine-tune"], [16, "3.-Compress-the-model-and-fine-tune"], [17, "3.-Compress-the-model-and-fine-tune"]], "Model compression using spatial SVD": [[16, "Model-compression-using-spatial-SVD"]], "Model compression using spatial SVD and channel pruning": [[17, "Model-compression-using-spatial-SVD-and-channel-pruning"]], "1. Define Constants and Helper functions": [[20, "1.-Define-Constants-and-Helper-functions"]], "3. Run AutoQuant": [[20, "3.-Run-AutoQuant"]], "2. Load FP32 model": [[21, "2.-Load-FP32-model"]], "3. Create a quantization simulation model and Perform QAT": [[21, "3.-Create-a-quantization-simulation-model-and-Perform-QAT"]], "Perform QAT": [[21, "Perform-QAT"]], "4. Perform BatchNorm Reestimation": [[21, "4.-Perform-BatchNorm-Reestimation"]], "Re-estimate BatchNorm Statistics": [[21, "Re-estimate-BatchNorm-Statistics"]], "Cross-Layer Equalization and Bias Correction": [[22, "Cross-Layer-Equalization-and-Bias-Correction"]], "Techniques": [[22, "Techniques"]], "4. Apply CLE and BC": [[22, "4.-Apply-CLE-and-BC"]], "CLE": [[22, "CLE"]], "Bias Correction": [[22, "Bias-Correction"]], "Quantization-aware training with range learning": [[24, "Quantization-aware-training-with-range-learning"]], "2. Load the model": [[25, "2.-Load-the-model"]], "Welcome to AI Model Efficiency Toolkit API Docs!": [[26, "welcome-to-ai-model-efficiency-toolkit-api-docs"]], "Indices and tables": [[26, "indices-and-tables"]], "AIMET TensorFlow APIs": [[27, "aimet-tensorflow-apis"]], "AIMET TensorFlow AdaRound API": [[28, "aimet-tensorflow-adaround-api"]], "User Guide Link": [[28, "user-guide-link"], [31, "user-guide-link"], [39, "user-guide-link"], [41, "user-guide-link"], [42, "user-guide-link"], [43, "user-guide-link"], [51, "user-guide-link"], [53, "user-guide-link"], [55, "user-guide-link"], [57, "user-guide-link"], [66, "user-guide-link"], [68, "user-guide-link"]], "Examples Notebook Link": [[28, "examples-notebook-link"], [29, "examples-notebook-link"], [31, "examples-notebook-link"], [51, "examples-notebook-link"], [53, "examples-notebook-link"], [54, "examples-notebook-link"], [57, "examples-notebook-link"], [66, "examples-notebook-link"], [68, "examples-notebook-link"]], "Top-level API": [[28, "top-level-api"], [32, "top-level-api"], [35, "top-level-api"], [37, "top-level-api"], [39, "top-level-api"], [41, "top-level-api"], [42, "top-level-api"], [44, "top-level-api"], [45, "top-level-api"], [46, "top-level-api"], [48, "top-level-api"], [51, "top-level-api"], [53, "top-level-api"], [58, "top-level-api"], [59, "top-level-api"], [61, "top-level-api"], [64, "top-level-api"], [66, "top-level-api"], [68, "top-level-api"], [88, "top-level-api"], [89, "top-level-api"]], "Adaround Parameters": [[28, "adaround-parameters"], [41, "adaround-parameters"], [51, "adaround-parameters"]], "Enum Definition": [[28, "enum-definition"], [51, "enum-definition"], [58, "enum-definition"], [68, "enum-definition"]], "Code Examples": [[28, "code-examples"], [30, "code-examples"], [33, "code-examples"], [35, "code-examples"], [37, "code-examples"], [39, "code-examples"], [42, "code-examples"], [45, "code-examples"], [46, "code-examples"], [48, "code-examples"], [53, "code-examples"], [56, "code-examples"], [59, "code-examples"], [61, "code-examples"], [66, "code-examples"], [70, "code-examples"], [71, "code-examples"], [72, "code-examples"]], "AIMET TensorFlow BatchNorm Re-estimation APIs": [[29, "aimet-tensorflow-batchnorm-re-estimation-apis"]], "Introduction": [[29, "introduction"], [30, "introduction"], [31, "introduction"], [36, "introduction"], [43, "introduction"], [54, "introduction"], [56, "introduction"], [57, "introduction"], [65, "introduction"]], "Top-level APIs": [[29, "top-level-apis"], [54, "top-level-apis"]], "Code Example": [[29, "code-example"], [31, "code-example"], [32, "code-example"], [43, "code-example"], [44, "code-example"], [57, "code-example"], [58, "code-example"], [69, "code-example"], [86, "code-example"]], "Limitations": [[29, "limitations"], [35, "limitations"]], "AIMET TensorFlow Compression API": [[30, "aimet-tensorflow-compression-api"]], "Top-level API for Compression": [[30, "top-level-api-for-compression"], [56, "top-level-api-for-compression"]], "Greedy Selection Parameters": [[30, "greedy-selection-parameters"], [56, "greedy-selection-parameters"]], "Spatial SVD Configuration": [[30, "spatial-svd-configuration"], [56, "spatial-svd-configuration"]], "Configuration Definitions": [[30, "configuration-definitions"], [56, "configuration-definitions"]], "AIMET TensorFlow Cross Layer Equalization APIs": [[31, "aimet-tensorflow-cross-layer-equalization-apis"]], "Cross Layer Equalization API": [[31, "cross-layer-equalization-api"], [43, "cross-layer-equalization-api"], [57, "cross-layer-equalization-api"]], "Primitive APIs": [[31, "primitive-apis"], [57, "primitive-apis"]], "AIMET TensorFlow Layer Output Generation API": [[32, "aimet-tensorflow-layer-output-generation-api"]], "AIMET TensorFlow Mixed Precision API": [[33, "aimet-tensorflow-mixed-precision-api"]], "Top-level API for Regular AMP": [[33, "top-level-api-for-regular-amp"]], "Top-level API for Fast AMP (AMP 2.0)": [[33, "top-level-api-for-fast-amp-amp-2-0"]], "Quantizer Groups definition": [[33, "quantizer-groups-definition"], [45, "quantizer-groups-definition"], [59, "quantizer-groups-definition"]], "CallbackFunc Definition": [[33, "callbackfunc-definition"], [45, "callbackfunc-definition"], [59, "callbackfunc-definition"]], "TensorFlow Model Guidelines": [[34, "tensorflow-model-guidelines"]], "TensorFlow Model Preparer API": [[35, "tensorflow-model-preparer-api"]], "AIMET TensorFlow Cross Layer Equalization Primitive API": [[36, "aimet-tensorflow-cross-layer-equalization-primitive-api"]], "Higher Level APIs for Cross Layer Equalization": [[36, "higher-level-apis-for-cross-layer-equalization"], [65, "higher-level-apis-for-cross-layer-equalization"]], "Code Examples for Higher Level APIs": [[36, "code-examples-for-higher-level-apis"], [65, "code-examples-for-higher-level-apis"]], "Lower Level APIs for Cross Layer Equalization": [[36, "lower-level-apis-for-cross-layer-equalization"], [65, "lower-level-apis-for-cross-layer-equalization"]], "Custom Datatype used": [[36, "custom-datatype-used"]], "Code Example for Lower level APIs": [[36, "code-example-for-lower-level-apis"]], "Example helper methods to perform CLE in manual mode": [[36, "example-helper-methods-to-perform-cle-in-manual-mode"]], "AIMET TensorFlow Quant Analyzer API": [[37, "aimet-tensorflow-quant-analyzer-api"]], "AIMET TensorFlow Quantization APIs": [[38, "aimet-tensorflow-quantization-apis"]], "AIMET TensorFlow Quantization SIM API": [[39, "aimet-tensorflow-quantization-sim-api"]], "AIMET ONNX APIs": [[40, "aimet-onnx-apis"]], "AIMET ONNX AdaRound API": [[41, "aimet-onnx-adaround-api"]], "Code Example - Adaptive Rounding (AdaRound)": [[41, "code-example-adaptive-rounding-adaround"], [51, "code-example-adaptive-rounding-adaround"]], "AIMET ONNX AutoQuant API": [[42, "aimet-onnx-autoquant-api"]], "AIMET ONNX Cross Layer Equalization APIs": [[43, "aimet-onnx-cross-layer-equalization-apis"]], "AIMET ONNX Layer Output Generation API": [[44, "aimet-onnx-layer-output-generation-api"]], "AIMET ONNX Mixed Precision API": [[45, "aimet-onnx-mixed-precision-api"]], "AIMET ONNX Quant Analyzer API": [[46, "aimet-onnx-quant-analyzer-api"]], "Run specific utility": [[46, "run-specific-utility"], [66, "run-specific-utility"]], "AIMET ONNX Quantization APIs": [[47, "aimet-onnx-quantization-apis"]], "AIMET ONNX Quantization SIM API": [[48, "aimet-onnx-quantization-sim-api"]], "Encoding Format Specification": [[49, "encoding-format-specification"]], "1. Versioning": [[49, "versioning"]], "2. Version 0.4.0 (up to)": [[49, "version-0-4-0-up-to"]], "2.1. Encoding Specification": [[49, "encoding-specification"]], "2.2. Encoding File Example for PyTorch": [[49, "encoding-file-example-for-pytorch"]], "2.3. Encoding File Example for TensorFlow": [[49, "encoding-file-example-for-tensorflow"]], "3. Version 0.5.0": [[49, "version-0-5-0"]], "3.1. Encoding Specification": [[49, "id1"]], "3.2. Encoding File Example for PyTorch": [[49, "id2"]], "3.3. Encoding File Example for TensorFlow": [[49, "id3"]], "4. Version 0.6.1": [[49, "version-0-6-1"]], "4.1. Encoding Specification": [[49, "id4"]], "AIMET PyTorch APIs": [[50, "aimet-pytorch-apis"]], "AIMET PyTorch AdaRound API": [[51, "aimet-pytorch-adaround-api"]], "Architecture Checker API": [[52, "architecture-checker-api"]], "HTML report content": [[52, "id1"]], "AIMET PyTorch AutoQuant API": [[53, "aimet-pytorch-autoquant-api"]], "AIMET PyTorch BatchNorm Re-estimation APIs": [[54, "aimet-pytorch-batchnorm-re-estimation-apis"]], "Code Example - BN-Reestimation": [[54, "code-example-bn-reestimation"]], "AIMET PyTorch Bias Correction API": [[55, "aimet-pytorch-bias-correction-api"]], "Bias Correction API": [[55, "bias-correction-api"]], "ConvBnInfoType": [[55, "convbninfotype"]], "ActivationType": [[55, "activationtype"]], "Quantization Params": [[55, "quantization-params"]], "Code Example #1 Empirical Bias Correction": [[55, "code-example-1-empirical-bias-correction"]], "Code Example #2 Analytical + Empirical Bias correction": [[55, "code-example-2-analytical-empirical-bias-correction"]], "AIMET PyTorch Compression API": [[56, "aimet-pytorch-compression-api"]], "Weight SVD Configuration": [[56, "weight-svd-configuration"]], "Channel Pruning Configuration": [[56, "channel-pruning-configuration"]], "AIMET PyTorch Cross Layer Equalization APIs": [[57, "aimet-pytorch-cross-layer-equalization-apis"]], "AIMET PyTorch Layer Output Generation API": [[58, "aimet-pytorch-layer-output-generation-api"]], "AIMET PyTorch Mixed Precision API": [[59, "aimet-pytorch-mixed-precision-api"]], "PyTorch Model Guidelines": [[60, "pytorch-model-guidelines"]], "Model Preparer API": [[61, "model-preparer-api"]], "Limitations of torch.fx symbolic trace API": [[61, "limitations-of-torch-fx-symbolic-trace-api"]], "Model Validator Utility": [[62, "model-validator-utility"]], "PyTorch Multi-GPU support": [[63, "pytorch-multi-gpu-support"]], "PEFT LoRA": [[64, "peft-lora"]], "User flow": [[64, "user-flow"]], "AIMET PyTorch Cross Layer Equalization Primitive API": [[65, "aimet-pytorch-cross-layer-equalization-primitive-api"]], "ClsSetInfo Definition": [[65, "clssetinfo-definition"]], "Code Examples for Lower Level APIs": [[65, "code-examples-for-lower-level-apis"]], "AIMET PyTorch Quant Analyzer API": [[66, "aimet-pytorch-quant-analyzer-api"]], "AIMET PyTorch Quantization APIs": [[67, "aimet-pytorch-quantization-apis"]], "aimet_torch": [[67, "aimet-torch"]], "API Reference": [[67, "api-reference"], [67, "id1"]], "aimet_torch.v2": [[67, "aimet-torch-v2"]], "What\u2019s New": [[67, "what-s-new"]], "Backwards Compatibility": [[67, "backwards-compatibility"]], "AIMET PyTorch Quantization SIM API": [[68, "aimet-pytorch-quantization-sim-api"]], "Guidelines": [[68, "guidelines"]], "Code Example - Quantization Aware Training (QAT)": [[68, "code-example-quantization-aware-training-qat"]], "AIMET Torch SparseConvolution custom onnx export": [[69, "aimet-torch-sparseconvolution-custom-onnx-export"]], "Custom API for the spconv modules": [[69, "custom-api-for-the-spconv-modules"]], "AIMET Visualization Compression API": [[70, "aimet-visualization-compression-api"]], "Top-level API Compression": [[70, "top-level-api-compression"]], "AIMET Visualization for Quantization API": [[71, "aimet-visualization-for-quantization-api"]], "Top-level API Quantization": [[71, "top-level-api-quantization"]], "Migrate to aimet_torch.v2": [[72, "migrate-to-aimet-torch-v2"]], "Changes in aimet_torch v2": [[72, "changes-in-aimet-torch-v2"]], "Migration Process": [[72, "migration-process"]], "Imports": [[72, "imports"]], "QuantizationSimModel": [[72, "quantizationsimmodel"]], "Moving from QuantWrapper to Quantized Modules": [[72, "moving-from-quantwrapper-to-quantized-modules"]], "Moving from StaticGrid and LearnedGrid Quantizer to Affine and Float Quantizer": [[72, "moving-from-staticgrid-and-learnedgrid-quantizer-to-affine-and-float-quantizer"]], "AIMET Installation": [[73, "aimet-installation"]], "Quick Install": [[73, "quick-install"]], "Release Packages": [[73, "release-packages"]], "System Requirements": [[73, "system-requirements"]], "Advanced Installation Instructions": [[73, "advanced-installation-instructions"]], "AIMET Installation in Docker": [[74, "aimet-installation-in-docker"]], "Set variant": [[74, "set-variant"]], "Use prebuilt docker image": [[74, "use-prebuilt-docker-image"]], "Build docker image locally": [[74, "build-docker-image-locally"]], "Start docker container": [[74, "start-docker-container"]], "Install AIMET packages": [[74, "install-aimet-packages"], [75, "install-aimet-packages"]], "From PyPI": [[74, "from-pypi"], [75, "from-pypi"]], "From Release Package": [[74, "from-release-package"], [75, "from-release-package"]], "Environment setup": [[74, "environment-setup"], [75, "environment-setup"]], "AIMET Installation and Setup": [[75, "aimet-installation-and-setup"]], "Install prerequisite packages": [[75, "install-prerequisite-packages"]], "Install GPU packages": [[75, "install-gpu-packages"]], "Install GPU packages for PyTorch 2.1 or PyTorch 1.13 or ONNX or TensorFlow": [[75, "install-gpu-packages-for-pytorch-2-1-or-pytorch-1-13-or-onnx-or-tensorflow"]], "Install common debian packages": [[75, "install-common-debian-packages"]], "Install tensorflow GPU debian packages": [[75, "install-tensorflow-gpu-debian-packages"]], "Install torch GPU debian packages": [[75, "install-torch-gpu-debian-packages"]], "Install ONNX GPU debian packages": [[75, "install-onnx-gpu-debian-packages"]], "Replace Pillow with Pillow-SIMD": [[75, "replace-pillow-with-pillow-simd"]], "Replace onnxruntime with onnxruntime-gpu": [[75, "replace-onnxruntime-with-onnxruntime-gpu"]], "Post installation steps": [[75, "post-installation-steps"]], "QuantizationMixin": [[77, "quantizationmixin"]], "quantization.affine": [[78, "module-aimet_torch.v2.quantization.affine"]], "Classes": [[78, "classes"], [80, "classes"], [81, "classes"]], "Functions": [[78, "functions"]], "FloatQuantizeDequantize": [[79, "floatquantizedequantize"]], "QuantizeDequantize": [[79, "quantizedequantize"]], "quantization.float": [[80, "module-aimet_torch.v2.quantization.float"]], "quantization.tensor": [[81, "quantization-tensor"]], "Visualization Tools": [[82, "visualization-tools"]], "Blockwise Quantization": [[83, "blockwise-quantization"]], "Low Power Blockwise Quantization (LPBQ)": [[83, "low-power-blockwise-quantization-lpbq"]], "Top Level API": [[83, "top-level-api"], [86, "top-level-api"]], "Export": [[83, "export"]], "Encoding Analyzers": [[84, "encoding-analyzers"]], "Variants": [[84, "variants"]], "Post-Training Quantization": [[85, "post-training-quantization"], [102, "post-training-quantization"]], "GPTVQ": [[86, "gptvq"]], "GPTVQ Parameters": [[86, "gptvq-parameters"]], "AIMET: AI Model Efficiency Toolkit Documentation": [[87, "aimet-ai-model-efficiency-toolkit-documentation"]], "Getting Started": [[87, "getting-started"]], "Examples": [[87, null]], "Feature Descriptions": [[87, null]], "AIMET PyTorch API": [[87, null]], "Quantized Modules": [[88, "quantized-modules"]], "Configuration": [[88, "configuration"]], "Computing Encodings": [[88, "computing-encodings"]], "Quantized Module Classes": [[88, "quantized-module-classes"]], "Quantizers": [[89, "quantizers"]], "Quickstart Guide": [[90, "quickstart-guide"]], "PyTorch prerequisites": [[90, "pytorch-prerequisites"]], "Prepare the floating point model for quantization": [[90, "prepare-the-floating-point-model-for-quantization"]], "1) Model preparation": [[90, "model-preparation"]], "2) BatchNorm fold": [[90, "batchnorm-fold"]], "Quantize the model": [[90, "quantize-the-model"]], "Fine-tune the model with quantization aware training": [[90, "fine-tune-the-model-with-quantization-aware-training"]], "Export the quantsim model": [[90, "export-the-quantsim-model"]], "AIMET AdaRound": [[91, "aimet-adaround"]], "AdaRound use cases": [[91, "adaround-use-cases"]], "AdaRound hyper parameters guidelines": [[91, "adaround-hyper-parameters-guidelines"]], "AdaRound API": [[91, "adaround-api"]], "AIMET AutoQuant": [[92, "aimet-autoquant"]], "Overview": [[92, "overview"], [93, "overview"], [97, "overview"], [98, "overview"], [100, "overview"], [103, "overview"], [104, "overview"], [105, "overview"], [106, "overview"], [108, "overview"], [111, "overview"], [112, "overview"], [114, "overview"]], "Workflow": [[92, "workflow"], [93, "workflow"]], "AutoQuant API": [[92, "autoquant-api"]], "AIMET Batch Norm Re-estimation": [[93, "aimet-batch-norm-re-estimation"]], "BN Re-estimation API": [[93, "bn-re-estimation-api"]], "AIMET channel pruning": [[94, "aimet-channel-pruning"]], "Procedure": [[94, "procedure"]], "Channel selection": [[94, "channel-selection"]], "Winnowing": [[94, "winnowing"]], "Weight reconstruction": [[94, "weight-reconstruction"]], "AIMET Compression Features Guidebook": [[95, "aimet-compression-features-guidebook"]], "AIMET examples": [[96, "aimet-examples"]], "Browse the notebooks": [[96, "browse-the-notebooks"]], "Running the notebooks": [[96, "running-the-notebooks"]], "1. Run the notebook server": [[96, "run-the-notebook-server"]], "2. Download the example notebooks and related code": [[96, "download-the-example-notebooks-and-related-code"]], "3. Run the notebooks": [[96, "run-the-notebooks"]], "AIMET greedy compression ratio selection": [[97, "aimet-greedy-compression-ratio-selection"]], "How it works": [[97, "how-it-works"]], "Per-layer exploration": [[97, "per-layer-exploration"]], "Compression ratio selection": [[97, "compression-ratio-selection"], [100, "compression-ratio-selection"]], "AI Model Efficiency Toolkit User Guide": [[98, "ai-model-efficiency-toolkit-user-guide"]], "Features": [[98, "features"]], "More Information": [[98, "more-information"]], "Release Information": [[98, "release-information"]], "toc tree": [[98, "toc-tree"]], "AIMET Known Issues": [[99, "aimet-known-issues"]], "AIMET model compression": [[100, "aimet-model-compression"]], "Use Case": [[100, "use-case"]], "Model compression": [[100, "model-compression"]], "Optional techniques": [[100, "optional-techniques"]], "Rank Rounding": [[100, "rank-rounding"]], "Per-layer fine-tuning": [[100, "per-layer-fine-tuning"]], "NOTE": [[100, null]], "FAQs": [[100, "faqs"], [103, "faqs"]], "References": [[100, "references"], [103, "references"]], "Model Guidelines for PyTorch": [[101, "model-guidelines-for-pytorch"]], "AIMET model quantization": [[102, "aimet-model-quantization"]], "Use cases": [[102, "use-cases"]], "AIMET quantization features": [[102, "aimet-quantization-features"]], "Debugging and Analysis Tools": [[102, "debugging-and-analysis-tools"]], "AIMET quantization workflow": [[102, "aimet-quantization-workflow"]], "PyTorch": [[102, "pytorch"], [112, "pytorch"]], "Debugging": [[102, "debugging"]], "AIMET post-training quantization techniques": [[103, "aimet-post-training-quantization-techniques"]], "User Flow": [[103, "user-flow"]], "Cross-Layer Equalization API": [[103, "cross-layer-equalization-api"]], "AIMET QuantAnalyzer": [[104, "aimet-quantanalyzer"]], "Requirements": [[104, "requirements"]], "Detailed analysis descriptions": [[104, "detailed-analysis-descriptions"]], "QuantAnalyzer API": [[104, "quantanalyzer-api"]], "AIMET quantization aware training": [[105, "aimet-quantization-aware-training"]], "QAT workflow": [[105, "qat-workflow"]], "QAT modes": [[105, "qat-modes"]], "Recommendations for quantization-aware training": [[105, "recommendations-for-quantization-aware-training"]], "Quantization simulation configuration": [[106, "quantization-simulation-configuration"]], "Configuration file structure": [[106, "configuration-file-structure"]], "Modifying configuration file sections": [[106, "modifying-configuration-file-sections"]], "AIMET quantization diagnostics": [[107, "aimet-quantization-diagnostics"]], "AIMET quantization simulation": [[108, "aimet-quantization-simulation"]], "QuantSim workflow": [[108, "quantsim-workflow"]], "Simulating quantization noise": [[108, "simulating-quantization-noise"]], "Determining quantization parameters (encodings)": [[108, "determining-quantization-parameters-encodings"]], "Quantization schemes": [[108, "quantization-schemes"]], "Configuring quantization simulation operations": [[108, "configuring-quantization-simulation-operations"]], "Quantization Simulation APIs": [[108, "quantization-simulation-apis"]], "AIMET Release Notes": [[109, "aimet-release-notes"]], "1.22.2": [[109, "id1"]], "1.22.1": [[109, "id2"]], "1.22.0": [[109, "id3"]], "1.21.0": [[109, "id4"]], "1.20.0": [[109, "id5"]], "1.19.1.py37": [[109, "py37"]], "1.19.1": [[109, "id6"]], "1.18.0.py37": [[109, "id7"]], "1.18.0": [[109, "id8"]], "1.17.0.py37": [[109, "id9"]], "1.17.0": [[109, "id10"]], "1.16.2.py37": [[109, "id11"]], "1.16.2": [[109, "id12"]], "1.16.1.py37": [[109, "id13"]], "1.16.1": [[109, "id14"]], "1.16.0": [[109, "id15"]], "1.14.0": [[109, "id16"]], "1.13.0": [[109, "id17"]], "AIMET spatial SVD": [[110, "aimet-spatial-svd"]], "AIMET visualization": [[111, "aimet-visualization"]], "Design": [[111, "design"]], "Compression": [[111, "compression"]], "Starting a Bokeh server session": [[111, "starting-a-bokeh-server-session"]], "Visualizing compression ratios": [[111, "visualizing-compression-ratios"]], "AIMET visualization for quantization": [[112, "aimet-visualization-for-quantization"]], "Quantization": [[112, "quantization"]], "TensorFlow": [[112, "tensorflow"]], "AIMET weight SVD": [[113, "aimet-weight-svd"]], "AIMET winnowing": [[114, "aimet-winnowing"]], "Winnowing overview": [[114, "winnowing-overview"]], "How winnowing works": [[114, "how-winnowing-works"]]}, "indexentries": {"adaroundparameters (class in aimet_tensorflow.keras.adaround_weight)": [[28, "aimet_tensorflow.keras.adaround_weight.AdaroundParameters"]], "quantscheme (class in aimet_common.defs)": [[28, "aimet_common.defs.QuantScheme"], [51, "aimet_common.defs.QuantScheme"], [68, "aimet_common.defs.QuantScheme"]], "apply_adaround() (in module aimet_tensorflow.keras.adaround_weight.adaround)": [[28, "aimet_tensorflow.keras.adaround_weight.Adaround.apply_adaround"]], "post_training_percentile (aimet_common.defs.quantscheme attribute)": [[28, "aimet_common.defs.QuantScheme.post_training_percentile"], [51, "aimet_common.defs.QuantScheme.post_training_percentile"], [68, "aimet_common.defs.QuantScheme.post_training_percentile"]], "post_training_tf (aimet_common.defs.quantscheme attribute)": [[28, "aimet_common.defs.QuantScheme.post_training_tf"], [51, "aimet_common.defs.QuantScheme.post_training_tf"], [68, "aimet_common.defs.QuantScheme.post_training_tf"]], "post_training_tf_enhanced (aimet_common.defs.quantscheme attribute)": [[28, "aimet_common.defs.QuantScheme.post_training_tf_enhanced"], [51, "aimet_common.defs.QuantScheme.post_training_tf_enhanced"], [68, "aimet_common.defs.QuantScheme.post_training_tf_enhanced"]], "training_range_learning_with_tf_enhanced_init (aimet_common.defs.quantscheme attribute)": [[28, "aimet_common.defs.QuantScheme.training_range_learning_with_tf_enhanced_init"], [51, "aimet_common.defs.QuantScheme.training_range_learning_with_tf_enhanced_init"], [68, "aimet_common.defs.QuantScheme.training_range_learning_with_tf_enhanced_init"]], "training_range_learning_with_tf_init (aimet_common.defs.quantscheme attribute)": [[28, "aimet_common.defs.QuantScheme.training_range_learning_with_tf_init"], [51, "aimet_common.defs.QuantScheme.training_range_learning_with_tf_init"], [68, "aimet_common.defs.QuantScheme.training_range_learning_with_tf_init"]], "fold_all_batch_norms_to_scale() (in module aimet_tensorflow.keras.batch_norm_fold)": [[29, "aimet_tensorflow.keras.batch_norm_fold.fold_all_batch_norms_to_scale"]], "reestimate_bn_stats() (in module aimet_tensorflow.keras.bn_reestimation)": [[29, "aimet_tensorflow.keras.bn_reestimation.reestimate_bn_stats"]], "compressionscheme (class in aimet_common.defs)": [[30, "aimet_common.defs.CompressionScheme"]], "costmetric (class in aimet_common.defs)": [[30, "aimet_common.defs.CostMetric"]], "modelcompressor (class in aimet_tensorflow.keras.compress)": [[30, "aimet_tensorflow.keras.compress.ModelCompressor"]], "modulecompratiopair (class in aimet_tensorflow.keras.defs)": [[30, "aimet_tensorflow.keras.defs.ModuleCompRatioPair"]], "spatialsvdparameters (class in aimet_tensorflow.keras.defs)": [[30, "aimet_tensorflow.keras.defs.SpatialSvdParameters"]], "spatialsvdparameters.automodeparams (class in aimet_tensorflow.keras.defs)": [[30, "aimet_tensorflow.keras.defs.SpatialSvdParameters.AutoModeParams"]], "spatialsvdparameters.manualmodeparams (class in aimet_tensorflow.keras.defs)": [[30, "aimet_tensorflow.keras.defs.SpatialSvdParameters.ManualModeParams"]], "spatialsvdparameters.mode (class in aimet_tensorflow.keras.defs)": [[30, "aimet_tensorflow.keras.defs.SpatialSvdParameters.Mode"]], "auto (aimet_tensorflow.keras.defs.spatialsvdparameters.mode attribute)": [[30, "aimet_tensorflow.keras.defs.SpatialSvdParameters.Mode.auto"]], "channel_pruning (aimet_common.defs.compressionscheme attribute)": [[30, "aimet_common.defs.CompressionScheme.channel_pruning"]], "compress_model() (aimet_tensorflow.keras.compress.modelcompressor static method)": [[30, "aimet_tensorflow.keras.compress.ModelCompressor.compress_model"]], "mac (aimet_common.defs.costmetric attribute)": [[30, "aimet_common.defs.CostMetric.mac"]], "manual (aimet_tensorflow.keras.defs.spatialsvdparameters.mode attribute)": [[30, "aimet_tensorflow.keras.defs.SpatialSvdParameters.Mode.manual"]], "memory (aimet_common.defs.costmetric attribute)": [[30, "aimet_common.defs.CostMetric.memory"]], "spatial_svd (aimet_common.defs.compressionscheme attribute)": [[30, "aimet_common.defs.CompressionScheme.spatial_svd"]], "weight_svd (aimet_common.defs.compressionscheme attribute)": [[30, "aimet_common.defs.CompressionScheme.weight_svd"]], "equalize_model() (in module aimet_tensorflow.keras.cross_layer_equalization)": [[31, "aimet_tensorflow.keras.cross_layer_equalization.equalize_model"]], "layeroutpututil (class in aimet_tensorflow.keras.layer_output_utils)": [[32, "aimet_tensorflow.keras.layer_output_utils.LayerOutputUtil"]], "generate_layer_outputs() (aimet_tensorflow.keras.layer_output_utils.layeroutpututil method)": [[32, "aimet_tensorflow.keras.layer_output_utils.LayerOutputUtil.generate_layer_outputs"]], "callbackfunc (class in aimet_common.defs)": [[33, "aimet_common.defs.CallbackFunc"], [45, "aimet_common.defs.CallbackFunc"], [59, "aimet_common.defs.CallbackFunc"]], "choose_fast_mixed_precision() (in module aimet_tensorflow.keras.mixed_precision)": [[33, "aimet_tensorflow.keras.mixed_precision.choose_fast_mixed_precision"]], "choose_mixed_precision() (in module aimet_tensorflow.keras.mixed_precision)": [[33, "aimet_tensorflow.keras.mixed_precision.choose_mixed_precision"]], "prepare_model() (in module aimet_tensorflow.keras.model_preparer)": [[35, "aimet_tensorflow.keras.model_preparer.prepare_model"]], "clssetinfo (class in aimet_tensorflow.keras.cross_layer_equalization)": [[36, "aimet_tensorflow.keras.cross_layer_equalization.ClsSetInfo"]], "clssetinfo.clssetlayerpairinfo (class in aimet_tensorflow.keras.cross_layer_equalization)": [[36, "aimet_tensorflow.keras.cross_layer_equalization.ClsSetInfo.ClsSetLayerPairInfo"]], "bias_fold() (in module aimet_tensorflow.keras.cross_layer_equalization.highbiasfold)": [[36, "aimet_tensorflow.keras.cross_layer_equalization.HighBiasFold.bias_fold"], [36, "id0"]], "fold_all_batch_norms() (in module aimet_tensorflow.keras.batch_norm_fold)": [[36, "aimet_tensorflow.keras.batch_norm_fold.fold_all_batch_norms"]], "fold_given_batch_norms() (in module aimet_tensorflow.keras.batch_norm_fold)": [[36, "aimet_tensorflow.keras.batch_norm_fold.fold_given_batch_norms"]], "scale_cls_sets() (in module aimet_tensorflow.keras.cross_layer_equalization.crosslayerscaling)": [[36, "aimet_tensorflow.keras.cross_layer_equalization.CrossLayerScaling.scale_cls_sets"]], "scale_model() (in module aimet_tensorflow.keras.cross_layer_equalization.crosslayerscaling)": [[36, "aimet_tensorflow.keras.cross_layer_equalization.CrossLayerScaling.scale_model"]], "quantanalyzer (class in aimet_tensorflow.keras.quant_analyzer)": [[37, "aimet_tensorflow.keras.quant_analyzer.QuantAnalyzer"]], "analyze() (aimet_tensorflow.keras.quant_analyzer.quantanalyzer method)": [[37, "aimet_tensorflow.keras.quant_analyzer.QuantAnalyzer.analyze"]], "quantizationsimmodel (class in aimet_tensorflow.keras.quantsim)": [[39, "aimet_tensorflow.keras.quantsim.QuantizationSimModel"]], "compute_encodings() (aimet_tensorflow.keras.quantsim.quantizationsimmodel method)": [[39, "aimet_tensorflow.keras.quantsim.QuantizationSimModel.compute_encodings"]], "export() (aimet_tensorflow.keras.quantsim.quantizationsimmodel method)": [[39, "aimet_tensorflow.keras.quantsim.QuantizationSimModel.export"]], "adaroundparameters (class in aimet_onnx.adaround.adaround_weight)": [[41, "aimet_onnx.adaround.adaround_weight.AdaroundParameters"]], "apply_adaround() (in module aimet_onnx.adaround.adaround_weight.adaround)": [[41, "aimet_onnx.adaround.adaround_weight.Adaround.apply_adaround"]], "autoquant (class in aimet_onnx.auto_quant_v2)": [[42, "aimet_onnx.auto_quant_v2.AutoQuant"]], "get_quant_scheme_candidates() (aimet_onnx.auto_quant_v2.autoquant method)": [[42, "aimet_onnx.auto_quant_v2.AutoQuant.get_quant_scheme_candidates"]], "optimize() (aimet_onnx.auto_quant_v2.autoquant method)": [[42, "aimet_onnx.auto_quant_v2.AutoQuant.optimize"]], "run_inference() (aimet_onnx.auto_quant_v2.autoquant method)": [[42, "aimet_onnx.auto_quant_v2.AutoQuant.run_inference"]], "set_adaround_params() (aimet_onnx.auto_quant_v2.autoquant method)": [[42, "aimet_onnx.auto_quant_v2.AutoQuant.set_adaround_params"]], "set_quant_scheme_candidates() (aimet_onnx.auto_quant_v2.autoquant method)": [[42, "aimet_onnx.auto_quant_v2.AutoQuant.set_quant_scheme_candidates"]], "equalize_model() (in module aimet_onnx.cross_layer_equalization)": [[43, "aimet_onnx.cross_layer_equalization.equalize_model"]], "layeroutpututil (class in aimet_onnx.layer_output_utils)": [[44, "aimet_onnx.layer_output_utils.LayerOutputUtil"]], "generate_layer_outputs() (aimet_onnx.layer_output_utils.layeroutpututil method)": [[44, "aimet_onnx.layer_output_utils.LayerOutputUtil.generate_layer_outputs"]], "evalcallbackfactory (class in aimet_onnx.amp.mixed_precision_algo)": [[45, "aimet_onnx.amp.mixed_precision_algo.EvalCallbackFactory"]], "quantizergroup (class in aimet_onnx.amp.quantizer_groups)": [[45, "aimet_onnx.amp.quantizer_groups.QuantizerGroup"]], "choose_mixed_precision() (in module aimet_onnx.mixed_precision)": [[45, "aimet_onnx.mixed_precision.choose_mixed_precision"]], "get_activation_quantizers() (aimet_onnx.amp.quantizer_groups.quantizergroup method)": [[45, "aimet_onnx.amp.quantizer_groups.QuantizerGroup.get_activation_quantizers"]], "get_active_quantizers() (aimet_onnx.amp.quantizer_groups.quantizergroup method)": [[45, "aimet_onnx.amp.quantizer_groups.QuantizerGroup.get_active_quantizers"]], "get_candidate() (aimet_onnx.amp.quantizer_groups.quantizergroup method)": [[45, "aimet_onnx.amp.quantizer_groups.QuantizerGroup.get_candidate"]], "get_param_quantizers() (aimet_onnx.amp.quantizer_groups.quantizergroup method)": [[45, "aimet_onnx.amp.quantizer_groups.QuantizerGroup.get_param_quantizers"]], "set_quantizers_to_candidate() (aimet_onnx.amp.quantizer_groups.quantizergroup method)": [[45, "aimet_onnx.amp.quantizer_groups.QuantizerGroup.set_quantizers_to_candidate"]], "sqnr() (aimet_onnx.amp.mixed_precision_algo.evalcallbackfactory method)": [[45, "aimet_onnx.amp.mixed_precision_algo.EvalCallbackFactory.sqnr"]], "to_list() (aimet_onnx.amp.quantizer_groups.quantizergroup method)": [[45, "aimet_onnx.amp.quantizer_groups.QuantizerGroup.to_list"]], "quantanalyzer (class in aimet_onnx.quant_analyzer)": [[46, "aimet_onnx.quant_analyzer.QuantAnalyzer"]], "analyze() (aimet_onnx.quant_analyzer.quantanalyzer method)": [[46, "aimet_onnx.quant_analyzer.QuantAnalyzer.analyze"]], "check_model_sensitivity_to_quantization() (aimet_onnx.quant_analyzer.quantanalyzer method)": [[46, "aimet_onnx.quant_analyzer.QuantAnalyzer.check_model_sensitivity_to_quantization"]], "create_quantsim_and_encodings() (aimet_onnx.quant_analyzer.quantanalyzer method)": [[46, "aimet_onnx.quant_analyzer.QuantAnalyzer.create_quantsim_and_encodings"]], "enable_per_layer_mse_loss() (aimet_onnx.quant_analyzer.quantanalyzer method)": [[46, "aimet_onnx.quant_analyzer.QuantAnalyzer.enable_per_layer_mse_loss"]], "export_per_layer_encoding_min_max_range() (aimet_onnx.quant_analyzer.quantanalyzer method)": [[46, "aimet_onnx.quant_analyzer.QuantAnalyzer.export_per_layer_encoding_min_max_range"]], "export_per_layer_mse_loss() (aimet_onnx.quant_analyzer.quantanalyzer method)": [[46, "aimet_onnx.quant_analyzer.QuantAnalyzer.export_per_layer_mse_loss"]], "export_per_layer_stats_histogram() (aimet_onnx.quant_analyzer.quantanalyzer method)": [[46, "aimet_onnx.quant_analyzer.QuantAnalyzer.export_per_layer_stats_histogram"]], "perform_per_layer_analysis_by_disabling_quantizers() (aimet_onnx.quant_analyzer.quantanalyzer method)": [[46, "aimet_onnx.quant_analyzer.QuantAnalyzer.perform_per_layer_analysis_by_disabling_quantizers"]], "perform_per_layer_analysis_by_enabling_quantizers() (aimet_onnx.quant_analyzer.quantanalyzer method)": [[46, "aimet_onnx.quant_analyzer.QuantAnalyzer.perform_per_layer_analysis_by_enabling_quantizers"]], "quantizationsimmodel (class in aimet_onnx.quantsim)": [[48, "aimet_onnx.quantsim.QuantizationSimModel"]], "compute_encodings() (aimet_onnx.quantsim.quantizationsimmodel method)": [[48, "aimet_onnx.quantsim.QuantizationSimModel.compute_encodings"]], "export() (aimet_onnx.quantsim.quantizationsimmodel method)": [[48, "aimet_onnx.quantsim.QuantizationSimModel.export"]], "adaroundparameters (class in aimet_torch.v1.adaround.adaround_weight)": [[51, "aimet_torch.v1.adaround.adaround_weight.AdaroundParameters"]], "apply_adaround() (in module aimet_torch.v1.adaround.adaround_weight.adaround)": [[51, "aimet_torch.v1.adaround.adaround_weight.Adaround.apply_adaround"]], "check_model_arch() (in module aimet_torch.arch_checker.arch_checker.archchecker)": [[52, "aimet_torch.arch_checker.arch_checker.ArchChecker.check_model_arch"]], "autoquant (class in aimet_torch.v1.auto_quant)": [[53, "aimet_torch.v1.auto_quant.AutoQuant"]], "fold_all_batch_norms_to_scale() (in module aimet_torch.batch_norm_fold)": [[54, "aimet_torch.batch_norm_fold.fold_all_batch_norms_to_scale"]], "reestimate_bn_stats() (in module aimet_torch.bn_reestimation)": [[54, "aimet_torch.bn_reestimation.reestimate_bn_stats"]], "activationtype (class in aimet_common.defs)": [[55, "aimet_common.defs.ActivationType"]], "convbninfotype (class in aimet_common.bias_correction)": [[55, "aimet_common.bias_correction.ConvBnInfoType"]], "quantparams (class in aimet_torch.v1.quantsim)": [[55, "aimet_torch.v1.quantsim.QuantParams"]], "correct_bias() (in module aimet_torch.bias_correction)": [[55, "aimet_torch.bias_correction.correct_bias"]], "no_activation (aimet_common.defs.activationtype attribute)": [[55, "aimet_common.defs.ActivationType.no_activation"]], "relu (aimet_common.defs.activationtype attribute)": [[55, "aimet_common.defs.ActivationType.relu"]], "relu6 (aimet_common.defs.activationtype attribute)": [[55, "aimet_common.defs.ActivationType.relu6"]], "channelpruningparameters (class in aimet_torch.defs)": [[56, "aimet_torch.defs.ChannelPruningParameters"]], "channelpruningparameters.automodeparams (class in aimet_torch.defs)": [[56, "aimet_torch.defs.ChannelPruningParameters.AutoModeParams"]], "channelpruningparameters.manualmodeparams (class in aimet_torch.defs)": [[56, "aimet_torch.defs.ChannelPruningParameters.ManualModeParams"]], "channelpruningparameters.mode (class in aimet_torch.defs)": [[56, "aimet_torch.defs.ChannelPruningParameters.Mode"]], "greedyselectionparameters (class in aimet_common.defs)": [[56, "aimet_common.defs.GreedySelectionParameters"]], "modelcompressor (class in aimet_torch.compress)": [[56, "aimet_torch.compress.ModelCompressor"]], "modulecompratiopair (class in aimet_torch.defs)": [[56, "aimet_torch.defs.ModuleCompRatioPair"]], "spatialsvdparameters (class in aimet_torch.defs)": [[56, "aimet_torch.defs.SpatialSvdParameters"]], "spatialsvdparameters.automodeparams (class in aimet_torch.defs)": [[56, "aimet_torch.defs.SpatialSvdParameters.AutoModeParams"]], "spatialsvdparameters.manualmodeparams (class in aimet_torch.defs)": [[56, "aimet_torch.defs.SpatialSvdParameters.ManualModeParams"]], "spatialsvdparameters.mode (class in aimet_torch.defs)": [[56, "aimet_torch.defs.SpatialSvdParameters.Mode"]], "weightsvdparameters (class in aimet_torch.defs)": [[56, "aimet_torch.defs.WeightSvdParameters"]], "weightsvdparameters.automodeparams (class in aimet_torch.defs)": [[56, "aimet_torch.defs.WeightSvdParameters.AutoModeParams"]], "weightsvdparameters.manualmodeparams (class in aimet_torch.defs)": [[56, "aimet_torch.defs.WeightSvdParameters.ManualModeParams"]], "weightsvdparameters.mode (class in aimet_torch.defs)": [[56, "aimet_torch.defs.WeightSvdParameters.Mode"]], "auto (aimet_torch.defs.channelpruningparameters.mode attribute)": [[56, "aimet_torch.defs.ChannelPruningParameters.Mode.auto"]], "auto (aimet_torch.defs.spatialsvdparameters.mode attribute)": [[56, "aimet_torch.defs.SpatialSvdParameters.Mode.auto"]], "auto (aimet_torch.defs.weightsvdparameters.mode attribute)": [[56, "aimet_torch.defs.WeightSvdParameters.Mode.auto"]], "compress_model() (aimet_torch.compress.modelcompressor static method)": [[56, "aimet_torch.compress.ModelCompressor.compress_model"]], "manual (aimet_torch.defs.channelpruningparameters.mode attribute)": [[56, "aimet_torch.defs.ChannelPruningParameters.Mode.manual"]], "manual (aimet_torch.defs.spatialsvdparameters.mode attribute)": [[56, "aimet_torch.defs.SpatialSvdParameters.Mode.manual"]], "manual (aimet_torch.defs.weightsvdparameters.mode attribute)": [[56, "aimet_torch.defs.WeightSvdParameters.Mode.manual"]], "equalize_model() (in module aimet_torch.cross_layer_equalization)": [[57, "aimet_torch.cross_layer_equalization.equalize_model"]], "layeroutpututil (class in aimet_torch.layer_output_utils)": [[58, "aimet_torch.layer_output_utils.LayerOutputUtil"]], "namingscheme (class in aimet_torch.layer_output_utils)": [[58, "aimet_torch.layer_output_utils.NamingScheme"]], "onnx (aimet_torch.layer_output_utils.namingscheme attribute)": [[58, "aimet_torch.layer_output_utils.NamingScheme.ONNX"]], "pytorch (aimet_torch.layer_output_utils.namingscheme attribute)": [[58, "aimet_torch.layer_output_utils.NamingScheme.PYTORCH"]], "torchscript (aimet_torch.layer_output_utils.namingscheme attribute)": [[58, "aimet_torch.layer_output_utils.NamingScheme.TORCHSCRIPT"]], "generate_layer_outputs() (aimet_torch.layer_output_utils.layeroutpututil method)": [[58, "aimet_torch.layer_output_utils.LayerOutputUtil.generate_layer_outputs"]], "evalcallbackfactory (class in aimet_torch.amp.mixed_precision_algo)": [[59, "aimet_torch.amp.mixed_precision_algo.EvalCallbackFactory"]], "quantizergroup (class in aimet_torch.amp.quantizer_groups)": [[59, "aimet_torch.amp.quantizer_groups.QuantizerGroup"]], "choose_mixed_precision() (in module aimet_torch.mixed_precision)": [[59, "aimet_torch.mixed_precision.choose_mixed_precision"]], "get_active_quantizers() (aimet_torch.amp.quantizer_groups.quantizergroup method)": [[59, "aimet_torch.amp.quantizer_groups.QuantizerGroup.get_active_quantizers"]], "get_candidate() (aimet_torch.amp.quantizer_groups.quantizergroup method)": [[59, "aimet_torch.amp.quantizer_groups.QuantizerGroup.get_candidate"]], "get_input_quantizer_modules() (aimet_torch.amp.quantizer_groups.quantizergroup method)": [[59, "aimet_torch.amp.quantizer_groups.QuantizerGroup.get_input_quantizer_modules"]], "set_quantizers_to_candidate() (aimet_torch.amp.quantizer_groups.quantizergroup method)": [[59, "aimet_torch.amp.quantizer_groups.QuantizerGroup.set_quantizers_to_candidate"]], "sqnr() (aimet_torch.amp.mixed_precision_algo.evalcallbackfactory method)": [[59, "aimet_torch.amp.mixed_precision_algo.EvalCallbackFactory.sqnr"]], "to_list() (aimet_torch.amp.quantizer_groups.quantizergroup method)": [[59, "aimet_torch.amp.quantizer_groups.QuantizerGroup.to_list"]], "prepare_model() (in module aimet_torch.model_preparer)": [[61, "aimet_torch.model_preparer.prepare_model"]], "adaptermetadata (class in aimet_torch.peft)": [[64, "aimet_torch.peft.AdapterMetaData"]], "peftquantutils (class in aimet_torch.peft)": [[64, "aimet_torch.peft.PeftQuantUtils"]], "disable_lora_adapters() (aimet_torch.peft.peftquantutils method)": [[64, "aimet_torch.peft.PeftQuantUtils.disable_lora_adapters"]], "enable_adapter_and_load_weights() (aimet_torch.peft.peftquantutils method)": [[64, "aimet_torch.peft.PeftQuantUtils.enable_adapter_and_load_weights"]], "export_adapter_weights() (aimet_torch.peft.peftquantutils method)": [[64, "aimet_torch.peft.PeftQuantUtils.export_adapter_weights"]], "freeze_base_model() (aimet_torch.peft.peftquantutils method)": [[64, "aimet_torch.peft.PeftQuantUtils.freeze_base_model"]], "freeze_base_model_activation_quantizers() (aimet_torch.peft.peftquantutils method)": [[64, "aimet_torch.peft.PeftQuantUtils.freeze_base_model_activation_quantizers"]], "freeze_base_model_param_quantizers() (aimet_torch.peft.peftquantutils method)": [[64, "aimet_torch.peft.PeftQuantUtils.freeze_base_model_param_quantizers"]], "get_fp_lora_layer() (aimet_torch.peft.peftquantutils method)": [[64, "aimet_torch.peft.PeftQuantUtils.get_fp_lora_layer"]], "get_quantized_lora_layer() (aimet_torch.peft.peftquantutils method)": [[64, "aimet_torch.peft.PeftQuantUtils.get_quantized_lora_layer"]], "quantize_lora_scale_with_fixed_range() (aimet_torch.peft.peftquantutils method)": [[64, "aimet_torch.peft.PeftQuantUtils.quantize_lora_scale_with_fixed_range"]], "replace_lora_layers_with_quantizable_layers() (aimet_torch.peft method)": [[64, "aimet_torch.peft.replace_lora_layers_with_quantizable_layers"]], "set_bitwidth_for_lora_adapters() (aimet_torch.peft.peftquantutils method)": [[64, "aimet_torch.peft.PeftQuantUtils.set_bitwidth_for_lora_adapters"]], "track_lora_meta_data() (aimet_torch.peft method)": [[64, "aimet_torch.peft.track_lora_meta_data"]], "clssetinfo (class in aimet_torch.cross_layer_equalization)": [[65, "aimet_torch.cross_layer_equalization.ClsSetInfo"]], "clssetinfo.clssetlayerpairinfo (class in aimet_torch.cross_layer_equalization)": [[65, "aimet_torch.cross_layer_equalization.ClsSetInfo.ClsSetLayerPairInfo"]], "bias_fold() (in module aimet_torch.cross_layer_equalization.highbiasfold)": [[65, "aimet_torch.cross_layer_equalization.HighBiasFold.bias_fold"], [65, "id0"]], "fold_all_batch_norms() (in module aimet_torch.batch_norm_fold)": [[65, "aimet_torch.batch_norm_fold.fold_all_batch_norms"]], "fold_given_batch_norms() (in module aimet_torch.batch_norm_fold)": [[65, "aimet_torch.batch_norm_fold.fold_given_batch_norms"]], "scale_cls_sets() (in module aimet_torch.cross_layer_equalization.crosslayerscaling)": [[65, "aimet_torch.cross_layer_equalization.CrossLayerScaling.scale_cls_sets"]], "scale_model() (in module aimet_torch.cross_layer_equalization.crosslayerscaling)": [[65, "aimet_torch.cross_layer_equalization.CrossLayerScaling.scale_model"]], "callbackfunc (class in aimet_common.utils)": [[66, "aimet_common.utils.CallbackFunc"]], "quantanalyzer (class in aimet_torch.v1.quant_analyzer)": [[66, "aimet_torch.v1.quant_analyzer.QuantAnalyzer"]], "analyze() (aimet_torch.v1.quant_analyzer.quantanalyzer method)": [[66, "aimet_torch.v1.quant_analyzer.QuantAnalyzer.analyze"]], "check_model_sensitivity_to_quantization() (aimet_torch.v1.quant_analyzer.quantanalyzer method)": [[66, "aimet_torch.v1.quant_analyzer.QuantAnalyzer.check_model_sensitivity_to_quantization"]], "enable_per_layer_mse_loss() (aimet_torch.v1.quant_analyzer.quantanalyzer method)": [[66, "aimet_torch.v1.quant_analyzer.QuantAnalyzer.enable_per_layer_mse_loss"]], "export_per_layer_encoding_min_max_range() (aimet_torch.v1.quant_analyzer.quantanalyzer method)": [[66, "aimet_torch.v1.quant_analyzer.QuantAnalyzer.export_per_layer_encoding_min_max_range"]], "export_per_layer_mse_loss() (aimet_torch.v1.quant_analyzer.quantanalyzer method)": [[66, "aimet_torch.v1.quant_analyzer.QuantAnalyzer.export_per_layer_mse_loss"]], "export_per_layer_stats_histogram() (aimet_torch.v1.quant_analyzer.quantanalyzer method)": [[66, "aimet_torch.v1.quant_analyzer.QuantAnalyzer.export_per_layer_stats_histogram"]], "perform_per_layer_analysis_by_disabling_quant_wrappers() (aimet_torch.v1.quant_analyzer.quantanalyzer method)": [[66, "aimet_torch.v1.quant_analyzer.QuantAnalyzer.perform_per_layer_analysis_by_disabling_quant_wrappers"]], "perform_per_layer_analysis_by_enabling_quant_wrappers() (aimet_torch.v1.quant_analyzer.quantanalyzer method)": [[66, "aimet_torch.v1.quant_analyzer.QuantAnalyzer.perform_per_layer_analysis_by_enabling_quant_wrappers"]], "quantizationsimmodel (class in aimet_torch.v1.quantsim)": [[68, "aimet_torch.v1.quantsim.QuantizationSimModel"]], "compute_encodings() (aimet_torch.v1.quantsim.quantizationsimmodel method)": [[68, "aimet_torch.v1.quantsim.QuantizationSimModel.compute_encodings"]], "export() (aimet_torch.v1.quantsim.quantizationsimmodel method)": [[68, "aimet_torch.v1.quantsim.QuantizationSimModel.export"]], "load_checkpoint() (aimet_torch.v1.quantsim method)": [[68, "aimet_torch.v1.quantsim.load_checkpoint"]], "save_checkpoint() (aimet_torch.v1.quantsim method)": [[68, "aimet_torch.v1.quantsim.save_checkpoint"]], "scatterdense (class in aimet_torch.nn.modules.custom)": [[69, "aimet_torch.nn.modules.custom.ScatterDense"]], "sparsetensorwrapper (class in aimet_torch.nn.modules.custom)": [[69, "aimet_torch.nn.modules.custom.SparseTensorWrapper"]], "visualizecompression (class in aimet_torch.visualize_serialized_data)": [[70, "aimet_torch.visualize_serialized_data.VisualizeCompression"]], "display_comp_ratio_plot() (aimet_torch.visualize_serialized_data.visualizecompression method)": [[70, "aimet_torch.visualize_serialized_data.VisualizeCompression.display_comp_ratio_plot"]], "display_eval_scores() (aimet_torch.visualize_serialized_data.visualizecompression method)": [[70, "aimet_torch.visualize_serialized_data.VisualizeCompression.display_eval_scores"]], "visualize_changes_after_optimization() (in module aimet_torch.visualize_model)": [[71, "aimet_torch.visualize_model.visualize_changes_after_optimization"]], "visualize_relative_weight_ranges_to_identify_problematic_layers() (in module aimet_torch.visualize_model)": [[71, "aimet_torch.visualize_model.visualize_relative_weight_ranges_to_identify_problematic_layers"]], "visualize_weight_ranges() (in module aimet_torch.visualize_model)": [[71, "aimet_torch.visualize_model.visualize_weight_ranges"]], "quantizationmixin (class in aimet_torch.v2.nn)": [[77, "aimet_torch.v2.nn.QuantizationMixin"], [88, "aimet_torch.v2.nn.QuantizationMixin"]], "__quant_init__() (aimet_torch.v2.nn.quantizationmixin method)": [[77, "aimet_torch.v2.nn.QuantizationMixin.__quant_init__"], [88, "aimet_torch.v2.nn.QuantizationMixin.__quant_init__"]], "compute_encodings() (aimet_torch.v2.nn.quantizationmixin method)": [[77, "aimet_torch.v2.nn.QuantizationMixin.compute_encodings"], [88, "aimet_torch.v2.nn.QuantizationMixin.compute_encodings"]], "forward() (aimet_torch.v2.nn.quantizationmixin method)": [[77, "aimet_torch.v2.nn.QuantizationMixin.forward"], [88, "aimet_torch.v2.nn.QuantizationMixin.forward"]], "from_module() (aimet_torch.v2.nn.quantizationmixin class method)": [[77, "aimet_torch.v2.nn.QuantizationMixin.from_module"]], "get_default_kernel() (aimet_torch.v2.nn.quantizationmixin class method)": [[77, "aimet_torch.v2.nn.QuantizationMixin.get_default_kernel"]], "get_kernel() (aimet_torch.v2.nn.quantizationmixin method)": [[77, "aimet_torch.v2.nn.QuantizationMixin.get_kernel"]], "implements() (aimet_torch.v2.nn.quantizationmixin class method)": [[77, "aimet_torch.v2.nn.QuantizationMixin.implements"]], "input_quantizers (aimet_torch.v2.nn.quantizationmixin attribute)": [[77, "aimet_torch.v2.nn.QuantizationMixin.input_quantizers"], [88, "aimet_torch.v2.nn.QuantizationMixin.input_quantizers"]], "output_quantizers (aimet_torch.v2.nn.quantizationmixin attribute)": [[77, "aimet_torch.v2.nn.QuantizationMixin.output_quantizers"], [88, "aimet_torch.v2.nn.QuantizationMixin.output_quantizers"]], "param_quantizers (aimet_torch.v2.nn.quantizationmixin attribute)": [[77, "aimet_torch.v2.nn.QuantizationMixin.param_quantizers"], [88, "aimet_torch.v2.nn.QuantizationMixin.param_quantizers"]], "set_default_kernel() (aimet_torch.v2.nn.quantizationmixin class method)": [[77, "aimet_torch.v2.nn.QuantizationMixin.set_default_kernel"]], "set_kernel() (aimet_torch.v2.nn.quantizationmixin method)": [[77, "aimet_torch.v2.nn.QuantizationMixin.set_kernel"]], "quantize (class in aimet_torch.v2.quantization.affine)": [[78, "aimet_torch.v2.quantization.affine.Quantize"]], "quantizedequantize (class in aimet_torch.v2.quantization.affine)": [[78, "aimet_torch.v2.quantization.affine.QuantizeDequantize"]], "aimet_torch.v2.quantization.affine": [[78, "module-aimet_torch.v2.quantization.affine"]], "dequantize() (in module aimet_torch.v2.quantization.affine)": [[78, "aimet_torch.v2.quantization.affine.dequantize"]], "module": [[78, "module-aimet_torch.v2.quantization.affine"], [80, "module-aimet_torch.v2.quantization.float"]], "quantize() (in module aimet_torch.v2.quantization.affine)": [[78, "aimet_torch.v2.quantization.affine.quantize"]], "quantize_dequantize() (in module aimet_torch.v2.quantization.affine)": [[78, "aimet_torch.v2.quantization.affine.quantize_dequantize"]], "floatquantizedequantize (class in aimet_torch.v2.quantization.float)": [[79, "aimet_torch.v2.quantization.float.FloatQuantizeDequantize"], [80, "aimet_torch.v2.quantization.float.FloatQuantizeDequantize"]], "quantizedequantize (class in aimet_torch.v2.quantization.float)": [[79, "aimet_torch.v2.quantization.float.QuantizeDequantize"], [80, "aimet_torch.v2.quantization.float.QuantizeDequantize"]], "aimet_torch.v2.quantization.float": [[80, "module-aimet_torch.v2.quantization.float"]], "dequantizedtensor (class in aimet_torch.v2.quantization.tensor)": [[81, "aimet_torch.v2.quantization.tensor.DequantizedTensor"]], "quantizedtensor (class in aimet_torch.v2.quantization.tensor)": [[81, "aimet_torch.v2.quantization.tensor.QuantizedTensor"]], "dequantize() (aimet_torch.v2.quantization.tensor.dequantizedtensor method)": [[81, "aimet_torch.v2.quantization.tensor.DequantizedTensor.dequantize"]], "dequantize() (aimet_torch.v2.quantization.tensor.quantizedtensor method)": [[81, "aimet_torch.v2.quantization.tensor.QuantizedTensor.dequantize"]], "quantize() (aimet_torch.v2.quantization.tensor.dequantizedtensor method)": [[81, "aimet_torch.v2.quantization.tensor.DequantizedTensor.quantize"]], "quantize() (aimet_torch.v2.quantization.tensor.quantizedtensor method)": [[81, "aimet_torch.v2.quantization.tensor.QuantizedTensor.quantize"]], "quantized_repr() (aimet_torch.v2.quantization.tensor.dequantizedtensor method)": [[81, "aimet_torch.v2.quantization.tensor.DequantizedTensor.quantized_repr"]], "quantized_repr() (aimet_torch.v2.quantization.tensor.quantizedtensor method)": [[81, "aimet_torch.v2.quantization.tensor.QuantizedTensor.quantized_repr"]], "visualize_stats() (in module aimet_torch.v2.visualization_tools)": [[82, "aimet_torch.v2.visualization_tools.visualize_stats"]], "set_activation_quantizers_to_float() (in module aimet_torch.v2.quantsim.config_utils)": [[83, "aimet_torch.v2.quantsim.config_utils.set_activation_quantizers_to_float"]], "set_blockwise_quantization_for_weights() (in module aimet_torch.v2.quantsim.config_utils)": [[83, "aimet_torch.v2.quantsim.config_utils.set_blockwise_quantization_for_weights"]], "set_grouped_blockwise_quantization_for_weights() (in module aimet_torch.v2.quantsim.config_utils)": [[83, "aimet_torch.v2.quantsim.config_utils.set_grouped_blockwise_quantization_for_weights"]], "encodinganalyzer (class in aimet_torch.v2.quantization.encoding_analyzer)": [[84, "aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer"]], "minmaxencodinganalyzer (class in aimet_torch.v2.quantization.encoding_analyzer)": [[84, "aimet_torch.v2.quantization.encoding_analyzer.MinMaxEncodingAnalyzer"]], "percentileencodinganalyzer (class in aimet_torch.v2.quantization.encoding_analyzer)": [[84, "aimet_torch.v2.quantization.encoding_analyzer.PercentileEncodingAnalyzer"]], "sqnrencodinganalyzer (class in aimet_torch.v2.quantization.encoding_analyzer)": [[84, "aimet_torch.v2.quantization.encoding_analyzer.SqnrEncodingAnalyzer"]], "compute_encodings() (aimet_torch.v2.quantization.encoding_analyzer.encodinganalyzer method)": [[84, "aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.compute_encodings"]], "reset_stats() (aimet_torch.v2.quantization.encoding_analyzer.encodinganalyzer method)": [[84, "aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.reset_stats"]], "update_stats() (aimet_torch.v2.quantization.encoding_analyzer.encodinganalyzer method)": [[84, "aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.update_stats"]], "gptvqparameters (class in aimet_torch.gptvq.defs)": [[86, "aimet_torch.gptvq.defs.GPTVQParameters"]], "apply_gptvq() (in module aimet_torch.gptvq.gptvq_weight.gptvq)": [[86, "aimet_torch.gptvq.gptvq_weight.GPTVQ.apply_gptvq"]], "quantize (class in aimet_torch.v2.quantization.affine.quantizer)": [[89, "aimet_torch.v2.quantization.affine.quantizer.Quantize"]], "quantizedequantize (class in aimet_torch.v2.quantization.affine.quantizer)": [[89, "aimet_torch.v2.quantization.affine.quantizer.QuantizeDequantize"]], "quantizerbase (class in aimet_torch.v2.quantization.affine.quantizer)": [[89, "aimet_torch.v2.quantization.affine.quantizer.QuantizerBase"]], "allow_overwrite() (aimet_torch.v2.quantization.affine.quantizer.quantizerbase method)": [[89, "aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.allow_overwrite"]], "compute_encodings() (aimet_torch.v2.quantization.affine.quantizer.quantizerbase method)": [[89, "aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.compute_encodings"]], "forward() (aimet_torch.v2.quantization.affine.quantizer.quantize method)": [[89, "aimet_torch.v2.quantization.affine.quantizer.Quantize.forward"]], "forward() (aimet_torch.v2.quantization.affine.quantizer.quantizedequantize method)": [[89, "aimet_torch.v2.quantization.affine.quantizer.QuantizeDequantize.forward"]], "get_encoding() (aimet_torch.v2.quantization.affine.quantizer.quantizerbase method)": [[89, "aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.get_encoding"]], "get_legacy_encodings() (aimet_torch.v2.quantization.affine.quantizer.quantizerbase method)": [[89, "aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.get_legacy_encodings"]], "is_initialized() (aimet_torch.v2.quantization.affine.quantizer.quantizerbase method)": [[89, "aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.is_initialized"]], "register_quantization_parameter() (aimet_torch.v2.quantization.affine.quantizer.quantizerbase method)": [[89, "aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.register_quantization_parameter"]], "set_legacy_encodings() (aimet_torch.v2.quantization.affine.quantizer.quantizerbase method)": [[89, "aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.set_legacy_encodings"]]}})
\ No newline at end of file
diff --git a/releases/1.35.1/torch_v2/install/index.html b/releases/1.35.1/torch_v2/install/index.html
index 9a8c439..4074712 100644
--- a/releases/1.35.1/torch_v2/install/index.html
+++ b/releases/1.35.1/torch_v2/install/index.html
@@ -134,25 +134,25 @@ <h2>Release Packages<a class="headerlink" href="#release-packages" title="Permal
 </div>
 <p><strong>PyTorch</strong></p>
 <pre class="literal-block"># Pytorch 2.1 with CUDA 12.x
-python3 -m pip install https://github.com/quic/aimet/releases/download/1.35.1/aimet_torch-1.35.1.cu121-cp310-cp310-manylinux_2_34_x86_64.whl -f https://download.pytorch.org/whl/torch_stable.html
+python3 -m pip install https://github.com/quic/aimet/releases/download/1.35.1/aimet_torch-1.35.1+cu121-cp310-cp310-manylinux_2_34_x86_64.whl -f https://download.pytorch.org/whl/torch_stable.html
 
 # Pytorch 2.1 CPU only
-python3 -m pip install https://github.com/quic/aimet/releases/download/1.35.1/aimet_torch-1.35.1.cpu-cp310-cp310-manylinux_2_34_x86_64.whl -f https://download.pytorch.org/whl/torch_stable.html
+python3 -m pip install https://github.com/quic/aimet/releases/download/1.35.1/aimet_torch-1.35.1+cpu-cp310-cp310-manylinux_2_34_x86_64.whl -f https://download.pytorch.org/whl/torch_stable.html
 
 # Pytorch 1.13 with CUDA 11.x
-python3 -m pip install https://github.com/quic/aimet/releases/download/1.35.1/aimet_torch-1.35.1.cu117-cp310-cp310-manylinux_2_34_x86_64.whl -f https://download.pytorch.org/whl/torch_stable.html</pre>
+python3 -m pip install https://github.com/quic/aimet/releases/download/1.35.1/aimet_torch-1.35.1+cu117-cp310-cp310-manylinux_2_34_x86_64.whl -f https://download.pytorch.org/whl/torch_stable.html</pre>
 <p><strong>TensorFlow</strong></p>
 <pre class="literal-block"># Tensorflow 2.10 GPU with CUDA 11.x
-python3 -m pip install https://github.com/quic/aimet/releases/download/1.35.1/aimet_tensorflow-1.35.1.cu118-cp310-cp310-manylinux_2_34_x86_64.whl
+python3 -m pip install https://github.com/quic/aimet/releases/download/1.35.1/aimet_tensorflow-1.35.1+cu118-cp310-cp310-manylinux_2_34_x86_64.whl
 
 # Tensorflow 2.10 CPU only
-python3 -m pip install https://github.com/quic/aimet/releases/download/1.35.1/aimet_tensorflow-1.35.1.cpu-cp310-cp310-manylinux_2_34_x86_64.whl</pre>
+python3 -m pip install https://github.com/quic/aimet/releases/download/1.35.1/aimet_tensorflow-1.35.1+cpu-cp310-cp310-manylinux_2_34_x86_64.whl</pre>
 <p><strong>ONNX</strong></p>
 <pre class="literal-block"># ONNX 1.16 GPU with CUDA 11.x
-python3 -m pip install https://github.com/quic/aimet/releases/download/1.35.1/aimet_onnx-1.35.1.cu117-cp310-cp310-manylinux_2_34_x86_64.whl -f https://download.pytorch.org/whl/torch_stable.html
+python3 -m pip install https://github.com/quic/aimet/releases/download/1.35.1/aimet_onnx-1.35.1+cu118-cp310-cp310-manylinux_2_34_x86_64.whl -f https://download.pytorch.org/whl/torch_stable.html
 
 # ONNX 1.16 CPU
-python3 -m pip install https://github.com/quic/aimet/releases/download/1.35.1/aimet_onnx-1.35.1.cpu-cp310-cp310-manylinux_2_34_x86_64.whl -f https://download.pytorch.org/whl/torch_stable.html</pre>
+python3 -m pip install https://github.com/quic/aimet/releases/download/1.35.1/aimet_onnx-1.35.1+cpu-cp310-cp310-manylinux_2_34_x86_64.whl -f https://download.pytorch.org/whl/torch_stable.html</pre>
 <p>For older versions, please browse the releases at <a class="reference external" href="https://github.com/quic/aimet/releases">https://github.com/quic/aimet/releases</a> and follow the documentation corresponding to that release to select and install the appropriate package.</p>
 </section>
 <section id="system-requirements">
diff --git a/releases/1.35.1/torch_v2/install/install_docker.html b/releases/1.35.1/torch_v2/install/install_docker.html
index e7d81f7..e5bc58f 100644
--- a/releases/1.35.1/torch_v2/install/install_docker.html
+++ b/releases/1.35.1/torch_v2/install/install_docker.html
@@ -217,14 +217,14 @@ <h3>From Release Package<a class="headerlink" href="#from-release-package" title
 </dd>
 </dl>
 <p>Set the package details as follows:</p>
-<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span><span class="c1"># Set the release tag ex. &quot;1.34.0&quot;</span>
+<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span><span class="c1"># Set the release tag ex. &quot;1.35.1&quot;</span>
 <span class="nb">export</span><span class="w"> </span><span class="nv">release_tag</span><span class="o">=</span><span class="s2">&quot;&lt;version release tag&gt;&quot;</span>
 
 <span class="c1"># Construct the download root URL</span>
 <span class="nb">export</span><span class="w"> </span><span class="nv">download_url</span><span class="o">=</span><span class="s2">&quot;https://github.com/quic/aimet/releases/download/</span><span class="si">${</span><span class="nv">release_tag</span><span class="si">}</span><span class="s2">&quot;</span>
 
 <span class="c1"># Set the wheel file name with extension</span>
-<span class="c1"># ex. &quot;aimet_torch-1.34.0.cu121-cp310-cp310-manylinux_2_34_x86_64.whl&quot;</span>
+<span class="c1"># ex. &quot;aimet_torch-1.35.1+cu121-cp310-cp310-manylinux_2_34_x86_64.whl&quot;</span>
 <span class="nb">export</span><span class="w"> </span><span class="nv">wheel_file_name</span><span class="o">=</span><span class="s2">&quot;&lt;wheel file name&gt;&quot;</span>
 
 <span class="c1"># NOTE: Do the following ONLY for the PyTorch and ONNX variant packages!</span>
diff --git a/releases/1.35.1/torch_v2/install/install_host.html b/releases/1.35.1/torch_v2/install/install_host.html
index 141c1a8..309f66f 100644
--- a/releases/1.35.1/torch_v2/install/install_host.html
+++ b/releases/1.35.1/torch_v2/install/install_host.html
@@ -201,14 +201,14 @@ <h3>From Release Package<a class="headerlink" href="#from-release-package" title
 </dd>
 </dl>
 <p>Set the package details as follows:</p>
-<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span><span class="c1"># Set the release tag ex. &quot;1.34.0&quot;</span>
+<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span><span class="c1"># Set the release tag ex. &quot;1.35.1&quot;</span>
 <span class="nb">export</span><span class="w"> </span><span class="nv">release_tag</span><span class="o">=</span><span class="s2">&quot;&lt;version release tag&gt;&quot;</span>
 
 <span class="c1"># Construct the download root URL</span>
 <span class="nb">export</span><span class="w"> </span><span class="nv">download_url</span><span class="o">=</span><span class="s2">&quot;https://github.com/quic/aimet/releases/download/</span><span class="si">${</span><span class="nv">release_tag</span><span class="si">}</span><span class="s2">&quot;</span>
 
 <span class="c1"># Set the wheel file name with extension</span>
-<span class="c1"># ex. &quot;aimet_torch-1.33.0.cu121-cp310-cp310-manylinux_2_34_x86_64.whl&quot;</span>
+<span class="c1"># ex. &quot;aimet_torch-1.35.1+cu121-cp310-cp310-manylinux_2_34_x86_64.whl&quot;</span>
 <span class="nb">export</span><span class="w"> </span><span class="nv">wheel_file_name</span><span class="o">=</span><span class="s2">&quot;&lt;wheel file name&gt;&quot;</span>
 
 <span class="c1"># NOTE: Do the following ONLY for the PyTorch and ONNX variant packages!</span>
diff --git a/releases/1.35.1/torch_v2/searchindex.js b/releases/1.35.1/torch_v2/searchindex.js
index 5afc858..374addf 100644
--- a/releases/1.35.1/torch_v2/searchindex.js
+++ b/releases/1.35.1/torch_v2/searchindex.js
@@ -1 +1 @@
-Search.setIndex({"docnames": ["_templates/autosummary/class", "_templates/autosummary/function", "install/index", "install/install_docker", "install/install_host", "toplevelhidden", "torch_docs/api/nn.quantization_mixin", "torch_docs/api/quantization/affine/index", "torch_docs/api/quantization/float/FloatQuantizeDequantize", "torch_docs/api/quantization/float/index", "torch_docs/api/quantization/tensor", "torch_docs/api/visualization_tools", "torch_docs/blockwise_quantization", "torch_docs/encoding_analyzer", "torch_docs/examples/ptq", "torch_docs/gptvq", "torch_docs/index", "torch_docs/quantized_modules", "torch_docs/quantizer", "torch_docs/tutorials/quickstart_guide", "user_guide/adaround", "user_guide/auto_quant", "user_guide/bn_reestimation", "user_guide/channel_pruning", "user_guide/compression_feature_guidebook", "user_guide/greedy_compression_ratio_selection", "user_guide/index", "user_guide/known_issues", "user_guide/model_compression", "user_guide/model_guidelines", "user_guide/model_quantization", "user_guide/post_training_quant_techniques", "user_guide/quant_analyzer", "user_guide/quantization_aware_training", "user_guide/quantization_configuration", "user_guide/quantization_feature_guidebook", "user_guide/quantization_sim", "user_guide/release_notes", "user_guide/spatial_svd", "user_guide/visualization_compression", "user_guide/visualization_quant", "user_guide/weight_svd", "user_guide/winnowing"], "filenames": ["_templates/autosummary/class.rst", "_templates/autosummary/function.rst", "install/index.rst", "install/install_docker.rst", "install/install_host.rst", "toplevelhidden.rst", "torch_docs/api/nn.quantization_mixin.rst", "torch_docs/api/quantization/affine/index.rst", "torch_docs/api/quantization/float/FloatQuantizeDequantize.rst", "torch_docs/api/quantization/float/index.rst", "torch_docs/api/quantization/tensor.rst", "torch_docs/api/visualization_tools.rst", "torch_docs/blockwise_quantization.rst", "torch_docs/encoding_analyzer.rst", "torch_docs/examples/ptq.rst", "torch_docs/gptvq.rst", "torch_docs/index.rst", "torch_docs/quantized_modules.rst", "torch_docs/quantizer.rst", "torch_docs/tutorials/quickstart_guide.rst", "user_guide/adaround.rst", "user_guide/auto_quant.rst", "user_guide/bn_reestimation.rst", "user_guide/channel_pruning.rst", "user_guide/compression_feature_guidebook.rst", "user_guide/greedy_compression_ratio_selection.rst", "user_guide/index.rst", "user_guide/known_issues.rst", "user_guide/model_compression.rst", "user_guide/model_guidelines.rst", "user_guide/model_quantization.rst", "user_guide/post_training_quant_techniques.rst", "user_guide/quant_analyzer.rst", "user_guide/quantization_aware_training.rst", "user_guide/quantization_configuration.rst", "user_guide/quantization_feature_guidebook.rst", "user_guide/quantization_sim.rst", "user_guide/release_notes.rst", "user_guide/spatial_svd.rst", "user_guide/visualization_compression.rst", "user_guide/visualization_quant.rst", "user_guide/weight_svd.rst", "user_guide/winnowing.rst"], "titles": ["&lt;no title&gt;", "&lt;no title&gt;", "AIMET Installation", "AIMET Installation in Docker", "AIMET Installation and Setup", "&lt;no title&gt;", "QuantizationMixin", "quantization.affine", "FloatQuantizeDequantize", "quantization.float", "quantization.tensor", "Visualization Tools", "Blockwise Quantization", "Encoding Analyzers", "Post-Training Quantization", "GPTVQ", "AIMET: AI Model Efficiency Toolkit Documentation", "Quantized Modules", "Quantizers", "Quickstart Guide", "AIMET AdaRound", "AIMET AutoQuant", "AIMET Batch Norm Re-estimation", "AIMET channel pruning", "AIMET Compression Features Guidebook", "AIMET greedy compression ratio selection", "AI Model Efficiency Toolkit User Guide", "AIMET Known Issues", "AIMET model compression", "Model Guidelines for PyTorch", "AIMET model quantization", "AIMET post-training quantization techniques", "AIMET QuantAnalyzer", "AIMET quantization aware training", "Quantization simulation configuration", "AIMET quantization diagnostics", "AIMET quantization simulation", "AIMET Release Notes", "AIMET spatial SVD", "AIMET visualization", "AIMET visualization for quantization", "AIMET weight SVD", "AIMET winnowing"], "terms": {"name": [0, 1, 3, 4, 6, 11, 15, 17, 18, 31, 36, 37, 39], "escap": [0, 1], "underlin": [0, 1], "qualcomm": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42], "innov": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42], "center": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42], "inc": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42], "ai": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 17, 18, 19, 20, 21, 22, 23, 24, 25, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42], "model": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 17, 18, 20, 21, 22, 23, 24, 25, 27, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42], "effici": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 17, 18, 19, 20, 21, 22, 23, 24, 25, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42], "toolkit": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 17, 18, 19, 20, 21, 22, 23, 24, 25, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42], "aimet_common": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42], "quantsim_config": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42], "default_config": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42], "json": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42], "1": [0, 1, 2, 3, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 38, 39, 40, 41, 42], "35": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42], "The": [2, 3, 4, 6, 7, 8, 9, 10, 11, 12, 13, 15, 16, 17, 19, 20, 21, 22, 23, 24, 25, 26, 28, 29, 30, 31, 32, 33, 34, 35, 36, 38, 39, 40, 41, 42], "pytorch": [2, 3, 6, 15, 17, 20, 21, 22, 26, 31, 32, 34, 36, 37], "gpu": [2, 3, 30, 37], "pypi": 2, "ar": [2, 3, 4, 6, 7, 8, 9, 12, 13, 15, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 29, 30, 31, 32, 33, 34, 35, 36, 39, 40, 42], "avail": [2, 19, 29, 32, 34, 35], "environ": 2, "meet": [2, 21, 24, 25], "follow": [2, 3, 4, 6, 12, 15, 17, 20, 22, 23, 24, 25, 26, 28, 29, 30, 32, 33, 34, 35, 36, 38, 41, 42], "64": [2, 7, 12, 13, 18, 20], "bit": [2, 8, 9, 12, 19, 20, 22, 30, 35, 36, 37], "intel": 2, "x86": 2, "compat": [2, 12, 19], "processor": 2, "linux": [2, 4], "ubuntu": [2, 4], "22": [2, 4, 13, 19], "04": [2, 4], "lt": [2, 4], "python": [2, 3, 4], "3": [2, 7, 10, 12, 13, 19, 24, 30, 33, 35], "10": [2, 3, 4, 6, 7, 10, 12, 13, 17, 18, 19, 25, 28, 33], "20": [2, 20, 33], "8": [2, 4, 6, 7, 8, 9, 10, 12, 13, 15, 17, 18, 19, 30, 35, 42], "cuda": [2, 3, 4, 19], "12": [2, 3, 4, 7, 12, 13], "0": [2, 3, 4, 6, 7, 8, 9, 10, 12, 13, 15, 17, 18, 19, 20, 24, 25, 29, 34], "torch": [2, 3, 6, 7, 8, 9, 10, 12, 13, 15, 16, 17, 18, 19, 29, 37], "2": [2, 3, 6, 7, 8, 9, 10, 12, 13, 15, 18, 20, 24, 25, 30, 35, 36], "pip": [2, 3, 4, 16, 39], "apt": [2, 3, 4, 16], "get": [2, 3, 4, 15, 28, 40], "liblapack": [2, 3, 4, 16], "libpython3": 2, "dev": [2, 3, 4], "python3": [2, 3, 4, 16], "m": [2, 3, 4, 16], "For": [2, 3, 4, 6, 12, 15, 16, 17, 19, 20, 23, 24, 25, 26, 27, 28, 30, 32, 34, 36], "other": [2, 12, 15, 25, 27, 30, 32, 35, 36, 37], "variant": [2, 4, 20, 21, 22, 30, 31, 32, 36], "latest": [2, 3], "version": [2, 3, 4, 6, 11, 12, 15, 17, 19, 26, 33], "from": [2, 6, 7, 8, 9, 10, 12, 13, 15, 17, 18, 19, 20, 23, 24, 25, 26, 28, 29, 30, 31, 32, 33, 34, 35, 36, 42], "whl": [2, 3, 4], "file": [2, 3, 4, 12, 15, 19, 30, 32, 33, 36, 37, 40], "host": [2, 3, 4, 37, 39], "http": [2, 3, 4, 31, 37, 39], "github": [2, 3, 4, 37], "com": [2, 3, 4, 37], "quic": [2, 3, 4, 37], "onli": [2, 3, 4, 7, 10, 11, 12, 17, 19, 22, 27, 28, 30, 32, 33, 34, 37, 39, 42], "thi": [2, 3, 4, 6, 7, 8, 9, 10, 11, 12, 13, 15, 17, 18, 19, 20, 21, 23, 24, 25, 26, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 39, 42], "time": [2, 12, 15, 19, 21, 28, 29, 33, 34, 39], "prerequisit": [2, 39], "pre": [2, 3, 4, 23, 26, 31, 32], "requisit": [2, 4], "appli": [2, 6, 7, 12, 15, 17, 18, 19, 20, 21, 22, 28, 30, 31, 33, 34, 35, 36, 37, 39, 40], "all": [2, 3, 6, 11, 12, 15, 17, 19, 23, 25, 28, 31, 32, 34, 35], "mai": [2, 3, 4, 6, 10, 11, 12, 15, 17, 20, 28, 30, 31, 32], "need": [2, 3, 4, 12, 15, 19, 30, 31, 33, 34, 36, 37, 40], "addit": [2, 6, 12, 15, 30, 33, 34, 37], "pleas": [2, 4, 16, 19, 31], "see": [2, 7, 17, 18, 19, 20, 21, 22, 23, 26, 28, 30, 32, 34, 35, 36, 39, 40], "detail": [2, 3, 4, 17, 25, 35, 36, 39, 40], "x": [2, 8, 9, 10, 17, 19, 24, 29, 32], "download": [2, 3, 4, 19], "aimet_torch": [2, 3, 4, 6, 7, 8, 9, 10, 11, 12, 13, 15, 16, 17, 18, 19, 29], "cu121": [2, 3, 4], "cp310": [2, 3, 4], "manylinux_2_34_x86_64": [2, 3, 4], "f": [2, 3, 4, 19], "org": [2, 3, 4, 31], "torch_stabl": [2, 3, 4], "html": [2, 3, 4, 11, 32, 37, 40], "cpu": [2, 3, 19, 30, 37], "13": [2, 3, 7, 13], "11": [2, 3, 4, 7, 10], "cu117": 2, "tensorflow": [2, 3, 22, 26, 27, 30, 34, 36, 37], "aimet_tensorflow": [2, 4], "cu118": 2, "onnx": [2, 3, 16, 20, 21, 26, 29, 30, 31, 32, 34, 36], "16": [2, 6, 7, 8, 9, 12, 13, 15, 17, 18], "aimet_onnx": [2, 4], "older": 2, "brows": [2, 3, 4], "document": [2, 4, 26, 37, 39], "correspond": [2, 3, 4, 12, 15, 17, 23, 32, 36, 42], "select": [2, 3, 4, 21, 24, 32, 36, 39, 42], "appropri": [2, 4, 6, 12, 15, 17, 25, 35], "platform": [2, 20, 30, 36], "setup": 2, "bash": [2, 3], "command": [2, 3, 4, 39], "shell": 2, "nvidia": [2, 3, 4], "card": 2, "comput": [2, 4, 6, 8, 9, 12, 13, 15, 19, 20, 28, 29, 31, 32, 36, 39, 42], "capabl": [2, 17, 39], "5": [2, 7, 8, 9, 12, 17, 18, 24, 33, 35], "later": [2, 15, 19], "docker": 2, "To": [2, 6, 15, 17, 19, 22, 25, 29, 30, 32, 34, 35, 36, 39, 40], "us": [2, 4, 6, 7, 10, 11, 12, 13, 15, 16, 17, 18, 19, 22, 24, 26, 29, 31, 32, 33, 34, 35, 36, 37, 39, 40], "acceler": [2, 16, 26, 28], "train": [2, 16, 20, 21, 22, 26, 28, 32, 35, 36, 37], "modul": [2, 6, 11, 12, 15, 16, 19, 30, 37, 42], "an": [2, 6, 10, 11, 12, 16, 17, 18, 19, 20, 21, 23, 24, 25, 26, 28, 29, 30, 32, 33, 34, 35, 36, 40, 42], "enabl": [2, 3, 12, 16, 22, 26, 30, 32, 34, 36, 37, 39], "minimum": [2, 7, 13], "driver": [2, 4], "455": 2, "i": [2, 3, 4, 6, 7, 8, 9, 11, 12, 13, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 28, 29, 30, 31, 32, 33, 34, 35, 36, 38, 39, 40, 41, 42], "alwai": [2, 25], "recommend": [2, 12, 20, 22, 24, 30, 35], "especi": [2, 30, 33, 35], "newer": 2, "both": [2, 7, 12, 15, 16, 17, 28, 30, 31, 33, 34, 35, 36, 38, 39, 42], "cudnn": 2, "more": [2, 12, 15, 16, 17, 19, 23, 24, 25, 28, 30, 31, 32, 34, 35, 36, 39], "interfac": 2, "support": [2, 6, 12, 15, 23, 24, 26, 27, 28, 29, 30, 31, 34, 35, 36, 37, 41], "There": [2, 29, 31, 33, 40], "two": [2, 12, 19, 25, 26, 28, 30, 31, 32, 33, 36, 38, 40, 41], "wai": [2, 12, 19, 29], "On": 2, "your": [2, 3, 4, 6, 16, 20, 21, 24, 28, 29, 30, 33, 36, 39], "machin": [2, 3, 28], "our": [2, 4, 19], "built": [2, 3, 6, 17], "develop": [2, 3, 4, 11, 12, 15], "imag": [2, 20, 32], "click": 2, "link": [2, 4, 22, 31, 32], "contain": [2, 6, 10, 11, 15, 17, 19, 30, 32, 33, 34, 36], "page": [3, 4, 24, 36, 37], "provid": [3, 4, 6, 8, 9, 12, 15, 16, 19, 20, 24, 25, 28, 30, 31, 32, 34, 35, 36, 39, 40], "instruct": [3, 4, 16], "insid": [3, 6, 17, 19], "variant_str": 3, "ONE": 3, "depend": [3, 4, 10, 24, 30, 34, 37], "desir": [3, 12, 19, 24, 28, 30, 35], "pt113": 3, "tf": [3, 32, 36, 37], "export": [3, 4, 15, 16, 22, 26, 28, 29, 30, 33, 36, 37], "aimet_vari": 3, "one": [3, 12, 15, 19, 23, 28, 33, 37, 38, 39, 41], "workspac": 3, "absolute_path_to_workspac": 3, "docker_image_nam": 3, "artifact": [3, 19], "codelinaro": 3, "docker_container_nam": 3, "any_nam": 3, "note": [3, 4, 12, 15, 19, 26, 39], "feel": 3, "free": [3, 31], "modifi": [3, 4, 30, 36, 37, 42], "you": [3, 4, 6, 15, 20, 21, 24, 26, 28, 29, 30, 32, 33, 34, 35, 36, 39, 40], "want": [3, 6], "If": [3, 4, 6, 7, 8, 9, 12, 15, 17, 18, 19, 20, 21, 24, 25, 29, 30, 31, 32, 34, 35, 39, 40, 42], "skip": [3, 23], "next": [3, 19, 33, 35, 36], "section": [3, 4, 12, 22, 30, 36], "any_tag": 3, "t": [3, 6, 20, 32, 33], "jenkin": 3, "dockerfil": 3, "ensur": [3, 17, 25, 30, 35], "alreadi": [3, 6, 35], "run": [3, 4, 7, 12, 17, 18, 22, 26, 28, 30, 31, 32, 36, 37, 39], "otherwis": [3, 4, 7, 12, 18, 35], "remov": [3, 19, 23, 26, 36, 42], "exist": [3, 6, 12, 17, 36], "new": [3, 7, 12, 15, 16, 18, 19, 30, 37], "p": [3, 13], "grep": 3, "kill": 3, "rm": 3, "u": 3, "id": [3, 39], "user": [3, 6, 12, 15, 16, 20, 24, 28, 32, 35, 37], "g": [3, 19, 22], "v": [3, 12], "etc": [3, 24, 30], "passwd": 3, "ro": 3, "group": [3, 12, 34, 36], "home": 3, "mnt": 3, "entrypoint": 3, "bin": [3, 4, 13], "w": [3, 42], "hostnam": 3, "abov": [3, 4, 12, 15, 16, 28, 31, 36, 39, 42], "base": [3, 6, 7, 8, 9, 12, 13, 17, 18, 23, 24, 25, 30, 39], "filesystem": 3, "add": [3, 6, 17, 19, 34, 36, 37, 42], "order": [3, 4, 6, 12, 17, 19, 22, 23, 30, 33, 34], "access": 3, "replac": [3, 12, 17, 19, 31, 36], "port": [3, 39], "forward": [3, 6, 7, 17, 18, 19, 29, 32, 35, 37], "done": [3, 7, 18, 28, 34, 36], "visual": [3, 28, 30, 31, 32, 35, 37], "api": [3, 11, 19, 26, 29, 30, 34, 37, 39], "can": [3, 7, 10, 12, 15, 16, 17, 18, 19, 21, 22, 24, 25, 26, 28, 30, 31, 32, 33, 34, 35, 36, 39, 40, 42], "achiev": [3, 12, 20, 24], "port_id": 3, "ani": [3, 6, 12, 15, 19, 34, 37], "number": [3, 6, 7, 8, 9, 12, 13, 17, 20, 25, 26, 28, 33, 36, 37, 39, 42], "default": [3, 4, 6, 7, 11, 15, 17, 18, 20, 25, 28, 34, 36, 37, 39], "go": [3, 4, 15, 19], "project": [3, 4], "requir": [3, 4, 6, 12, 15, 19, 22, 24, 28, 30, 31, 34, 35, 39], "each": [3, 4, 6, 11, 12, 17, 18, 19, 22, 23, 24, 25, 28, 30, 31, 32, 33, 34, 35, 36, 40], "identifi": [3, 4, 12, 23, 32, 35, 37, 42], "wish": [3, 4], "some": [3, 4, 17, 19, 20, 24, 25, 29, 30, 31, 33, 35, 36, 42], "tip": [3, 4], "32": [3, 4, 7, 15, 18, 35], "post1": [3, 4], "7": [3, 4, 7, 8, 9, 19, 35, 42], "31": [3, 4], "prepend": [3, 4, 17], "sudo": [3, 4], "y": [3, 4, 19, 32], "we": [3, 4, 12, 15, 17, 19, 20, 24, 28, 30, 31, 35], "also": [3, 4, 12, 23, 28, 30, 32, 34, 36, 37, 40, 42], "wheel": [3, 4], "differ": [3, 4, 12, 23, 25, 28, 30, 31, 33, 35, 36], "which": [3, 4, 6, 7, 10, 12, 13, 15, 16, 17, 18, 19, 22, 24, 25, 28, 30, 31, 32, 34, 36, 37, 39, 42], "tag": [3, 4, 37], "below": [3, 4, 6, 7, 12, 15, 17, 18, 19, 22, 23, 25, 28, 30, 31, 32, 34, 35, 36, 39], "ex": [3, 4, 12], "34": [3, 4], "release_tag": [3, 4], "construct": [3, 4, 19, 29], "root": [3, 4, 19], "url": [3, 4, 39], "download_url": [3, 4], "extens": [3, 4, 17], "wheel_file_nam": [3, 4], "do": [3, 4, 19, 28, 32, 35, 36], "find_pkg_url_str": [3, 4], "specifi": [3, 4, 7, 8, 9, 12, 18, 19, 21, 23, 24, 25, 28, 34, 36, 39], "automat": [3, 4, 12, 24, 28, 30, 32, 37], "common": [3, 12, 35, 40], "variabl": [3, 4, 7, 18, 25], "sourc": [3, 4, 6, 7, 8, 9, 10, 11, 12, 13, 15, 17, 18, 35], "usr": [3, 4], "lib": [3, 4], "dist": [3, 4], "envsetup": [3, 4], "sh": [3, 4], "unless": [4, 6, 15, 42], "pend": 4, "pip3": 4, "h": [4, 41, 42], "These": [4, 17, 19, 21, 22, 23, 24, 29, 30, 31, 32, 35, 36], "assum": [4, 12, 15, 25], "path": [4, 11, 15], "local": [4, 39], "case": [4, 7, 12, 17, 19, 25, 31, 34], "accordingli": 4, "basic": [4, 16, 19], "updat": [4, 13, 18, 30, 31, 33, 36, 37, 39], "upgrad": 4, "ye": [4, 28], "wget": 4, "gnupg2": 4, "have": [4, 6, 11, 12, 19, 28, 31, 32, 35], "multipl": [4, 12, 17, 26, 28, 37], "set": [4, 6, 11, 12, 15, 17, 18, 20, 24, 25, 28, 29, 31, 32, 33, 34, 35], "altern": [4, 12], "were": [4, 15, 24, 34, 42], "test": 4, "sub": [4, 36], "visit": [4, 16], "archiv": 4, "obtain": [4, 24, 32], "correct": [4, 19, 20, 30, 31, 35], "exact": [4, 22, 30], "up": [4, 12, 20, 28, 34, 42], "date": 4, "execut": [4, 19, 39], "final": [4, 12, 23, 24, 25, 33, 35], "aforement": 4, "repo": 4, "ubuntu2204": 4, "x86_64": 4, "keyring_1": 4, "1_all": 4, "deb": 4, "dpkg": 4, "33": [4, 7, 18], "cat": 4, "reqs_deb_common": 4, "txt": 4, "xarg": 4, "reqs_deb_torch_common": 4, "reqs_deb_onnx_common": 4, "reqs_deb_tf_gpu": 4, "reqs_deb_torch_gpu": 4, "reqs_deb_onnx_gpu": 4, "option": [4, 6, 7, 12, 15, 16, 18, 19, 20, 32, 34, 36], "uninstal": 4, "cach": 4, "dir": 4, "9": [4, 7, 10], "onnxruntime_v": 4, "c": [4, 24], "import": [4, 6, 7, 8, 9, 10, 12, 13, 15, 16, 17, 18, 19, 22, 23], "print": [4, 6, 7, 17, 19, 32], "__version__": 4, "ln": 4, "": [4, 6, 12, 16, 17, 18, 19, 23, 24, 25, 27, 28, 30, 31, 32, 33, 35, 36, 40, 42], "gnu": 4, "libjpeg": 4, "so": [4, 17, 25, 29, 32], "chose": 4, "between": [4, 12, 17, 31, 32, 34, 36], "class": [6, 8, 12, 13, 15, 18, 19], "v2": [6, 7, 8, 9, 10, 11, 12, 13, 15, 16, 17, 18, 19], "nn": [6, 7, 11, 12, 16, 17, 18, 19, 29, 37], "arg": [6, 7, 10, 12, 15, 17, 18], "kwarg": [6, 7, 10, 17, 18], "mixin": [6, 17], "quantiz": [6, 8, 11, 13, 15, 16, 20, 21, 22, 24, 26, 28, 32, 37, 39], "function": [6, 10, 11, 12, 17, 19, 20, 25, 28, 29, 32, 36, 37, 39, 40], "top": [6, 23, 39], "regular": [6, 17, 20, 30, 36], "specif": [6, 12, 17, 19, 21, 22, 26, 29, 30, 31, 34, 37], "input": [6, 7, 8, 9, 11, 12, 13, 15, 17, 18, 19, 23, 25, 28, 32, 34, 36, 38, 41, 42], "output": [6, 7, 12, 17, 18, 19, 23, 28, 31, 32, 34, 36, 37, 38, 41, 42], "paramet": [6, 7, 8, 9, 10, 11, 12, 13, 17, 18, 19, 22, 23, 28, 29, 30, 31, 32, 33, 34, 40], "tensor": [6, 7, 8, 9, 12, 13, 15, 17, 18, 19, 20, 23, 29, 30, 32, 34, 35, 36, 37], "its": [6, 10, 15, 16, 17, 19, 23, 26, 32, 36, 42], "held": [6, 17, 19], "quantizerbas": [6, 17, 18], "object": [6, 10, 11, 12, 15, 17, 18, 19, 22, 30, 33, 36], "dure": [6, 11, 15, 17, 19, 20, 26, 28, 30, 33, 34, 36, 39, 40], "method": [6, 12, 15, 17, 19, 25, 28, 30, 35, 36], "inherit": [6, 17], "layer": [6, 11, 12, 15, 17, 19, 20, 21, 22, 23, 24, 27, 29, 30, 32, 34, 35, 36, 37, 38, 39, 40, 41, 42], "oper": [6, 17, 19, 29, 30, 31, 34, 35], "none": [6, 7, 8, 9, 11, 12, 15, 17, 19, 39], "behav": [6, 17, 35], "exactli": [6, 17, 36], "same": [6, 10, 12, 17, 18, 22, 31, 34, 40], "parent": [6, 17], "input_quant": [6, 17, 19], "modulelist": [6, 17, 19], "output_quant": [6, 17, 19], "param_quant": [6, 12, 17, 19], "moduledict": [6, 17, 19], "map": [6, 7, 10, 12, 17, 25, 32, 34], "associ": [6, 17, 30], "exampl": [6, 7, 8, 9, 10, 11, 12, 13, 17, 18, 19, 20, 24, 26, 30, 32, 34, 35, 36, 37, 42], "qlinear": [6, 17], "quantizedlinear": [6, 12, 17, 19], "in_featur": [6, 17, 19], "out_featur": [6, 17, 19], "bia": [6, 8, 9, 17, 19, 20, 23, 30, 31, 34, 35, 37], "true": [6, 7, 8, 9, 10, 12, 13, 17, 18, 19, 29, 34], "weight": [6, 11, 12, 13, 15, 17, 19, 20, 22, 24, 28, 30, 31, 32, 33, 34, 35, 36, 40], "abstract": [6, 17, 18], "should": [6, 12, 15, 17, 19, 24], "perform": [6, 7, 12, 15, 17, 18, 19, 21, 22, 23, 24, 25, 28, 30, 31, 32, 33, 35], "logic": [6, 17, 37], "param": [6, 12, 17, 18, 34], "call": [6, 8, 9, 10, 12, 17, 19, 30, 32, 34, 36, 37, 38, 41], "pass": [6, 12, 15, 16, 17, 19, 26, 29, 31, 32, 33, 35, 36, 37, 39], "__quant_init__": [6, 17], "initi": [6, 7, 8, 9, 17, 18, 20, 33, 36], "invok": [6, 17, 28, 30, 39, 40], "right": [6, 7, 8, 9, 17, 18, 42], "after": [6, 13, 15, 17, 19, 20, 21, 22, 24, 28, 30, 35, 39, 40], "__init__": [6, 17, 19], "structur": [6, 17, 28], "size": [6, 7, 12, 15, 17, 18, 20, 29, 38, 41], "initializd": [6, 17], "custom": [6, 17, 35, 36], "overridden": [6, 17, 34], "length": [6, 12, 17], "given": [6, 11, 12, 13, 17, 21, 25, 28, 31], "set_kernel": 6, "kernel": [6, 12, 23, 38, 41], "instanc": [6, 39], "In": [6, 12, 17, 19, 20, 24, 25, 28, 30, 31, 33, 34, 36, 39, 40, 42], "gener": [6, 7, 12, 15, 18, 19, 28, 30, 32, 33, 34, 35, 36], "signatur": [6, 7], "equival": [6, 7, 8, 9, 12, 19], "return": [6, 10, 11, 12, 13, 15, 16, 18, 19, 21, 25, 26, 32, 36], "quantizedtensor": [6, 7, 10, 18], "take": [6, 12, 19, 25, 28, 30, 31, 33, 35, 42], "keyword": 6, "argument": [6, 8, 9, 12], "output_encod": 6, "onc": [6, 22, 23, 28, 32, 33, 36], "within": [6, 10, 17, 24, 32, 36], "compute_encod": [6, 7, 8, 9, 10, 11, 13, 15, 16, 17, 18, 19], "context": [6, 17, 19], "callabl": [6, 12], "underli": [6, 35], "q": [6, 7, 8, 9, 10, 17, 18, 36], "def": [6, 15, 19], "int_multipli": 6, "b": [6, 7, 18], "encod": [6, 7, 10, 12, 15, 16, 18, 19, 20, 22, 30, 32, 33, 37], "enc": 6, "affin": [6, 10, 12, 15, 16, 17, 18, 19], "rais": 6, "notimplementederror": 6, "q_output": 6, "quantized_repr": [6, 10], "offset": [6, 7, 12, 13, 15, 18, 30, 32, 33, 36], "dq_output": 6, "scale": [6, 7, 8, 9, 10, 12, 15, 18, 22, 30, 31, 32, 33, 36], "qmult": 6, "quantizedmultipli": [6, 17], "classmethod": 6, "set_default_kernel": 6, "cl": [6, 37], "ha": [6, 10, 12, 15, 19, 24, 25, 30, 31, 33, 36, 39, 42], "been": [6, 10, 11, 12, 15, 36, 42], "get_kernel": 6, "enter": [6, 17, 21], "observ": [6, 13, 17, 18, 19, 28, 31, 32, 36], "upon": [6, 17, 19], "exit": [6, 17, 19], "symmetr": [6, 7, 10, 12, 13, 17, 18, 19, 34, 36], "fals": [6, 7, 10, 12, 13, 15, 17, 18, 19, 29, 34], "randn": [6, 7, 10, 13, 17, 18], "is_initi": [6, 7, 8, 9, 17, 18], "from_modul": 6, "creat": [6, 11, 13, 15, 16, 17, 19, 20, 22, 28, 29, 30, 33, 36], "result": [6, 10, 12, 13, 15, 20, 21, 23, 24, 26, 28, 31, 32, 33, 34, 36], "attribut": [6, 17, 32], "origin": [6, 17, 19, 23, 24, 25, 30, 31, 32, 36, 39], "assign": [6, 7, 17, 18], "float": [6, 8, 10, 12, 13, 16, 30, 32, 35, 36, 40], "point": [6, 10, 12, 16, 26, 30, 32, 35, 36, 40], "linear": [6, 12, 17, 19, 22, 23], "quantized_linear": 6, "get_default_kernel": 6, "type": [6, 10, 11, 12, 15, 17, 18, 28, 30, 32, 34, 36, 39], "current": [6, 27, 41], "doe": [6, 19, 23, 25, 27, 30, 35, 36], "retriev": 6, "implement": [6, 29, 30, 35], "module_cl": 6, "decor": 6, "regist": [6, 18], "definit": [6, 19, 30], "even": 6, "though": [6, 12, 34], "aimet": [6, 15, 17, 19, 26, 29, 34], "subpackag": 6, "conv2d": [6, 12, 17, 19, 23, 28, 37, 42], "awar": [6, 20, 22, 26, 28, 30, 35, 36], "quantizationsimmodel": [6, 11, 12, 15, 16, 19, 20, 22], "throw": 6, "runtim": [6, 12, 15, 16, 19, 24, 26, 28, 30, 32, 34, 36, 37], "error": [6, 21, 30, 32, 33, 35, 36], "when": [6, 12, 15, 16, 17, 19, 20, 28, 30, 31, 32, 33, 34, 35, 36, 39, 40, 42], "encount": [6, 19], "defin": [6, 12, 17, 19, 30, 32, 34, 36], "ask": 6, "doesn": [6, 33], "know": 6, "declar": 6, "subclass": [6, 13], "As": [6, 12, 15, 21, 24, 25, 31, 32, 36], "maskedadd": 6, "self": [6, 10, 19], "mask": 6, "valu": [6, 7, 8, 9, 10, 11, 12, 13, 15, 18, 19, 20, 23, 24, 25, 28, 30, 31, 32, 33, 34, 36, 38, 40, 41], "befor": [6, 11, 17, 19, 20, 21, 22, 28, 30, 32, 33, 36, 40], "typic": [6, 12, 17, 19, 24, 30, 32, 33, 36], "quantizedmaskedadd": 6, "matter": 6, "super": [6, 19], "input_qtzr": 6, "_": [6, 7, 11, 16, 17, 18, 19, 30], "don": [6, 20, 32], "boolean": 6, "value_qtzr": 6, "output_qtzr": 6, "shape": [7, 8, 9, 10, 12, 13, 17, 18, 19, 32], "precis": [7, 8, 9, 16, 18, 30], "out": [7, 8, 9, 18], "clamp": [7, 8, 9, 18, 36], "left": [7, 8, 9, 18, 25, 42], "lceil": [7, 8, 9, 18], "frac": [7, 8, 9, 18], "rfloor": [7, 8, 9, 18], "qmin": [7, 18, 36], "qmax": [7, 18, 36], "where": [7, 8, 9, 15, 18, 19, 22, 25, 32, 38, 39, 41, 42], "deriv": [7, 18, 36], "learnabl": [7, 18], "theta_": [7, 18], "min": [7, 11, 13, 18, 19, 32, 36], "max": [7, 8, 9, 11, 13, 18, 19, 28, 31, 32, 36], "block": [7, 12, 15, 18], "begin": [7, 18, 34], "pmatrix": [7, 18], "b_0": [7, 18], "b_1": [7, 12, 18], "cdot": [7, 18], "b_": [7, 18], "d": [7, 18], "end": [7, 18, 19, 28], "equat": [7, 12, 18, 36], "further": [7, 10, 12, 18, 19, 20, 23, 26, 28], "out_": [7, 18], "j_0": [7, 18], "j_": [7, 18], "input_": [7, 18], "scale_": [7, 18], "i_0": [7, 18], "i_": [7, 18], "offset_": [7, 18], "text": [7, 18], "quad": [7, 18, 36], "forall_": [7, 18], "leq": [7, 18], "i_d": [7, 18], "lfloor": [7, 8, 9, 18], "j_d": [7, 18], "b_d": [7, 18], "tupl": [7, 12, 13, 15, 18], "bitwidth": [7, 8, 9, 10, 12, 15, 17, 18, 19, 22, 30, 35, 36], "int": [7, 8, 9, 12, 13, 18], "bool": [7, 12, 13, 18], "asymmetr": [7, 13, 18, 34, 36], "encoding_analyz": [7, 8, 9, 13, 18], "encodinganalyz": [7, 8, 9, 13, 18], "analyz": [7, 16, 17, 18, 21, 23, 29, 32, 39, 40], "calibr": [7, 11, 12, 13, 15, 16, 17, 18, 19, 30, 32, 33, 35, 36], "absolut": [7, 18], "block_siz": [7, 12, 18], "cannot": [7, 18], "until": [7, 18, 21], "properli": [7, 18, 19], "statist": [7, 8, 9, 11, 13, 17, 18, 19, 22, 30, 32, 40], "manual": [7, 18, 21, 28], "129": [7, 18, 29], "255": [7, 10, 18], "122": [7, 18], "192": [7, 18], "106": [7, 18], "94": [7, 18], "145": [7, 18], "181": [7, 18], "144": [7, 18], "194": [7, 18], "74": [7, 18], "86": [7, 18], "150": [7, 18], "103": [7, 18], "37": [7, 18], "111": [7, 18], "237": [7, 18], "218": [7, 18], "49": [7, 18], "155": [7, 18], "179": [7, 18], "66": [7, 18, 24], "89": [7, 18], "110": [7, 18], "17": [7, 13, 18], "36": [7, 18], "83": [7, 18], "grad_fn": [7, 10, 18], "aliasbackward0": [7, 10, 18], "ones_lik": [7, 18], "187": [7, 18], "186": [7, 18], "131": [7, 18], "203": [7, 18], "80": [7, 13, 18], "143": [7, 18], "152": [7, 18], "226": [7, 18], "55": [7, 18], "172": [7, 18], "207": [7, 18], "146": [7, 18], "216": [7, 18], "238": [7, 18], "141": [7, 18], "178": [7, 18], "188": [7, 18], "63": [7, 18], "59": [7, 18], "19": [7, 13, 18], "162": [7, 18], "30": [7, 18], "109": [7, 18], "quantizedequant": [7, 9, 10, 12, 17, 18, 19], "fake": [7, 8, 9, 18, 19], "dequant": [7, 10, 18], "overlin": [7, 18], "qdq": [7, 8, 9, 18], "dequantizedtensor": [7, 10, 18], "2771": [7, 18], "3038": [7, 18], "0819": [7, 18], "9700": [7, 18], "9487": [7, 18], "1307": [7, 18], "7894": [7, 18], "1709": [7, 18], "2212": [7, 18], "7741": [7, 18], "0295": [7, 18], "2265": [7, 18], "0564": [7, 18], "6177": [7, 18], "0386": [7, 18], "0176": [7, 18], "6054": [7, 18], "8836": [7, 18], "1232": [7, 18], "8229": [7, 18], "5540": [7, 18], "3992": [7, 18], "2363": [7, 18], "2546": [7, 18], "0036": [7, 18], "2355": [7, 18], "1741": [7, 18], "6079": [7, 18], "6247": [7, 18], "0115": [7, 18], "2458": [7, 18], "9157": [7, 18], "4694": [7, 18], "0639": [7, 18], "2568": [7, 18], "0680": [7, 18], "6695": [7, 18], "7932": [7, 18], "1889": [7, 18], "0158": [7, 18], "5695": [7, 18], "5220": [7, 18], "1977": [7, 18], "4475": [7, 18], "0424": [7, 18], "1128": [7, 18], "8796": [7, 18], "1060": [7, 18], "5897": [7, 18], "6196": [7, 18], "9961": [7, 18], "0549": [7, 18], "6431": [7, 18], "0039": [7, 18], "8706": [7, 18], "4706": [7, 18], "2353": [7, 18], "8078": [7, 18], "3451": [7, 18], "1176": [7, 18], "4549": [7, 18], "0471": [7, 18], "5255": [7, 18], "4157": [7, 18], "0784": [7, 18], "5333": [7, 18], "1647": [7, 18], "2118": [7, 18], "2196": [7, 18], "9176": [7, 18], "9490": [7, 18], "7765": [7, 18], "4784": [7, 18], "6039": [7, 18], "3137": [7, 18], "3216": [7, 18], "8000": [7, 18], "4392": [7, 18], "4863": [7, 18], "overload": 7, "list": [7, 12, 15, 17, 18, 25, 27, 29, 34], "sign": [7, 36], "rceil": 7, "posit": 7, "integ": [7, 12, 20, 30, 32], "rang": [7, 11, 13, 19, 20, 22, 25, 30, 31, 32, 33, 35, 36, 37, 40], "over": [7, 13, 17, 20, 25, 28, 40], "neg": [7, 12], "num_step": [7, 13], "num": 7, "_step": 7, "step": [7, 13, 15, 16, 19, 20, 21, 22, 23, 24, 25, 28, 30, 31, 33, 35], "maximum": [7, 8, 9, 13], "arang": 7, "start": [7, 19, 20, 24, 34, 36], "05": [7, 19], "0000e": 7, "01": [7, 20], "5000e": 7, "02": 7, "1921e": 7, "08": 7, "4": [7, 10, 12, 19, 22, 25, 30, 35, 42], "6": [7, 12, 13, 15, 33, 35], "00": 7, "0500e": 7, "1000e": 7, "1500e": 7, "2000e": 7, "2500e": 7, "15": [7, 28, 33], "14": [7, 19], "quantize_dequant": 7, "0000": [7, 10], "0667": 7, "1333": 7, "2000": [7, 10], "2667": 7, "3333": 7, "4000": [7, 10], "4667": 7, "6000": [7, 10], "6667": 7, "7333": 7, "8667": 7, "9333": 7, "exponent_bit": [8, 9, 12], "mantissa_bit": [8, 9, 12], "dtype": [8, 9, 10, 12, 15], "simul": [8, 9, 12, 15, 16, 17, 19, 26, 30, 33, 37], "cast": [8, 9], "expon": [8, 9, 12], "mantissa": [8, 9, 12], "x_c": [8, 9], "log_2": [8, 9], "ieee": [8, 9, 28, 31], "standard": [8, 9, 17], "represent": [8, 9, 10], "_max": [8, 9], "mutual": [8, 9, 12], "exclus": [8, 9, 12], "repres": [8, 9, 10, 17, 18, 19, 25, 31, 32, 33, 36], "determin": [8, 9, 12, 17, 19, 21, 30, 31, 32, 40], "dynam": [8, 9, 31, 36, 37, 40], "finer": [8, 9, 12], "8998": [8, 9], "0947": [8, 9], "0891": [8, 9], "1727": [8, 9], "unlik": [8, 9], "affinequant": [8, 9], "floatquant": [8, 9], "without": [8, 9, 10, 11, 12, 15, 21, 30, 33, 36, 42], "is_bfloat16": [8, 9], "8984": [8, 9], "0859": [8, 9], "1729": [8, 9], "minmaxencodinganalyz": [8, 9, 13], "float16": [8, 9, 12], "is_float16": [8, 9], "8994": [8, 9], "0889": [8, 9], "alia": [8, 9], "floatquantizedequant": 9, "hold": [10, 12, 15, 17, 34, 35], "store": [10, 12, 15], "along": [10, 12, 19, 33, 36], "encodingbas": [10, 18], "inform": [10, 15, 30], "necessari": [10, 12, 19, 39], "back": [10, 19, 34], "real": [10, 39], "produc": [10, 11, 12, 13, 25, 32], "rtype": 10, "57": 10, "312": 10, "153": 10, "205": 10, "set_rang": 10, "128": [10, 12, 19], "127": 10, "x_q": 10, "26": 10, "23": [10, 13], "x_dq": 10, "3000": 10, "equal": [10, 12, 20, 21, 24, 25, 29, 30, 32, 35, 36, 40], "data": [10, 11, 12, 13, 15, 16, 19, 20, 22, 27, 31, 32, 33, 35, 36], "abl": [10, 19], "carri": 10, "gradient": 10, "thu": 10, "autograd": 10, "allow": [10, 12, 21, 28, 35, 36, 37, 39], "backpropag": 10, "requires_grad": 10, "38": [10, 28], "28": 10, "40": 10, "int8": [10, 33, 36, 40], "subsequ": [10, 15, 29, 31, 34], "well": [10, 12, 15, 28, 31, 32], "about": [10, 19, 26, 32], "wa": [10, 28], "With": [10, 30, 33], "convert": [10, 19, 21, 30, 40], "loss": [10, 16, 19, 20, 26, 28, 30, 32, 36], "39": [10, 19], "51": 10, "521": 10, "41": 10, "quant_dequ": 10, "x_qdq": 10, "52": 10, "68": 10, "97": 10, "uint8": 10, "featur": [11, 12, 15, 20, 21, 22, 28, 31, 32, 35, 36, 37, 39, 40], "under": [11, 12, 15, 32, 34], "heavi": [11, 12, 15, 39, 40], "chang": [11, 12, 15, 19, 20, 28, 32, 33, 34, 36, 40, 42], "occur": [11, 12, 15], "notic": [11, 12, 15], "futur": [11, 12, 15], "visualization_tool": 11, "visualize_stat": 11, "sim": [11, 12, 15, 16, 19, 33, 36], "dummy_input": [11, 12, 15, 19], "save_path": 11, "quant_stats_visu": 11, "interact": 11, "view": [11, 16, 19, 22, 26, 29, 31, 32, 39], "stat": [11, 13], "collect": [11, 12, 25, 32], "expect": [11, 13, 15, 19, 28, 30, 32], "plot": [11, 32], "activ": [11, 12, 15, 17, 19, 30, 32, 33, 34, 35, 36], "quantsim": [11, 12, 15, 16, 30, 33, 34, 37], "includ": [11, 12, 22, 25, 32, 33, 34, 36, 37, 39], "adjust": [11, 12, 20, 22, 23, 24, 30, 31, 35], "threshold": [11, 17, 21], "flag": [11, 18], "whose": [11, 12, 31, 34], "exce": 11, "tabl": [11, 39], "exceed": 11, "save": [11, 15, 19, 36, 40], "quant_schem": [11, 15], "quantschem": [11, 15, 21], "post_training_tf": [11, 15], "data_load": [11, 15, 16, 19], "sampl": [11, 16, 17, 19, 23, 31, 32, 33, 36], "trace": 11, "str": [11, 15], "known": [12, 26], "like": [12, 15, 16, 19, 21, 26, 28, 30, 32, 33, 34], "grid": 12, "counterpart": [12, 17], "process": [12, 13, 16, 19, 21, 23, 25, 26, 28, 31, 36], "particular": [12, 30, 34], "choos": [12, 23, 24, 28], "come": [12, 28, 33], "cover": [12, 36], "whole": [12, 36], "split": 12, "describ": [12, 28, 29, 30, 31, 34, 35, 36, 39], "sever": [12, 17, 24, 32], "pro": 12, "con": 12, "per": [12, 15, 17, 22, 31, 32, 34, 35, 36, 37, 39], "entir": [12, 19, 28], "singl": [12, 20, 25, 28, 31], "benefit": [12, 20], "less": [12, 13, 23, 25, 34], "storag": 12, "space": 12, "drawback": 12, "outlier": [12, 32, 36], "affect": [12, 22, 34], "channel": [12, 15, 17, 22, 24, 25, 27, 28, 31, 32, 34, 35, 36, 37, 38, 40, 41, 42], "individu": [12, 22, 25, 30, 32, 34, 35], "dimens": [12, 15, 17, 35, 38, 41], "compar": [12, 15, 19, 30, 32, 33, 40], "would": [12, 13, 34, 37], "influenc": 12, "resid": [12, 37], "chunk": 12, "across": [12, 31, 32, 40], "improv": [12, 19, 24, 28, 30, 33, 35, 40], "granular": [12, 28, 35, 36, 40], "found": [12, 33, 36], "isol": 12, "optim": [12, 15, 19, 20, 21, 26, 28, 30, 33, 36, 37, 39], "cost": [12, 25, 28, 33], "increas": [12, 25, 31], "favor": 12, "possibl": [12, 19, 25, 32, 34, 35], "similarli": [12, 15, 35], "lead": [12, 20, 22, 31, 35], "better": [12, 20, 21, 28, 30, 31, 33], "accuraci": [12, 16, 19, 20, 21, 24, 25, 26, 28, 30, 31, 32, 33, 35, 36, 37, 40, 42], "part": [12, 28, 31, 32], "basi": 12, "instanti": [12, 15, 19, 39], "relationship": 12, "actual": 12, "being": [12, 23], "rule": [12, 34], "must": [12, 15, 17, 21, 22, 24, 26, 27, 30, 32, 34, 42], "match": [12, 23, 28, 32, 34, 35, 36, 42], "most": [12, 19, 34], "long": [12, 15], "b_2": 12, "b_n": 12, "s_1": 12, "s_2": 12, "s_n": 12, "satisfi": [12, 19, 21], "n": [12, 19, 37], "word": 12, "evenli": 12, "divid": [12, 17, 24, 33], "valid": [12, 21, 30, 37], "sinc": [12, 22, 24, 36], "divis": 12, "permit": 12, "essenti": [12, 16], "invalid": 12, "combin": [12, 21, 24, 28, 30, 31], "3d": 12, "infer": [12, 15, 16, 19, 22, 24, 26, 31, 33, 36, 37], "while": [12, 17, 20, 25, 29, 33, 35], "arbitrari": 12, "experiment": [12, 28], "purpos": 12, "restrict": [12, 29], "place": [12, 15, 34], "constraint": 12, "still": [12, 30, 35], "themselv": [12, 33], "code": [12, 19, 20], "show": [12, 15, 16, 19, 22, 25, 26, 31, 35], "how": [12, 15, 17, 19, 28, 30, 31, 32, 34, 35, 36, 38, 41], "configur": [12, 15, 19, 27, 37], "convolut": [12, 19, 22, 23, 24, 28, 35, 38, 41, 42], "conv_1": 12, "refer": [12, 15, 17, 20, 36], "quantizedconv2d": [12, 17, 19], "work": [12, 28, 31], "too": 12, "linear_1": 12, "scheme": [12, 13, 21, 22, 28, 32], "lower": [12, 25, 30, 35], "thei": [12, 35, 39], "lie": 12, "higher": [12, 13, 22, 25, 33, 35], "leverag": 12, "than": [12, 15, 19, 24, 27, 33, 34], "due": [12, 31], "fact": 12, "expans": [12, 28], "factor": [12, 13, 24, 28, 31], "fashion": 12, "groupedblockquantizedequant": 12, "introduc": [12, 17, 30, 34, 36], "decompressed_bw": 12, "expand": 12, "greater": [12, 24, 25], "block_group": 12, "togeth": 12, "except": 12, "make": [12, 17, 29, 30], "easier": 12, "config_util": 12, "set_blockwise_quantization_for_weight": 12, "consist": [12, 25, 36], "either": [12, 20, 42], "A": [12, 20, 24, 25, 28, 30, 32, 33, 36], "union": [12, 15], "arrai": 12, "in_channel": [12, 19], "out_channel": [12, 19], "conv": [12, 27, 34, 37, 38, 41, 42], "input_channel": 12, "conv2": [12, 19], "linear1": 12, "dim": [12, 19], "lambda": 12, "isinst": 12, "util": [12, 19, 22, 30], "certain": [12, 28, 29, 34], "Of": 12, "signific": [12, 35], "second": [12, 17, 34], "subset": [12, 20, 22, 32, 42], "switch": 12, "docstr": 12, "instead": [12, 15, 30, 31, 42], "4d": 12, "2d": [12, 23, 28, 42], "handl": 12, "mention": 12, "assist": 12, "transform": [12, 15, 19, 37], "set_activation_quantizers_to_float": 12, "set_grouped_blockwise_quantization_for_weight": 12, "decompress": 12, "bw": 12, "experi": [12, 28], "similar": [12, 31, 33, 36], "addition": 12, "effect": [12, 17, 19, 22, 30, 32, 36], "larger": [12, 38, 41], "reduc": [12, 15, 17, 28, 30, 31, 33, 35, 37, 42], "write": [12, 15], "snippet": [12, 15], "format": [12, 15, 18, 21, 27], "encoding_vers": [12, 15], "exported_model": [12, 15], "present": [12, 15, 19, 31], "gather": 13, "is_symmetr": [13, 34], "reset_stat": 13, "reset": 13, "intern": [13, 28, 31, 34], "update_stat": 13, "input_tensor": 13, "involv": [13, 19, 30, 35], "track": [13, 32], "calcul": [13, 17, 25, 31, 32, 33, 36], "100": [13, 15, 19], "math": [13, 19], "pow": 13, "0991": 13, "3696": 13, "_minmaxrang": 13, "1721": 13, "2592": 13, "sqnrencodinganalyz": 13, "num_bin": 13, "2048": [13, 15], "asymmetric_delta_candid": 13, "symmetric_delta_candid": 13, "101": 13, "offset_candid": 13, "21": 13, "max_parallel": 13, "gamma": 13, "sqnr": [13, 36], "record": 13, "histogram": [13, 30, 32, 36, 37], "lowest": [13, 23], "delta": [13, 36], "search": [13, 33, 34], "mode": [13, 18, 29, 30, 34], "parallel": 13, "memori": [13, 24, 28, 38, 41, 42], "usag": [13, 16], "faster": [13, 26], "clip": [13, 34, 36], "nois": [13, 19, 30, 31, 32, 33, 34], "percentil": 13, "3612": 13, "8497": 13, "_histogram": 13, "bin_edg": 13, "8907": 13, "3625": 13, "8343": 13, "3061": 13, "7779": 13, "2497": 13, "2784": 13, "8066": 13, "3348": 13, "8630": 13, "3912": 13, "7080": 13, "2438": 13, "percentileencodinganalyz": 13, "largest": 13, "smallest": 13, "1188": 13, "3368": 13, "27": 13, "5710": 13, "0989": 13, "6269": 13, "1548": 13, "6827": 13, "2106": 13, "2614": 13, "7335": 13, "2056": 13, "6776": 13, "1497": 13, "gptvq_weight": 15, "apply_gptvq": 15, "gptvq_param": 15, "param_encoding_path": 15, "module_names_to_exclud": 15, "block_level_module_nam": 15, "file_name_prefix": 15, "config_file_path": 15, "round": [15, 16, 20, 30, 32, 36], "separ": [15, 22, 32, 35, 37], "qat": [15, 19, 20, 22, 26, 30, 35, 36, 37], "dummi": [15, 32], "pars": 15, "graph": [15, 29, 30, 36, 39], "devic": [15, 16, 19, 36], "gptvqparamet": 15, "dataclass": 15, "exclud": 15, "leaf": [15, 37], "prefix": [15, 17], "filenam": 15, "forward_fn": 15, "row_axi": 15, "col_axi": 15, "rows_per_block": 15, "cols_per_block": 15, "256": [15, 19, 32], "vector_dim": 15, "vector_bw": 15, "vector_strid": 15, "index_bw": 15, "num_of_kmeans_iter": 15, "assignment_chunk_s": 15, "carrier": 15, "dataload": [15, 19, 32], "wise": [15, 35], "explicitli": [15, 42], "load": [15, 28], "pretrain": [15, 33, 36], "opt": 15, "125m": 15, "packag": [15, 37], "optforcausallm": 15, "from_pretrain": 15, "facebook": 15, "now": [15, 19, 37], "gptvq_applied_model": 15, "zero": [15, 36, 37], "lm_head": 15, "gptvq_opt": 15, "default_param_bw": [15, 19], "default_output_bw": [15, 19], "load_encod": 15, "allow_overwrit": [15, 18], "through": [15, 17, 19, 31, 32, 36], "here": [15, 19, 30, 33, 34], "vector": 15, "index": [15, 17, 37], "blockwis": 15, "lpbq": 15, "tool": [16, 19, 31, 40, 42], "compress": [16, 23, 26, 37, 38, 40, 41, 42], "deploi": [16, 36], "edg": [16, 26], "fix": [16, 26, 30, 35, 36, 37], "post": [16, 19, 20, 21, 26, 28, 33, 36, 37], "fine": [16, 24, 26, 30, 33, 36], "tune": [16, 24, 26, 30, 33, 36], "techniqu": [16, 19, 21, 23, 24, 26, 30, 32, 33, 35, 36, 37, 38, 41], "minim": [16, 26, 30, 36], "incur": [16, 26, 32], "pictur": 16, "high": [16, 20, 24, 25, 26, 31, 37, 40], "level": [16, 24, 25, 26, 30, 35, 39], "workflow": [16, 19, 24, 26], "low": [16, 20, 22, 28, 30, 31], "recov": [16, 26, 35, 36], "lost": [16, 26, 36], "via": [16, 24, 36], "torchscript": 16, "target": [16, 22, 24, 25, 26, 28, 30, 35, 36, 37], "neural": [16, 19, 21, 24, 26, 28, 30, 33, 35, 36, 41], "sdk": [16, 19, 26], "instal": [16, 26, 37, 39], "sample_input": [16, 19], "sample_output": 16, "out_dir": 16, "quantized_model": 16, "quickstart": 16, "guid": [16, 24, 31, 35, 37], "depth": [16, 24, 35], "adapt": [16, 19, 20, 30, 32, 37], "adaround": [16, 21, 30, 35, 37], "quantizationmixin": [16, 17], "product": [16, 24, 26], "technologi": [16, 26], "subsidiari": [16, 26], "network": [17, 19, 21, 24, 25, 28, 30, 33, 35, 36, 39, 41], "extra": 17, "serv": [17, 39], "drop": [17, 21, 24, 28, 31, 32, 33, 35, 36], "nativ": 17, "quantizedsoftmax": [17, 19], "softmax": [17, 19], "full": 17, "behavior": [17, 19, 26], "control": [17, 36], "descript": [17, 20, 29], "dict": [17, 18], "By": [17, 20, 28, 36], "mean": [17, 19, 32, 34, 36], "respect": [17, 32], "per_channel_quant": [17, 34], "elementwis": [17, 37], "multipli": [17, 24, 28], "qmul": 17, "sens": 17, "share": 17, "indic": [17, 24, 42], "qadd": 17, "quantizedadd": 17, "first": [17, 19, 28, 30, 33, 35], "disabl": [17, 25, 28, 32, 34, 36], "them": [17, 19, 28], "calibration_data_load": 17, "adaptiveavgpool1d": 17, "quantizedadaptiveavgpool1d": 17, "adaptiveavgpool2d": 17, "quantizedadaptiveavgpool2d": 17, "adaptiveavgpool3d": 17, "quantizedadaptiveavgpool3d": 17, "adaptivemaxpool1d": 17, "quantizedadaptivemaxpool1d": 17, "adaptivemaxpool2d": 17, "quantizedadaptivemaxpool2d": 17, "adaptivemaxpool3d": 17, "quantizedadaptivemaxpool3d": 17, "alphadropout": 17, "quantizedalphadropout": 17, "avgpool1d": 17, "quantizedavgpool1d": 17, "avgpool2d": 17, "quantizedavgpool2d": 17, "avgpool3d": 17, "quantizedavgpool3d": 17, "batchnorm1d": 17, "quantizedbatchnorm1d": 17, "batchnorm2d": [17, 19], "quantizedbatchnorm2d": 17, "batchnorm3d": 17, "quantizedbatchnorm3d": 17, "celu": 17, "quantizedcelu": 17, "channelshuffl": 17, "quantizedchannelshuffl": 17, "constantpad1d": 17, "quantizedconstantpad1d": 17, "constantpad2d": 17, "quantizedconstantpad2d": 17, "constantpad3d": 17, "quantizedconstantpad3d": 17, "conv1d": [17, 37], "quantizedconv1d": 17, "conv3d": 17, "quantizedconv3d": 17, "convtranspose1d": [17, 37], "quantizedconvtranspose1d": 17, "convtranspose2d": 17, "quantizedconvtranspose2d": 17, "convtranspose3d": 17, "quantizedconvtranspose3d": 17, "dropout": 17, "quantizeddropout": 17, "dropout2d": 17, "quantizeddropout2d": 17, "dropout3d": 17, "quantizeddropout3d": 17, "elu": 17, "quantizedelu": 17, "featurealphadropout": 17, "quantizedfeaturealphadropout": 17, "flatten": 17, "quantizedflatten": 17, "fold": [17, 20, 21, 22, 30, 31, 32, 37], "quantizedfold": 17, "fractionalmaxpool2d": 17, "quantizedfractionalmaxpool2d": 17, "fractionalmaxpool3d": 17, "quantizedfractionalmaxpool3d": 17, "gelu": 17, "quantizedgelu": 17, "glu": 17, "quantizedglu": 17, "groupnorm": 17, "quantizedgroupnorm": 17, "hardshrink": 17, "quantizedhardshrink": 17, "hardsigmoid": 17, "quantizedhardsigmoid": 17, "hardswish": 17, "quantizedhardswish": 17, "hardtanh": 17, "quantizedhardtanh": 17, "instancenorm1d": 17, "quantizedinstancenorm1d": 17, "instancenorm2d": 17, "quantizedinstancenorm2d": 17, "instancenorm3d": 17, "quantizedinstancenorm3d": 17, "lppool1d": 17, "quantizedlppool1d": 17, "lppool2d": 17, "quantizedlppool2d": 17, "layernorm": 17, "quantizedlayernorm": 17, "leakyrelu": 17, "quantizedleakyrelu": 17, "localresponsenorm": 17, "quantizedlocalresponsenorm": 17, "logsigmoid": 17, "quantizedlogsigmoid": 17, "logsoftmax": 17, "quantizedlogsoftmax": 17, "maxpool1d": 17, "quantizedmaxpool1d": 17, "maxpool2d": 17, "quantizedmaxpool2d": 17, "maxpool3d": 17, "quantizedmaxpool3d": 17, "maxunpool1d": 17, "quantizedmaxunpool1d": 17, "maxunpool2d": 17, "quantizedmaxunpool2d": 17, "maxunpool3d": 17, "quantizedmaxunpool3d": 17, "mish": 17, "quantizedmish": 17, "prelu": 17, "quantizedprelu": 17, "pixelshuffl": 17, "quantizedpixelshuffl": 17, "pixelunshuffl": 17, "quantizedpixelunshuffl": 17, "rrelu": 17, "quantizedrrelu": 17, "relu": [17, 19, 31, 34, 42], "quantizedrelu": [17, 19], "relu6": [17, 31], "quantizedrelu6": 17, "reflectionpad1d": 17, "quantizedreflectionpad1d": 17, "reflectionpad2d": 17, "quantizedreflectionpad2d": 17, "replicationpad1d": 17, "quantizedreplicationpad1d": 17, "replicationpad2d": 17, "quantizedreplicationpad2d": 17, "replicationpad3d": 17, "quantizedreplicationpad3d": 17, "selu": 17, "quantizedselu": 17, "silu": 17, "quantizedsilu": 17, "sigmoid": 17, "quantizedsigmoid": 17, "softmax2d": 17, "quantizedsoftmax2d": 17, "softmin": 17, "quantizedsoftmin": 17, "softplu": 17, "quantizedsoftplu": 17, "softshrink": 17, "quantizedsoftshrink": 17, "softsign": 17, "quantizedsoftsign": 17, "tanh": 17, "quantizedtanh": 17, "tanhshrink": 17, "quantizedtanhshrink": 17, "quantizedthreshold": 17, "unflatten": 17, "quantizedunflatten": 17, "unfold": 17, "quantizedunfold": 17, "upsampl": [17, 29], "quantizedupsampl": 17, "upsamplingbilinear2d": 17, "quantizedupsamplingbilinear2d": 17, "upsamplingnearest2d": 17, "quantizedupsamplingnearest2d": 17, "zeropad2d": 17, "quantizedzeropad2d": 17, "bceloss": 17, "quantizedbceloss": 17, "bcewithlogitsloss": 17, "quantizedbcewithlogitsloss": 17, "bilinear": [17, 29], "quantizedbilinear": 17, "ctcloss": 17, "quantizedctcloss": 17, "cosinesimilar": 17, "quantizedcosinesimilar": 17, "crossentropyloss": [17, 19], "quantizedcrossentropyloss": 17, "hingeembeddingloss": 17, "quantizedhingeembeddingloss": 17, "huberloss": 17, "quantizedhuberloss": 17, "kldivloss": 17, "quantizedkldivloss": 17, "l1loss": 17, "quantizedl1loss": 17, "mseloss": 17, "quantizedmseloss": 17, "multilabelmarginloss": 17, "quantizedmultilabelmarginloss": 17, "multilabelsoftmarginloss": 17, "quantizedmultilabelsoftmarginloss": 17, "multimarginloss": 17, "quantizedmultimarginloss": 17, "nllloss": 17, "quantizednllloss": 17, "nllloss2d": 17, "quantizednllloss2d": 17, "pairwisedist": 17, "quantizedpairwisedist": 17, "poissonnllloss": 17, "quantizedpoissonnllloss": 17, "smoothl1loss": 17, "quantizedsmoothl1loss": 17, "softmarginloss": 17, "quantizedsoftmarginloss": 17, "cosineembeddingloss": 17, "quantizedcosineembeddingloss": 17, "gaussiannllloss": 17, "quantizedgaussiannllloss": 17, "marginrankingloss": 17, "quantizedmarginrankingloss": 17, "tripletmarginloss": 17, "quantizedtripletmarginloss": 17, "tripletmarginwithdistanceloss": 17, "quantizedtripletmarginwithdistanceloss": 17, "embed": [17, 28, 35], "quantizedembed": 17, "embeddingbag": 17, "quantizedembeddingbag": 17, "gru": [17, 37], "quantizedgru": 17, "rnn": [17, 37], "quantizedrnn": 17, "grucel": 17, "quantizedgrucel": 17, "rnncell": 17, "quantizedrnncel": 17, "lstm": [17, 37], "quantizedlstm": 17, "lstmcell": 17, "quantizedlstmcel": 17, "cumsum": 17, "quantizedcumsum": 17, "sin": 17, "quantizedsin": 17, "co": 17, "quantizedco": 17, "rsqrt": 17, "quantizedrsqrt": 17, "reshap": 17, "quantizedreshap": 17, "matmul": [17, 37], "quantizedmatmul": 17, "subtract": 17, "quantizedsubtract": 17, "quantizeddivid": 17, "bmm": 17, "quantizedbmm": 17, "baddbmm": 17, "quantizedbaddbmm": 17, "addmm": 17, "quantizedaddmm": 17, "concat": [17, 37], "quantizedconcat": 17, "allow_overwit": 18, "get_encod": 18, "get_legacy_encod": 18, "register_quantization_paramet": 18, "set_legacy_encod": 18, "tutori": 19, "simpl": 19, "intend": 19, "It": [19, 22, 23, 25, 33, 42], "meant": 19, "demonstr": 19, "state": 19, "art": 19, "eval": [19, 25, 28, 39], "loop": [19, 35], "evalu": [19, 21, 25, 28, 30, 32, 33, 36, 39], "clearli": 19, "what": [19, 39], "happen": 19, "let": 19, "special": 19, "look": [19, 21], "torchvis": 19, "is_avail": 19, "els": [19, 31], "loader": [19, 20], "cifar10_train_data": 19, "dataset": [19, 30, 31, 36], "fashionmnist": 19, "tmp": 19, "cifar10": 19, "totensor": 19, "cifar10_test_data": 19, "train_load": 19, "batch_siz": 19, "shuffl": 19, "test_load": 19, "conv1": 19, "kernel_s": 19, "pad": 19, "stride": 19, "bn_1": 19, "bn_2": 19, "total": [19, 25, 36], "argmax": 19, "sum": 19, "few": [19, 24], "epoch": [19, 26, 28, 33], "establish": 19, "baselin": [19, 25, 28, 33], "send": 19, "loss_fn": 19, "adam": 19, "lr": 19, "1e": [19, 33], "batch_idx": 19, "enumer": 19, "backward": 19, "zero_grad": 19, "fp_accuraci": 19, "91": 19, "70999908447266": 19, "accur": 19, "coupl": 19, "care": [19, 28], "conform": 19, "guidelin": [19, 30, 33], "wherea": [19, 36], "incorrectli": 19, "ignor": 19, "previou": [19, 24, 35], "complet": [19, 22, 35], "redefin": 19, "thankfulli": 19, "model_prepar": 19, "incompat": 19, "fulli": [19, 27, 28, 41], "prepared_model": 19, "prepare_model": 19, "fp_accuracy_prepar": 19, "assert": 19, "2024": 19, "07": 19, "747": 19, "info": [19, 37], "806": 19, "modelprepar": 19, "ad": [19, 27, 34, 37], "node": [19, 33, 36], "module_relu": 19, "module_relu_1": 19, "module_softmax": 19, "graphmodul": 19, "ep": 19, "momentum": 19, "track_running_stat": 19, "12544": 19, "getattr_1": 19, "getitem": 19, "debug": [19, 35], "graph_modul": 19, "print_read": 19, "distinct": 19, "adjac": [19, 34], "whenev": 19, "unnecessari": [19, 42], "good": [19, 20, 28], "idea": 19, "batch_norm_fold": 19, "iter": [19, 20, 31], "fold_all_batch_norm": 19, "input_shap": 19, "ident": 19, "passthrough": 19, "previous": 19, "had": 19, "impact": [19, 25, 35], "readi": [19, 35], "e": [19, 22], "therefor": [19, 24, 31], "theoret": 19, "could": [19, 42], "practic": [19, 28], "usual": [19, 28, 33, 36], "500": [19, 20, 31, 32], "1000": [19, 20, 31, 32], "estim": [19, 30, 31], "idx": 19, "break": 19, "quantized_accuraci": 19, "1500015258789": 19, "noth": 19, "everi": [19, 25, 28, 33, 40], "discuss": [19, 24, 36], "advanc": 19, "re": [19, 30], "One": 19, "op": [19, 34, 36, 37], "repeat": [19, 23], "post_qat_accuraci": 19, "92": 19, "05333709716797": 19, "happi": 19, "export_path": 19, "model_nam": 19, "fashion_mnist_model": 19, "sent": 19, "nearest": 20, "illustr": [20, 23, 25, 30, 36, 38, 39, 41, 42], "figur": [20, 23, 25, 35, 38, 39, 41, 42], "unlabel": [20, 30, 32], "far": 20, "decid": [20, 39], "whether": [20, 25, 33], "closer": 20, "fp32": [20, 26, 31, 32, 33, 35, 36], "width": [20, 35, 36, 38, 41, 42], "freez": 20, "terminologi": 20, "abbrevi": 20, "bc": 20, "bnf": 20, "batch": [20, 30, 31, 32], "norm": [20, 30, 31, 32], "cle": [20, 21, 30, 35, 37], "cross": [20, 21, 29, 30, 32, 35, 40], "hbf": 20, "sequenc": [20, 21, 22, 29, 34], "help": [20, 25, 28, 30, 31, 32, 33, 35, 40], "might": [20, 32, 35], "speed": [20, 28, 31, 33, 37], "Not": [20, 25], "expos": [20, 32], "stabl": 20, "mani": [20, 24, 31], "often": [20, 21, 28, 33], "approxim": [20, 24, 31, 32], "16x": 20, "1024": [20, 29], "10000": 20, "caution": 20, "avoid": [20, 24], "beta": 20, "warm": 20, "period": 20, "kera": [20, 22, 26, 30, 31, 32, 34, 36, 37], "offer": 21, "suit": 21, "best": [21, 24, 28, 30, 36], "toler": [21, 24], "soon": 21, "reach": 21, "stop": 21, "try": [21, 23, 24, 28, 30, 35], "prone": 21, "consum": [21, 28], "prepar": [21, 30, 37], "check": [21, 30, 33, 35], "friendli": [21, 30, 31], "preprat": 21, "proce": 21, "three": [21, 24, 40], "batchnorm": [21, 31, 42], "effort": 21, "manner": 21, "fail": [21, 29, 30], "goal": 21, "small": [22, 26, 30], "preceed": 22, "learn": [22, 28, 30, 33, 36, 37], "pcq": [22, 32], "scenario": [22, 42], "decreas": 22, "main": [22, 34, 37, 40], "issu": [22, 26, 29, 35, 37, 39, 40], "depthwis": [22, 37], "oscil": 22, "quant": 22, "diagram": [22, 26, 36], "cp": [23, 24, 25, 42], "occurr": 23, "explain": [23, 28, 31, 36], "ratio": [23, 24], "magnitud": 23, "upstream": [23, 42], "gain": [23, 24, 28], "connect": [23, 27, 28, 41], "residu": 23, "sometim": [23, 28, 31, 32], "prevent": [23, 29], "regress": 23, "random": [23, 32], "against": 23, "outlin": 24, "svd": [24, 25, 27, 28, 37], "spatial": [24, 25, 27, 28, 37], "prune": [24, 25, 27, 28, 37, 42], "accumul": [24, 28], "mac": [24, 28, 38, 41], "reduct": [24, 30], "uncompress": 24, "algorithm": [24, 25, 28, 35, 42], "overal": [24, 25, 35], "latenc": 24, "bandwidth": 24, "vari": [24, 31, 40], "websit": 24, "At": [24, 39], "half": 24, "unknown": 24, "ssvd": 24, "f0": 24, "65": 24, "75": 24, "yield": [24, 35, 36], "pick": [24, 25], "2b": 24, "rel": [24, 35, 40], "sai": 24, "veri": [24, 28, 32, 40], "larg": [24, 33, 38, 41], "revisit": 24, "close": [24, 36], "resnet": 24, "50": 24, "assess": 25, "sensit": [25, 30, 32, 35, 36, 37], "find": [25, 30, 32, 33, 36], "maintain": [25, 28], "highest": 25, "dictionari": [25, 28, 34], "column": 25, "score": [25, 28, 39], "unmodifi": 25, "compris": 25, "candid": [25, 28], "omit": [25, 34], "monoton": 25, "fit": 25, "procedur": [25, 39], "curv": 25, "account": [25, 30, 33, 35], "constant": [25, 30], "interpol": 25, "solut": [25, 33, 35], "accept": [25, 31, 35], "suggest": [25, 28, 31], "vice": [25, 35, 36], "versa": [25, 35, 36], "fall": [25, 34], "drastic": 25, "softwar": 26, "framework": [26, 30, 34, 36], "meta": [26, 30], "checkpoint": [26, 30], "h5": [26, 30], "hardwar": [26, 30, 31, 36], "ptq": [26, 30, 32, 33], "redund": 26, "smaller": [26, 35, 38, 41], "limit": 27, "dilat": 27, "modules_to_ignor": 27, "depthwiseconv2d": 27, "last": 27, "librari": 28, "littl": 28, "variou": [28, 30, 35, 36, 37, 40], "singular": [28, 38, 41], "decomposit": [28, 38, 41], "guidebook": 28, "summari": 28, "phase": 28, "inspect": 28, "choic": [28, 36], "greedi": [28, 39], "decompos": [28, 38, 41], "fc": [28, 41], "ml": [28, 30, 31], "give": 28, "tri": [28, 30], "caus": [28, 29, 30, 34, 35], "sharp": 28, "rate": [28, 33], "decai": 28, "respons": 28, "Then": 28, "slow": 28, "someth": 28, "itself": [28, 36, 38], "searcher": 28, "Or": 28, "fewer": 28, "wors": 28, "strike": 28, "balanc": 28, "major": 28, "But": 28, "seem": [28, 30], "xiangyu": 28, "zhang": 28, "jianhua": 28, "zou": 28, "kaim": 28, "he": 28, "jian": 28, "sun": 28, "deep": 28, "classif": 28, "detect": 28, "transact": 28, "pattern": 28, "analysi": [28, 35], "intellig": 28, "vol": 28, "pp": 28, "1943": 28, "1955": 28, "oct": 28, "2016": 28, "yihui": 28, "confer": [28, 31], "vision": [28, 31], "iccv": [28, 31], "venic": 28, "2017": 28, "1398": 28, "1406": 28, "jaderberg": 28, "andrea": 28, "vedaldi": 28, "andrew": 28, "zisserman": 28, "british": 28, "jan": 28, "2014": 28, "andrei": 28, "kuzmin": 28, "marku": [28, 31], "nagel": [28, 31], "saurabh": 28, "pitr": 28, "sandeep": 28, "pendyam": 28, "tijmen": [28, 31], "blankevoort": [28, 31], "taxonomi": 28, "cross_layer_equ": 29, "equalize_model": 29, "potenti": [29, 39, 40], "workaround": 29, "applic": 29, "primit": 29, "sure": 29, "rewrit": 29, "slice": 29, "written": [29, 30], "statement": 29, "align_corn": 29, "deconvolut": 29, "dconvolut": 29, "deeplabv3": 29, "address": [29, 35, 39], "releas": 29, "howev": [30, 31], "briefli": 30, "move": 30, "retrain": 30, "becaus": 30, "pipelin": [30, 33, 35, 36], "suffici": [30, 32, 33, 36], "fast": 30, "easi": 30, "insert": [30, 36], "robust": 30, "longer": [30, 33], "_aimet": 30, "trainabl": 30, "bias": 30, "remain": [30, 31, 36], "reflect": [30, 36], "autoqu": [30, 33, 37], "integr": 30, "standalon": 30, "consecut": [30, 31], "bn": [30, 32, 37], "deprec": 30, "quantanalyz": [30, 37], "autom": 30, "understand": [30, 40], "prep": 30, "attempt": [30, 31], "accord": 30, "complainc": 30, "align": 30, "flow": [30, 35, 36], "put": 30, "retri": 30, "continu": [30, 31, 33, 35], "warn": 30, "hand": 30, "ref": 30, "satisfactori": [30, 35], "onto": 30, "item": 30, "pb": 30, "trial": [30, 35], "diagnost": 30, "becom": 31, "design": 31, "paper": 31, "2019": 31, "arxiv": 31, "ab": 31, "1906": 31, "04721": 31, "surround": 31, "highlight": [31, 39, 40], "big": 31, "discrep": 31, "off": 31, "wide": 31, "varianc": 31, "seen": [31, 32], "significantli": 31, "quantizaion": 31, "shown": [31, 32, 35, 42], "distribut": [31, 35, 36], "did": 31, "shift": 31, "empir": 31, "analyt": [31, 39], "extract": 31, "bottleneck": [31, 35], "hybrid": 31, "approach": [31, 36], "mart": 31, "van": 31, "baalen": 31, "seoul": 31, "octob": 31, "analys": 32, "area": 32, "hotspot": 32, "callback": [32, 36], "mse": [32, 36], "label": [32, 33], "metric": [32, 36], "relat": [32, 36], "doc": 32, "normal": 32, "benefici": 32, "situat": 32, "log": 32, "pinpoint": 32, "culprit": 32, "again": [32, 33], "per_layer_quant_en": 32, "per_layer_quant_dis": 32, "axi": 32, "directli": [32, 36], "min_max_rang": 32, "folder": 32, "enhanc": [32, 36], "delet": 32, "displai": [32, 39, 40], "activations_pdf": 32, "weights_pdf": 32, "squar": [32, 36], "monitor": 32, "contribut": [32, 35], "read": 32, "per_layer_mse_loss": 32, "presenc": 33, "hyperparamet": 33, "converg": 33, "hyper": 33, "schedul": 33, "fuse": [34, 36], "placement": 34, "config": [34, 37], "six": 34, "turn": 34, "op_typ": 34, "empti": 34, "is_output_quant": 34, "is_quant": 34, "strict_symmetr": 34, "unsigned_symmetr": 34, "outsid": 34, "strict": [34, 36], "unsign": [34, 36], "rather": 34, "throughout": [34, 40], "gemm": 34, "is_input_quant": 34, "keep": 34, "convent": 34, "supergroup": [34, 37], "made": 34, "op_list": 34, "member": 34, "sequenti": [34, 35], "branch": 34, "those": 34, "entri": 34, "string": 34, "model_input": 34, "model_output": 34, "insight": [35, 39, 40], "why": 35, "underperform": 35, "chart": 35, "confid": 35, "independ": 35, "kept": 35, "toward": 35, "uneven": 35, "global": 35, "restor": 35, "consid": [35, 38, 41], "rest": 35, "inner": 35, "token": 35, "bert": 35, "reveal": 35, "problemat": [35, 40], "problem": 35, "resort": 35, "revert": 35, "power": 35, "mitig": 36, "recogn": 36, "copi": 36, "ingest": 36, "feed": 36, "000": 36, "de": 36, "hook": 36, "intercept": 36, "four": 36, "textrm": 36, "dfrac": 36, "elimin": 36, "extrem": 36, "induc": 36, "signal": 36, "satur": 36, "erro": 36, "static": 36, "alongsid": 36, "just": [36, 42], "settabl": 36, "non": [36, 39], "intermedi": 36, "slim": 37, "backslash": 37, "io": 37, "user_guid": 37, "api_doc": 37, "quantizablemultiheadattent": 37, "kyuykim": 37, "multi": 37, "mangal": 37, "geunle": 37, "bug": 37, "correctli": 37, "klhsieh": 37, "akhobar": 37, "multiheadattent": 37, "ashvkuma": 37, "mha": 37, "pdf": 37, "abil": 37, "fp16": 37, "minor": 37, "stand": 37, "adaptiveround": 37, "recurr": 37, "\ud835\udc5a": [38, 41], "\ud835\udc5b": [38, 41], "\u210e": [38, 41], "\ud835\udc64": [38, 41], "height": [38, 41, 42], "\ud835\udc58": [38, 41], "rank": [38, 41], "degre": [38, 41], "augment": 39, "progress": [39, 40], "computation": [39, 40], "task": [39, 40], "arrang": 39, "websocket": 39, "listen": 39, "5006": 39, "compress_model": 39, "display_eval_scor": 39, "display_comp_ratio_plot": 39, "visualizecompress": 39, "lot": 40, "term": 41, "anoth": [41, 42], "lose": 42, "much": 42, "volum": 42, "hxwx8": 42, "hxwx5": 42, "preced": 42, "propag": 42, "That": 42, "downstream": 42, "denot": 42, "green": 42, "side": 42, "action": 42, "taken": 42, "pink": 42, "color": 42, "orang": 42, "Its": 42}, "objects": {"aimet_torch.gptvq.defs": [[15, 0, 1, "", "GPTVQParameters"]], "aimet_torch.gptvq.gptvq_weight.GPTVQ": [[15, 1, 1, "", "apply_gptvq"]], "aimet_torch.v2.nn": [[17, 0, 1, "", "QuantizationMixin"]], "aimet_torch.v2.nn.QuantizationMixin": [[17, 2, 1, "", "__quant_init__"], [17, 2, 1, "", "compute_encodings"], [17, 2, 1, "", "forward"], [6, 2, 1, "", "from_module"], [6, 2, 1, "", "get_default_kernel"], [6, 2, 1, "", "get_kernel"], [6, 2, 1, "", "implements"], [17, 3, 1, "", "input_quantizers"], [17, 3, 1, "", "output_quantizers"], [17, 3, 1, "", "param_quantizers"], [6, 2, 1, "", "set_default_kernel"], [6, 2, 1, "", "set_kernel"]], "aimet_torch.v2.quantization": [[7, 4, 0, "-", "affine"], [9, 4, 0, "-", "float"]], "aimet_torch.v2.quantization.affine": [[7, 0, 1, "", "Quantize"], [7, 0, 1, "", "QuantizeDequantize"], [7, 1, 1, "", "dequantize"], [7, 1, 1, "", "quantize"], [7, 1, 1, "", "quantize_dequantize"]], "aimet_torch.v2.quantization.affine.quantizer": [[18, 0, 1, "", "Quantize"], [18, 0, 1, "", "QuantizeDequantize"], [18, 0, 1, "", "QuantizerBase"]], "aimet_torch.v2.quantization.affine.quantizer.Quantize": [[18, 2, 1, "", "forward"]], "aimet_torch.v2.quantization.affine.quantizer.QuantizeDequantize": [[18, 2, 1, "", "forward"]], "aimet_torch.v2.quantization.affine.quantizer.QuantizerBase": [[18, 2, 1, "", "allow_overwrite"], [18, 2, 1, "", "compute_encodings"], [18, 2, 1, "", "get_encoding"], [18, 2, 1, "", "get_legacy_encodings"], [18, 2, 1, "", "is_initialized"], [18, 2, 1, "", "register_quantization_parameter"], [18, 2, 1, "", "set_legacy_encodings"]], "aimet_torch.v2.quantization.encoding_analyzer": [[13, 0, 1, "", "EncodingAnalyzer"], [13, 0, 1, "", "MinMaxEncodingAnalyzer"], [13, 0, 1, "", "PercentileEncodingAnalyzer"], [13, 0, 1, "", "SqnrEncodingAnalyzer"]], "aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer": [[13, 2, 1, "", "compute_encodings"], [13, 2, 1, "", "reset_stats"], [13, 2, 1, "", "update_stats"]], "aimet_torch.v2.quantization.float": [[9, 0, 1, "", "FloatQuantizeDequantize"], [9, 0, 1, "", "QuantizeDequantize"]], "aimet_torch.v2.quantization.tensor": [[10, 0, 1, "", "DequantizedTensor"], [10, 0, 1, "", "QuantizedTensor"]], "aimet_torch.v2.quantization.tensor.DequantizedTensor": [[10, 2, 1, "", "dequantize"], [10, 2, 1, "", "quantize"], [10, 2, 1, "", "quantized_repr"]], "aimet_torch.v2.quantization.tensor.QuantizedTensor": [[10, 2, 1, "", "dequantize"], [10, 2, 1, "", "quantize"], [10, 2, 1, "", "quantized_repr"]], "aimet_torch.v2.quantsim.config_utils": [[12, 1, 1, "", "set_activation_quantizers_to_float"], [12, 1, 1, "", "set_blockwise_quantization_for_weights"], [12, 1, 1, "", "set_grouped_blockwise_quantization_for_weights"]], "aimet_torch.v2.visualization_tools": [[11, 1, 1, "", "visualize_stats"]]}, "objtypes": {"0": "py:class", "1": "py:function", "2": "py:method", "3": "py:attribute", "4": "py:module"}, "objnames": {"0": ["py", "class", "Python class"], "1": ["py", "function", "Python function"], "2": ["py", "method", "Python method"], "3": ["py", "attribute", "Python attribute"], "4": ["py", "module", "Python module"]}, "titleterms": {"aimet": [2, 3, 4, 16, 20, 21, 22, 23, 24, 25, 27, 28, 30, 31, 32, 33, 35, 36, 37, 38, 39, 40, 41, 42], "instal": [2, 3, 4], "quick": 2, "releas": [2, 3, 4, 26, 37], "packag": [2, 3, 4], "system": 2, "requir": [2, 32], "advanc": 2, "instruct": 2, "docker": 3, "set": 3, "variant": [3, 13], "us": [3, 20, 28, 30], "prebuilt": 3, "imag": 3, "build": 3, "local": 3, "start": [3, 16, 39], "contain": 3, "from": [3, 4], "pypi": [3, 4], "environ": [3, 4], "setup": [3, 4], "prerequisit": [4, 19], "gpu": 4, "pytorch": [4, 16, 19, 29, 30, 40], "2": [4, 19, 37], "1": [4, 19, 37], "13": [4, 37], "onnx": 4, "tensorflow": [4, 40], "common": 4, "debian": 4, "torch": 4, "replac": 4, "pillow": 4, "simd": 4, "onnxruntim": 4, "post": [4, 14, 30, 31], "step": 4, "quantizationmixin": 6, "quantiz": [7, 9, 10, 12, 14, 17, 18, 19, 30, 31, 33, 34, 35, 36, 40], "affin": 7, "class": [7, 9, 10, 17], "function": 7, "floatquantizedequant": 8, "quantizedequant": 8, "float": [9, 19], "tensor": 10, "visual": [11, 39, 40], "tool": [11, 30], "blockwis": 12, "low": 12, "power": 12, "lpbq": 12, "top": [12, 15, 17, 18], "level": [12, 15, 17, 18], "api": [12, 15, 16, 17, 18, 20, 21, 22, 31, 32, 36], "export": [12, 19], "encod": [13, 17, 36], "analyz": 13, "train": [14, 19, 30, 31, 33], "gptvq": 15, "paramet": [15, 20, 36], "code": 15, "exampl": [15, 16], "ai": [16, 26], "model": [16, 19, 26, 28, 29, 30], "effici": [16, 26], "toolkit": [16, 26], "document": 16, "get": 16, "featur": [16, 24, 26, 30], "descript": [16, 32], "modul": 17, "configur": [17, 34, 36], "comput": 17, "quickstart": 19, "guid": [19, 26], "overal": 19, "flow": [19, 31], "prepar": 19, "point": 19, "batchnorm": 19, "fold": 19, "fine": [19, 28], "tune": [19, 28], "awar": [19, 33], "quantsim": [19, 36], "adaround": 20, "case": [20, 28, 30], "hyper": 20, "guidelin": [20, 29], "autoqu": 21, "overview": [21, 22, 25, 26, 28, 31, 32, 33, 34, 36, 39, 40, 42], "workflow": [21, 22, 30, 33, 36], "batch": 22, "norm": 22, "re": 22, "estim": 22, "bn": 22, "channel": 23, "prune": 23, "procedur": 23, "select": [23, 25, 28], "winnow": [23, 42], "weight": [23, 41], "reconstruct": 23, "compress": [24, 25, 28, 39], "guidebook": 24, "greedi": 25, "ratio": [25, 28, 39], "how": [25, 42], "work": [25, 42], "per": [25, 28], "layer": [25, 28, 31], "explor": 25, "user": [26, 31], "more": 26, "inform": 26, "toc": 26, "tree": 26, "known": 27, "issu": 27, "option": 28, "techniqu": [28, 31], "rank": 28, "round": 28, "note": [28, 37], "faq": [28, 31], "refer": [28, 31], "debug": 30, "analysi": [30, 32], "cross": 31, "equal": 31, "quantanalyz": 32, "detail": 32, "qat": 33, "mode": 33, "recommend": 33, "simul": [34, 36], "file": 34, "structur": 34, "modifi": 34, "section": 34, "diagnost": 35, "nois": 36, "determin": 36, "scheme": 36, "oper": 36, "22": 37, "0": 37, "21": 37, "20": 37, "19": 37, "py37": 37, "18": 37, "17": 37, "16": 37, "14": 37, "spatial": 38, "svd": [38, 41], "design": 39, "bokeh": 39, "server": 39, "session": 39}, "envversion": {"sphinx.domains.c": 2, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 8, "sphinx.domains.index": 1, "sphinx.domains.javascript": 2, "sphinx.domains.math": 2, "sphinx.domains.python": 3, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "nbsphinx": 4, "sphinx.ext.intersphinx": 1, "sphinx.ext.viewcode": 1, "sphinx": 57}, "alltitles": {"AIMET Installation": [[2, "aimet-installation"]], "Quick Install": [[2, "quick-install"]], "Release Packages": [[2, "release-packages"]], "System Requirements": [[2, "system-requirements"]], "Advanced Installation Instructions": [[2, "advanced-installation-instructions"]], "AIMET Installation in Docker": [[3, "aimet-installation-in-docker"]], "Set variant": [[3, "set-variant"]], "Use prebuilt docker image": [[3, "use-prebuilt-docker-image"]], "Build docker image locally": [[3, "build-docker-image-locally"]], "Start docker container": [[3, "start-docker-container"]], "Install AIMET packages": [[3, "install-aimet-packages"], [4, "install-aimet-packages"]], "From PyPI": [[3, "from-pypi"], [4, "from-pypi"]], "From Release Package": [[3, "from-release-package"], [4, "from-release-package"]], "Environment setup": [[3, "environment-setup"], [4, "environment-setup"]], "AIMET Installation and Setup": [[4, "aimet-installation-and-setup"]], "Install prerequisite packages": [[4, "install-prerequisite-packages"]], "Install GPU packages": [[4, "install-gpu-packages"]], "Install GPU packages for PyTorch 2.1 or PyTorch 1.13 or ONNX or TensorFlow": [[4, "install-gpu-packages-for-pytorch-2-1-or-pytorch-1-13-or-onnx-or-tensorflow"]], "Install common debian packages": [[4, "install-common-debian-packages"]], "Install tensorflow GPU debian packages": [[4, "install-tensorflow-gpu-debian-packages"]], "Install torch GPU debian packages": [[4, "install-torch-gpu-debian-packages"]], "Install ONNX GPU debian packages": [[4, "install-onnx-gpu-debian-packages"]], "Replace Pillow with Pillow-SIMD": [[4, "replace-pillow-with-pillow-simd"]], "Replace onnxruntime with onnxruntime-gpu": [[4, "replace-onnxruntime-with-onnxruntime-gpu"]], "Post installation steps": [[4, "post-installation-steps"]], "QuantizationMixin": [[6, "quantizationmixin"]], "quantization.affine": [[7, "module-aimet_torch.v2.quantization.affine"]], "Classes": [[7, "classes"], [9, "classes"], [10, "classes"]], "Functions": [[7, "functions"]], "FloatQuantizeDequantize": [[8, "floatquantizedequantize"]], "QuantizeDequantize": [[8, "quantizedequantize"]], "quantization.float": [[9, "module-aimet_torch.v2.quantization.float"]], "quantization.tensor": [[10, "quantization-tensor"]], "Visualization Tools": [[11, "visualization-tools"]], "Blockwise Quantization": [[12, "blockwise-quantization"]], "Low Power Blockwise Quantization (LPBQ)": [[12, "low-power-blockwise-quantization-lpbq"]], "Top Level API": [[12, "top-level-api"], [15, "top-level-api"]], "Export": [[12, "export"]], "Encoding Analyzers": [[13, "encoding-analyzers"]], "Variants": [[13, "variants"]], "Post-Training Quantization": [[14, "post-training-quantization"], [30, "post-training-quantization"]], "GPTVQ": [[15, "gptvq"]], "GPTVQ Parameters": [[15, "gptvq-parameters"]], "Code Example": [[15, "code-example"]], "AIMET: AI Model Efficiency Toolkit Documentation": [[16, "aimet-ai-model-efficiency-toolkit-documentation"]], "Getting Started": [[16, "getting-started"]], "Examples": [[16, null]], "Feature Descriptions": [[16, null]], "AIMET PyTorch API": [[16, null]], "Quantized Modules": [[17, "quantized-modules"]], "Top-level API": [[17, "top-level-api"], [18, "top-level-api"]], "Configuration": [[17, "configuration"]], "Computing Encodings": [[17, "computing-encodings"]], "Quantized Module Classes": [[17, "quantized-module-classes"]], "Quantizers": [[18, "quantizers"]], "Quickstart Guide": [[19, "quickstart-guide"]], "Overall flow": [[19, "overall-flow"]], "PyTorch prerequisites": [[19, "pytorch-prerequisites"]], "Prepare the floating point model for quantization": [[19, "prepare-the-floating-point-model-for-quantization"]], "1) Model preparation": [[19, "model-preparation"]], "2) BatchNorm fold": [[19, "batchnorm-fold"]], "Quantize the model": [[19, "quantize-the-model"]], "Fine-tune the model with quantization aware training": [[19, "fine-tune-the-model-with-quantization-aware-training"]], "Export the quantsim model": [[19, "export-the-quantsim-model"]], "AIMET AdaRound": [[20, "aimet-adaround"]], "AdaRound use cases": [[20, "adaround-use-cases"]], "AdaRound hyper parameters guidelines": [[20, "adaround-hyper-parameters-guidelines"]], "AdaRound API": [[20, "adaround-api"]], "AIMET AutoQuant": [[21, "aimet-autoquant"]], "Overview": [[21, "overview"], [22, "overview"], [25, "overview"], [26, "overview"], [28, "overview"], [31, "overview"], [32, "overview"], [33, "overview"], [34, "overview"], [36, "overview"], [39, "overview"], [40, "overview"], [42, "overview"]], "Workflow": [[21, "workflow"], [22, "workflow"]], "AutoQuant API": [[21, "autoquant-api"]], "AIMET Batch Norm Re-estimation": [[22, "aimet-batch-norm-re-estimation"]], "BN Re-estimation API": [[22, "bn-re-estimation-api"]], "AIMET channel pruning": [[23, "aimet-channel-pruning"]], "Procedure": [[23, "procedure"]], "Channel selection": [[23, "channel-selection"]], "Winnowing": [[23, "winnowing"]], "Weight reconstruction": [[23, "weight-reconstruction"]], "AIMET Compression Features Guidebook": [[24, "aimet-compression-features-guidebook"]], "AIMET greedy compression ratio selection": [[25, "aimet-greedy-compression-ratio-selection"]], "How it works": [[25, "how-it-works"]], "Per-layer exploration": [[25, "per-layer-exploration"]], "Compression ratio selection": [[25, "compression-ratio-selection"], [28, "compression-ratio-selection"]], "AI Model Efficiency Toolkit User Guide": [[26, "ai-model-efficiency-toolkit-user-guide"]], "Features": [[26, "features"]], "More Information": [[26, "more-information"]], "Release Information": [[26, "release-information"]], "toc tree": [[26, "toc-tree"]], "AIMET Known Issues": [[27, "aimet-known-issues"]], "AIMET model compression": [[28, "aimet-model-compression"]], "Use Case": [[28, "use-case"]], "Model compression": [[28, "model-compression"]], "Optional techniques": [[28, "optional-techniques"]], "Rank Rounding": [[28, "rank-rounding"]], "Per-layer fine-tuning": [[28, "per-layer-fine-tuning"]], "NOTE": [[28, null]], "FAQs": [[28, "faqs"], [31, "faqs"]], "References": [[28, "references"], [31, "references"]], "Model Guidelines for PyTorch": [[29, "model-guidelines-for-pytorch"]], "AIMET model quantization": [[30, "aimet-model-quantization"]], "Use cases": [[30, "use-cases"]], "AIMET quantization features": [[30, "aimet-quantization-features"]], "Debugging and Analysis Tools": [[30, "debugging-and-analysis-tools"]], "AIMET quantization workflow": [[30, "aimet-quantization-workflow"]], "PyTorch": [[30, "pytorch"], [40, "pytorch"]], "Debugging": [[30, "debugging"]], "AIMET post-training quantization techniques": [[31, "aimet-post-training-quantization-techniques"]], "User Flow": [[31, "user-flow"]], "Cross-Layer Equalization API": [[31, "cross-layer-equalization-api"]], "AIMET QuantAnalyzer": [[32, "aimet-quantanalyzer"]], "Requirements": [[32, "requirements"]], "Detailed analysis descriptions": [[32, "detailed-analysis-descriptions"]], "QuantAnalyzer API": [[32, "quantanalyzer-api"]], "AIMET quantization aware training": [[33, "aimet-quantization-aware-training"]], "QAT workflow": [[33, "qat-workflow"]], "QAT modes": [[33, "qat-modes"]], "Recommendations for quantization-aware training": [[33, "recommendations-for-quantization-aware-training"]], "Quantization simulation configuration": [[34, "quantization-simulation-configuration"]], "Configuration file structure": [[34, "configuration-file-structure"]], "Modifying configuration file sections": [[34, "modifying-configuration-file-sections"]], "AIMET quantization diagnostics": [[35, "aimet-quantization-diagnostics"]], "AIMET quantization simulation": [[36, "aimet-quantization-simulation"]], "QuantSim workflow": [[36, "quantsim-workflow"]], "Simulating quantization noise": [[36, "simulating-quantization-noise"]], "Determining quantization parameters (encodings)": [[36, "determining-quantization-parameters-encodings"]], "Quantization schemes": [[36, "quantization-schemes"]], "Configuring quantization simulation operations": [[36, "configuring-quantization-simulation-operations"]], "Quantization Simulation APIs": [[36, "quantization-simulation-apis"]], "AIMET Release Notes": [[37, "aimet-release-notes"]], "1.22.2": [[37, "id1"]], "1.22.1": [[37, "id2"]], "1.22.0": [[37, "id3"]], "1.21.0": [[37, "id4"]], "1.20.0": [[37, "id5"]], "1.19.1.py37": [[37, "py37"]], "1.19.1": [[37, "id6"]], "1.18.0.py37": [[37, "id7"]], "1.18.0": [[37, "id8"]], "1.17.0.py37": [[37, "id9"]], "1.17.0": [[37, "id10"]], "1.16.2.py37": [[37, "id11"]], "1.16.2": [[37, "id12"]], "1.16.1.py37": [[37, "id13"]], "1.16.1": [[37, "id14"]], "1.16.0": [[37, "id15"]], "1.14.0": [[37, "id16"]], "1.13.0": [[37, "id17"]], "AIMET spatial SVD": [[38, "aimet-spatial-svd"]], "AIMET visualization": [[39, "aimet-visualization"]], "Design": [[39, "design"]], "Compression": [[39, "compression"]], "Starting a Bokeh server session": [[39, "starting-a-bokeh-server-session"]], "Visualizing compression ratios": [[39, "visualizing-compression-ratios"]], "AIMET visualization for quantization": [[40, "aimet-visualization-for-quantization"]], "Quantization": [[40, "quantization"]], "TensorFlow": [[40, "tensorflow"]], "AIMET weight SVD": [[41, "aimet-weight-svd"]], "AIMET winnowing": [[42, "aimet-winnowing"]], "Winnowing overview": [[42, "winnowing-overview"]], "How winnowing works": [[42, "how-winnowing-works"]]}, "indexentries": {"quantizationmixin (class in aimet_torch.v2.nn)": [[6, "aimet_torch.v2.nn.QuantizationMixin"], [17, "aimet_torch.v2.nn.QuantizationMixin"]], "__quant_init__() (aimet_torch.v2.nn.quantizationmixin method)": [[6, "aimet_torch.v2.nn.QuantizationMixin.__quant_init__"], [17, "aimet_torch.v2.nn.QuantizationMixin.__quant_init__"]], "compute_encodings() (aimet_torch.v2.nn.quantizationmixin method)": [[6, "aimet_torch.v2.nn.QuantizationMixin.compute_encodings"], [17, "aimet_torch.v2.nn.QuantizationMixin.compute_encodings"]], "forward() (aimet_torch.v2.nn.quantizationmixin method)": [[6, "aimet_torch.v2.nn.QuantizationMixin.forward"], [17, "aimet_torch.v2.nn.QuantizationMixin.forward"]], "from_module() (aimet_torch.v2.nn.quantizationmixin class method)": [[6, "aimet_torch.v2.nn.QuantizationMixin.from_module"]], "get_default_kernel() (aimet_torch.v2.nn.quantizationmixin class method)": [[6, "aimet_torch.v2.nn.QuantizationMixin.get_default_kernel"]], "get_kernel() (aimet_torch.v2.nn.quantizationmixin method)": [[6, "aimet_torch.v2.nn.QuantizationMixin.get_kernel"]], "implements() (aimet_torch.v2.nn.quantizationmixin class method)": [[6, "aimet_torch.v2.nn.QuantizationMixin.implements"]], "input_quantizers (aimet_torch.v2.nn.quantizationmixin attribute)": [[6, "aimet_torch.v2.nn.QuantizationMixin.input_quantizers"], [17, "aimet_torch.v2.nn.QuantizationMixin.input_quantizers"]], "output_quantizers (aimet_torch.v2.nn.quantizationmixin attribute)": [[6, "aimet_torch.v2.nn.QuantizationMixin.output_quantizers"], [17, "aimet_torch.v2.nn.QuantizationMixin.output_quantizers"]], "param_quantizers (aimet_torch.v2.nn.quantizationmixin attribute)": [[6, "aimet_torch.v2.nn.QuantizationMixin.param_quantizers"], [17, "aimet_torch.v2.nn.QuantizationMixin.param_quantizers"]], "set_default_kernel() (aimet_torch.v2.nn.quantizationmixin class method)": [[6, "aimet_torch.v2.nn.QuantizationMixin.set_default_kernel"]], "set_kernel() (aimet_torch.v2.nn.quantizationmixin method)": [[6, "aimet_torch.v2.nn.QuantizationMixin.set_kernel"]], "quantize (class in aimet_torch.v2.quantization.affine)": [[7, "aimet_torch.v2.quantization.affine.Quantize"]], "quantizedequantize (class in aimet_torch.v2.quantization.affine)": [[7, "aimet_torch.v2.quantization.affine.QuantizeDequantize"]], "aimet_torch.v2.quantization.affine": [[7, "module-aimet_torch.v2.quantization.affine"]], "dequantize() (in module aimet_torch.v2.quantization.affine)": [[7, "aimet_torch.v2.quantization.affine.dequantize"]], "module": [[7, "module-aimet_torch.v2.quantization.affine"], [9, "module-aimet_torch.v2.quantization.float"]], "quantize() (in module aimet_torch.v2.quantization.affine)": [[7, "aimet_torch.v2.quantization.affine.quantize"]], "quantize_dequantize() (in module aimet_torch.v2.quantization.affine)": [[7, "aimet_torch.v2.quantization.affine.quantize_dequantize"]], "floatquantizedequantize (class in aimet_torch.v2.quantization.float)": [[8, "aimet_torch.v2.quantization.float.FloatQuantizeDequantize"], [9, "aimet_torch.v2.quantization.float.FloatQuantizeDequantize"]], "quantizedequantize (class in aimet_torch.v2.quantization.float)": [[8, "aimet_torch.v2.quantization.float.QuantizeDequantize"], [9, "aimet_torch.v2.quantization.float.QuantizeDequantize"]], "aimet_torch.v2.quantization.float": [[9, "module-aimet_torch.v2.quantization.float"]], "dequantizedtensor (class in aimet_torch.v2.quantization.tensor)": [[10, "aimet_torch.v2.quantization.tensor.DequantizedTensor"]], "quantizedtensor (class in aimet_torch.v2.quantization.tensor)": [[10, "aimet_torch.v2.quantization.tensor.QuantizedTensor"]], "dequantize() (aimet_torch.v2.quantization.tensor.dequantizedtensor method)": [[10, "aimet_torch.v2.quantization.tensor.DequantizedTensor.dequantize"]], "dequantize() (aimet_torch.v2.quantization.tensor.quantizedtensor method)": [[10, "aimet_torch.v2.quantization.tensor.QuantizedTensor.dequantize"]], "quantize() (aimet_torch.v2.quantization.tensor.dequantizedtensor method)": [[10, "aimet_torch.v2.quantization.tensor.DequantizedTensor.quantize"]], "quantize() (aimet_torch.v2.quantization.tensor.quantizedtensor method)": [[10, "aimet_torch.v2.quantization.tensor.QuantizedTensor.quantize"]], "quantized_repr() (aimet_torch.v2.quantization.tensor.dequantizedtensor method)": [[10, "aimet_torch.v2.quantization.tensor.DequantizedTensor.quantized_repr"]], "quantized_repr() (aimet_torch.v2.quantization.tensor.quantizedtensor method)": [[10, "aimet_torch.v2.quantization.tensor.QuantizedTensor.quantized_repr"]], "visualize_stats() (in module aimet_torch.v2.visualization_tools)": [[11, "aimet_torch.v2.visualization_tools.visualize_stats"]], "set_activation_quantizers_to_float() (in module aimet_torch.v2.quantsim.config_utils)": [[12, "aimet_torch.v2.quantsim.config_utils.set_activation_quantizers_to_float"]], "set_blockwise_quantization_for_weights() (in module aimet_torch.v2.quantsim.config_utils)": [[12, "aimet_torch.v2.quantsim.config_utils.set_blockwise_quantization_for_weights"]], "set_grouped_blockwise_quantization_for_weights() (in module aimet_torch.v2.quantsim.config_utils)": [[12, "aimet_torch.v2.quantsim.config_utils.set_grouped_blockwise_quantization_for_weights"]], "encodinganalyzer (class in aimet_torch.v2.quantization.encoding_analyzer)": [[13, "aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer"]], "minmaxencodinganalyzer (class in aimet_torch.v2.quantization.encoding_analyzer)": [[13, "aimet_torch.v2.quantization.encoding_analyzer.MinMaxEncodingAnalyzer"]], "percentileencodinganalyzer (class in aimet_torch.v2.quantization.encoding_analyzer)": [[13, "aimet_torch.v2.quantization.encoding_analyzer.PercentileEncodingAnalyzer"]], "sqnrencodinganalyzer (class in aimet_torch.v2.quantization.encoding_analyzer)": [[13, "aimet_torch.v2.quantization.encoding_analyzer.SqnrEncodingAnalyzer"]], "compute_encodings() (aimet_torch.v2.quantization.encoding_analyzer.encodinganalyzer method)": [[13, "aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.compute_encodings"]], "reset_stats() (aimet_torch.v2.quantization.encoding_analyzer.encodinganalyzer method)": [[13, "aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.reset_stats"]], "update_stats() (aimet_torch.v2.quantization.encoding_analyzer.encodinganalyzer method)": [[13, "aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.update_stats"]], "gptvqparameters (class in aimet_torch.gptvq.defs)": [[15, "aimet_torch.gptvq.defs.GPTVQParameters"]], "apply_gptvq() (in module aimet_torch.gptvq.gptvq_weight.gptvq)": [[15, "aimet_torch.gptvq.gptvq_weight.GPTVQ.apply_gptvq"]], "quantize (class in aimet_torch.v2.quantization.affine.quantizer)": [[18, "aimet_torch.v2.quantization.affine.quantizer.Quantize"]], "quantizedequantize (class in aimet_torch.v2.quantization.affine.quantizer)": [[18, "aimet_torch.v2.quantization.affine.quantizer.QuantizeDequantize"]], "quantizerbase (class in aimet_torch.v2.quantization.affine.quantizer)": [[18, "aimet_torch.v2.quantization.affine.quantizer.QuantizerBase"]], "allow_overwrite() (aimet_torch.v2.quantization.affine.quantizer.quantizerbase method)": [[18, "aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.allow_overwrite"]], "compute_encodings() (aimet_torch.v2.quantization.affine.quantizer.quantizerbase method)": [[18, "aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.compute_encodings"]], "forward() (aimet_torch.v2.quantization.affine.quantizer.quantize method)": [[18, "aimet_torch.v2.quantization.affine.quantizer.Quantize.forward"]], "forward() (aimet_torch.v2.quantization.affine.quantizer.quantizedequantize method)": [[18, "aimet_torch.v2.quantization.affine.quantizer.QuantizeDequantize.forward"]], "get_encoding() (aimet_torch.v2.quantization.affine.quantizer.quantizerbase method)": [[18, "aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.get_encoding"]], "get_legacy_encodings() (aimet_torch.v2.quantization.affine.quantizer.quantizerbase method)": [[18, "aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.get_legacy_encodings"]], "is_initialized() (aimet_torch.v2.quantization.affine.quantizer.quantizerbase method)": [[18, "aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.is_initialized"]], "register_quantization_parameter() (aimet_torch.v2.quantization.affine.quantizer.quantizerbase method)": [[18, "aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.register_quantization_parameter"]], "set_legacy_encodings() (aimet_torch.v2.quantization.affine.quantizer.quantizerbase method)": [[18, "aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.set_legacy_encodings"]]}})
\ No newline at end of file
+Search.setIndex({"docnames": ["_templates/autosummary/class", "_templates/autosummary/function", "install/index", "install/install_docker", "install/install_host", "toplevelhidden", "torch_docs/api/nn.quantization_mixin", "torch_docs/api/quantization/affine/index", "torch_docs/api/quantization/float/FloatQuantizeDequantize", "torch_docs/api/quantization/float/index", "torch_docs/api/quantization/tensor", "torch_docs/api/visualization_tools", "torch_docs/blockwise_quantization", "torch_docs/encoding_analyzer", "torch_docs/examples/ptq", "torch_docs/gptvq", "torch_docs/index", "torch_docs/quantized_modules", "torch_docs/quantizer", "torch_docs/tutorials/quickstart_guide", "user_guide/adaround", "user_guide/auto_quant", "user_guide/bn_reestimation", "user_guide/channel_pruning", "user_guide/compression_feature_guidebook", "user_guide/greedy_compression_ratio_selection", "user_guide/index", "user_guide/known_issues", "user_guide/model_compression", "user_guide/model_guidelines", "user_guide/model_quantization", "user_guide/post_training_quant_techniques", "user_guide/quant_analyzer", "user_guide/quantization_aware_training", "user_guide/quantization_configuration", "user_guide/quantization_feature_guidebook", "user_guide/quantization_sim", "user_guide/release_notes", "user_guide/spatial_svd", "user_guide/visualization_compression", "user_guide/visualization_quant", "user_guide/weight_svd", "user_guide/winnowing"], "filenames": ["_templates/autosummary/class.rst", "_templates/autosummary/function.rst", "install/index.rst", "install/install_docker.rst", "install/install_host.rst", "toplevelhidden.rst", "torch_docs/api/nn.quantization_mixin.rst", "torch_docs/api/quantization/affine/index.rst", "torch_docs/api/quantization/float/FloatQuantizeDequantize.rst", "torch_docs/api/quantization/float/index.rst", "torch_docs/api/quantization/tensor.rst", "torch_docs/api/visualization_tools.rst", "torch_docs/blockwise_quantization.rst", "torch_docs/encoding_analyzer.rst", "torch_docs/examples/ptq.rst", "torch_docs/gptvq.rst", "torch_docs/index.rst", "torch_docs/quantized_modules.rst", "torch_docs/quantizer.rst", "torch_docs/tutorials/quickstart_guide.rst", "user_guide/adaround.rst", "user_guide/auto_quant.rst", "user_guide/bn_reestimation.rst", "user_guide/channel_pruning.rst", "user_guide/compression_feature_guidebook.rst", "user_guide/greedy_compression_ratio_selection.rst", "user_guide/index.rst", "user_guide/known_issues.rst", "user_guide/model_compression.rst", "user_guide/model_guidelines.rst", "user_guide/model_quantization.rst", "user_guide/post_training_quant_techniques.rst", "user_guide/quant_analyzer.rst", "user_guide/quantization_aware_training.rst", "user_guide/quantization_configuration.rst", "user_guide/quantization_feature_guidebook.rst", "user_guide/quantization_sim.rst", "user_guide/release_notes.rst", "user_guide/spatial_svd.rst", "user_guide/visualization_compression.rst", "user_guide/visualization_quant.rst", "user_guide/weight_svd.rst", "user_guide/winnowing.rst"], "titles": ["&lt;no title&gt;", "&lt;no title&gt;", "AIMET Installation", "AIMET Installation in Docker", "AIMET Installation and Setup", "&lt;no title&gt;", "QuantizationMixin", "quantization.affine", "FloatQuantizeDequantize", "quantization.float", "quantization.tensor", "Visualization Tools", "Blockwise Quantization", "Encoding Analyzers", "Post-Training Quantization", "GPTVQ", "AIMET: AI Model Efficiency Toolkit Documentation", "Quantized Modules", "Quantizers", "Quickstart Guide", "AIMET AdaRound", "AIMET AutoQuant", "AIMET Batch Norm Re-estimation", "AIMET channel pruning", "AIMET Compression Features Guidebook", "AIMET greedy compression ratio selection", "AI Model Efficiency Toolkit User Guide", "AIMET Known Issues", "AIMET model compression", "Model Guidelines for PyTorch", "AIMET model quantization", "AIMET post-training quantization techniques", "AIMET QuantAnalyzer", "AIMET quantization aware training", "Quantization simulation configuration", "AIMET quantization diagnostics", "AIMET quantization simulation", "AIMET Release Notes", "AIMET spatial SVD", "AIMET visualization", "AIMET visualization for quantization", "AIMET weight SVD", "AIMET winnowing"], "terms": {"name": [0, 1, 3, 4, 6, 11, 15, 17, 18, 31, 36, 37, 39], "escap": [0, 1], "underlin": [0, 1], "qualcomm": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42], "innov": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42], "center": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42], "inc": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42], "ai": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 17, 18, 19, 20, 21, 22, 23, 24, 25, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42], "model": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 17, 18, 20, 21, 22, 23, 24, 25, 27, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42], "effici": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 17, 18, 19, 20, 21, 22, 23, 24, 25, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42], "toolkit": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 17, 18, 19, 20, 21, 22, 23, 24, 25, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42], "aimet_common": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42], "quantsim_config": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42], "default_config": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42], "json": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42], "1": [0, 1, 2, 3, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 38, 39, 40, 41, 42], "35": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42], "The": [2, 3, 4, 6, 7, 8, 9, 10, 11, 12, 13, 15, 16, 17, 19, 20, 21, 22, 23, 24, 25, 26, 28, 29, 30, 31, 32, 33, 34, 35, 36, 38, 39, 40, 41, 42], "pytorch": [2, 3, 6, 15, 17, 20, 21, 22, 26, 31, 32, 34, 36, 37], "gpu": [2, 3, 30, 37], "pypi": 2, "ar": [2, 3, 4, 6, 7, 8, 9, 12, 13, 15, 17, 18, 19, 20, 21, 22, 23, 24, 25, 28, 29, 30, 31, 32, 33, 34, 35, 36, 39, 40, 42], "avail": [2, 19, 29, 32, 34, 35], "environ": 2, "meet": [2, 21, 24, 25], "follow": [2, 3, 4, 6, 12, 15, 17, 20, 22, 23, 24, 25, 26, 28, 29, 30, 32, 33, 34, 35, 36, 38, 41, 42], "64": [2, 7, 12, 13, 18, 20], "bit": [2, 8, 9, 12, 19, 20, 22, 30, 35, 36, 37], "intel": 2, "x86": 2, "compat": [2, 12, 19], "processor": 2, "linux": [2, 4], "ubuntu": [2, 4], "22": [2, 4, 13, 19], "04": [2, 4], "lt": [2, 4], "python": [2, 3, 4], "3": [2, 7, 10, 12, 13, 19, 24, 30, 33, 35], "10": [2, 3, 4, 6, 7, 10, 12, 13, 17, 18, 19, 25, 28, 33], "20": [2, 20, 33], "8": [2, 4, 6, 7, 8, 9, 10, 12, 13, 15, 17, 18, 19, 30, 35, 42], "cuda": [2, 3, 4, 19], "12": [2, 3, 4, 7, 12, 13], "0": [2, 3, 4, 6, 7, 8, 9, 10, 12, 13, 15, 17, 18, 19, 20, 24, 25, 29, 34], "torch": [2, 3, 6, 7, 8, 9, 10, 12, 13, 15, 16, 17, 18, 19, 29, 37], "2": [2, 3, 6, 7, 8, 9, 10, 12, 13, 15, 18, 20, 24, 25, 30, 35, 36], "pip": [2, 3, 4, 16, 39], "apt": [2, 3, 4, 16], "get": [2, 3, 4, 15, 28, 40], "liblapack": [2, 3, 4, 16], "libpython3": 2, "dev": [2, 3, 4], "python3": [2, 3, 4, 16], "m": [2, 3, 4, 16], "For": [2, 3, 4, 6, 12, 15, 16, 17, 19, 20, 23, 24, 25, 26, 27, 28, 30, 32, 34, 36], "other": [2, 12, 15, 25, 27, 30, 32, 35, 36, 37], "variant": [2, 4, 20, 21, 22, 30, 31, 32, 36], "latest": [2, 3], "version": [2, 3, 4, 6, 11, 12, 15, 17, 19, 26, 33], "from": [2, 6, 7, 8, 9, 10, 12, 13, 15, 17, 18, 19, 20, 23, 24, 25, 26, 28, 29, 30, 31, 32, 33, 34, 35, 36, 42], "whl": [2, 3, 4], "file": [2, 3, 4, 12, 15, 19, 30, 32, 33, 36, 37, 40], "host": [2, 3, 4, 37, 39], "http": [2, 3, 4, 31, 37, 39], "github": [2, 3, 4, 37], "com": [2, 3, 4, 37], "quic": [2, 3, 4, 37], "onli": [2, 3, 4, 7, 10, 11, 12, 17, 19, 22, 27, 28, 30, 32, 33, 34, 37, 39, 42], "thi": [2, 3, 4, 6, 7, 8, 9, 10, 11, 12, 13, 15, 17, 18, 19, 20, 21, 23, 24, 25, 26, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 39, 42], "time": [2, 12, 15, 19, 21, 28, 29, 33, 34, 39], "prerequisit": [2, 39], "pre": [2, 3, 4, 23, 26, 31, 32], "requisit": [2, 4], "appli": [2, 6, 7, 12, 15, 17, 18, 19, 20, 21, 22, 28, 30, 31, 33, 34, 35, 36, 37, 39, 40], "all": [2, 3, 6, 11, 12, 15, 17, 19, 23, 25, 28, 31, 32, 34, 35], "mai": [2, 3, 4, 6, 10, 11, 12, 15, 17, 20, 28, 30, 31, 32], "need": [2, 3, 4, 12, 15, 19, 30, 31, 33, 34, 36, 37, 40], "addit": [2, 6, 12, 15, 30, 33, 34, 37], "pleas": [2, 4, 16, 19, 31], "see": [2, 7, 17, 18, 19, 20, 21, 22, 23, 26, 28, 30, 32, 34, 35, 36, 39, 40], "detail": [2, 3, 4, 17, 25, 35, 36, 39, 40], "x": [2, 8, 9, 10, 17, 19, 24, 29, 32], "download": [2, 3, 4, 19], "aimet_torch": [2, 3, 4, 6, 7, 8, 9, 10, 11, 12, 13, 15, 16, 17, 18, 19, 29], "cu121": [2, 3, 4], "cp310": [2, 3, 4], "manylinux_2_34_x86_64": [2, 3, 4], "f": [2, 3, 4, 19], "org": [2, 3, 4, 31], "torch_stabl": [2, 3, 4], "html": [2, 3, 4, 11, 32, 37, 40], "cpu": [2, 3, 19, 30, 37], "13": [2, 3, 7, 13], "11": [2, 3, 4, 7, 10], "cu117": 2, "tensorflow": [2, 3, 22, 26, 27, 30, 34, 36, 37], "aimet_tensorflow": [2, 4], "cu118": 2, "onnx": [2, 3, 16, 20, 21, 26, 29, 30, 31, 32, 34, 36], "16": [2, 6, 7, 8, 9, 12, 13, 15, 17, 18], "aimet_onnx": [2, 4], "older": 2, "brows": [2, 3, 4], "document": [2, 4, 26, 37, 39], "correspond": [2, 3, 4, 12, 15, 17, 23, 32, 36, 42], "select": [2, 3, 4, 21, 24, 32, 36, 39, 42], "appropri": [2, 4, 6, 12, 15, 17, 25, 35], "platform": [2, 20, 30, 36], "setup": 2, "bash": [2, 3], "command": [2, 3, 4, 39], "shell": 2, "nvidia": [2, 3, 4], "card": 2, "comput": [2, 4, 6, 8, 9, 12, 13, 15, 19, 20, 28, 29, 31, 32, 36, 39, 42], "capabl": [2, 17, 39], "5": [2, 7, 8, 9, 12, 17, 18, 24, 33, 35], "later": [2, 15, 19], "docker": 2, "To": [2, 6, 15, 17, 19, 22, 25, 29, 30, 32, 34, 35, 36, 39, 40], "us": [2, 4, 6, 7, 10, 11, 12, 13, 15, 16, 17, 18, 19, 22, 24, 26, 29, 31, 32, 33, 34, 35, 36, 37, 39, 40], "acceler": [2, 16, 26, 28], "train": [2, 16, 20, 21, 22, 26, 28, 32, 35, 36, 37], "modul": [2, 6, 11, 12, 15, 16, 19, 30, 37, 42], "an": [2, 6, 10, 11, 12, 16, 17, 18, 19, 20, 21, 23, 24, 25, 26, 28, 29, 30, 32, 33, 34, 35, 36, 40, 42], "enabl": [2, 3, 12, 16, 22, 26, 30, 32, 34, 36, 37, 39], "minimum": [2, 7, 13], "driver": [2, 4], "455": 2, "i": [2, 3, 4, 6, 7, 8, 9, 11, 12, 13, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 28, 29, 30, 31, 32, 33, 34, 35, 36, 38, 39, 40, 41, 42], "alwai": [2, 25], "recommend": [2, 12, 20, 22, 24, 30, 35], "especi": [2, 30, 33, 35], "newer": 2, "both": [2, 7, 12, 15, 16, 17, 28, 30, 31, 33, 34, 35, 36, 38, 39, 42], "cudnn": 2, "more": [2, 12, 15, 16, 17, 19, 23, 24, 25, 28, 30, 31, 32, 34, 35, 36, 39], "interfac": 2, "support": [2, 6, 12, 15, 23, 24, 26, 27, 28, 29, 30, 31, 34, 35, 36, 37, 41], "There": [2, 29, 31, 33, 40], "two": [2, 12, 19, 25, 26, 28, 30, 31, 32, 33, 36, 38, 40, 41], "wai": [2, 12, 19, 29], "On": 2, "your": [2, 3, 4, 6, 16, 20, 21, 24, 28, 29, 30, 33, 36, 39], "machin": [2, 3, 28], "our": [2, 4, 19], "built": [2, 3, 6, 17], "develop": [2, 3, 4, 11, 12, 15], "imag": [2, 20, 32], "click": 2, "link": [2, 4, 22, 31, 32], "contain": [2, 6, 10, 11, 15, 17, 19, 30, 32, 33, 34, 36], "page": [3, 4, 24, 36, 37], "provid": [3, 4, 6, 8, 9, 12, 15, 16, 19, 20, 24, 25, 28, 30, 31, 32, 34, 35, 36, 39, 40], "instruct": [3, 4, 16], "insid": [3, 6, 17, 19], "variant_str": 3, "ONE": 3, "depend": [3, 4, 10, 24, 30, 34, 37], "desir": [3, 12, 19, 24, 28, 30, 35], "pt113": 3, "tf": [3, 32, 36, 37], "export": [3, 4, 15, 16, 22, 26, 28, 29, 30, 33, 36, 37], "aimet_vari": 3, "one": [3, 12, 15, 19, 23, 28, 33, 37, 38, 39, 41], "workspac": 3, "absolute_path_to_workspac": 3, "docker_image_nam": 3, "artifact": [3, 19], "codelinaro": 3, "docker_container_nam": 3, "any_nam": 3, "note": [3, 4, 12, 15, 19, 26, 39], "feel": 3, "free": [3, 31], "modifi": [3, 4, 30, 36, 37, 42], "you": [3, 4, 6, 15, 20, 21, 24, 26, 28, 29, 30, 32, 33, 34, 35, 36, 39, 40], "want": [3, 6], "If": [3, 4, 6, 7, 8, 9, 12, 15, 17, 18, 19, 20, 21, 24, 25, 29, 30, 31, 32, 34, 35, 39, 40, 42], "skip": [3, 23], "next": [3, 19, 33, 35, 36], "section": [3, 4, 12, 22, 30, 36], "any_tag": 3, "t": [3, 6, 20, 32, 33], "jenkin": 3, "dockerfil": 3, "ensur": [3, 17, 25, 30, 35], "alreadi": [3, 6, 35], "run": [3, 4, 7, 12, 17, 18, 22, 26, 28, 30, 31, 32, 36, 37, 39], "otherwis": [3, 4, 7, 12, 18, 35], "remov": [3, 19, 23, 26, 36, 42], "exist": [3, 6, 12, 17, 36], "new": [3, 7, 12, 15, 16, 18, 19, 30, 37], "p": [3, 13], "grep": 3, "kill": 3, "rm": 3, "u": 3, "id": [3, 39], "user": [3, 6, 12, 15, 16, 20, 24, 28, 32, 35, 37], "g": [3, 19, 22], "v": [3, 12], "etc": [3, 24, 30], "passwd": 3, "ro": 3, "group": [3, 12, 34, 36], "home": 3, "mnt": 3, "entrypoint": 3, "bin": [3, 4, 13], "w": [3, 42], "hostnam": 3, "abov": [3, 4, 12, 15, 16, 28, 31, 36, 39, 42], "base": [3, 6, 7, 8, 9, 12, 13, 17, 18, 23, 24, 25, 30, 39], "filesystem": 3, "add": [3, 6, 17, 19, 34, 36, 37, 42], "order": [3, 4, 6, 12, 17, 19, 22, 23, 30, 33, 34], "access": 3, "replac": [3, 12, 17, 19, 31, 36], "port": [3, 39], "forward": [3, 6, 7, 17, 18, 19, 29, 32, 35, 37], "done": [3, 7, 18, 28, 34, 36], "visual": [3, 28, 30, 31, 32, 35, 37], "api": [3, 11, 19, 26, 29, 30, 34, 37, 39], "can": [3, 7, 10, 12, 15, 16, 17, 18, 19, 21, 22, 24, 25, 26, 28, 30, 31, 32, 33, 34, 35, 36, 39, 40, 42], "achiev": [3, 12, 20, 24], "port_id": 3, "ani": [3, 6, 12, 15, 19, 34, 37], "number": [3, 6, 7, 8, 9, 12, 13, 17, 20, 25, 26, 28, 33, 36, 37, 39, 42], "default": [3, 4, 6, 7, 11, 15, 17, 18, 20, 25, 28, 34, 36, 37, 39], "go": [3, 4, 15, 19], "project": [3, 4], "requir": [3, 4, 6, 12, 15, 19, 22, 24, 28, 30, 31, 34, 35, 39], "each": [3, 4, 6, 11, 12, 17, 18, 19, 22, 23, 24, 25, 28, 30, 31, 32, 33, 34, 35, 36, 40], "identifi": [3, 4, 12, 23, 32, 35, 37, 42], "wish": [3, 4], "some": [3, 4, 17, 19, 20, 24, 25, 29, 30, 31, 33, 35, 36, 42], "tip": [3, 4], "32": [3, 4, 7, 15, 18, 35], "post1": [3, 4], "7": [3, 4, 7, 8, 9, 19, 35, 42], "31": [3, 4], "prepend": [3, 4, 17], "sudo": [3, 4], "y": [3, 4, 19, 32], "we": [3, 4, 12, 15, 17, 19, 20, 24, 28, 30, 31, 35], "also": [3, 4, 12, 23, 28, 30, 32, 34, 36, 37, 40, 42], "wheel": [3, 4], "differ": [3, 4, 12, 23, 25, 28, 30, 31, 33, 35, 36], "which": [3, 4, 6, 7, 10, 12, 13, 15, 16, 17, 18, 19, 22, 24, 25, 28, 30, 31, 32, 34, 36, 37, 39, 42], "tag": [3, 4, 37], "below": [3, 4, 6, 7, 12, 15, 17, 18, 19, 22, 23, 25, 28, 30, 31, 32, 34, 35, 36, 39], "ex": [3, 4, 12], "release_tag": [3, 4], "construct": [3, 4, 19, 29], "root": [3, 4, 19], "url": [3, 4, 39], "download_url": [3, 4], "extens": [3, 4, 17], "wheel_file_nam": [3, 4], "do": [3, 4, 19, 28, 32, 35, 36], "find_pkg_url_str": [3, 4], "specifi": [3, 4, 7, 8, 9, 12, 18, 19, 21, 23, 24, 25, 28, 34, 36, 39], "automat": [3, 4, 12, 24, 28, 30, 32, 37], "common": [3, 12, 35, 40], "variabl": [3, 4, 7, 18, 25], "sourc": [3, 4, 6, 7, 8, 9, 10, 11, 12, 13, 15, 17, 18, 35], "usr": [3, 4], "lib": [3, 4], "dist": [3, 4], "envsetup": [3, 4], "sh": [3, 4], "unless": [4, 6, 15, 42], "pend": 4, "pip3": 4, "h": [4, 41, 42], "These": [4, 17, 19, 21, 22, 23, 24, 29, 30, 31, 32, 35, 36], "assum": [4, 12, 15, 25], "path": [4, 11, 15], "local": [4, 39], "case": [4, 7, 12, 17, 19, 25, 31, 34], "accordingli": 4, "basic": [4, 16, 19], "updat": [4, 13, 18, 30, 31, 33, 36, 37, 39], "upgrad": 4, "ye": [4, 28], "wget": 4, "gnupg2": 4, "have": [4, 6, 11, 12, 19, 28, 31, 32, 35], "multipl": [4, 12, 17, 26, 28, 37], "set": [4, 6, 11, 12, 15, 17, 18, 20, 24, 25, 28, 29, 31, 32, 33, 34, 35], "altern": [4, 12], "were": [4, 15, 24, 34, 42], "test": 4, "sub": [4, 36], "visit": [4, 16], "archiv": 4, "obtain": [4, 24, 32], "correct": [4, 19, 20, 30, 31, 35], "exact": [4, 22, 30], "up": [4, 12, 20, 28, 34, 42], "date": 4, "execut": [4, 19, 39], "final": [4, 12, 23, 24, 25, 33, 35], "aforement": 4, "repo": 4, "ubuntu2204": 4, "x86_64": 4, "keyring_1": 4, "1_all": 4, "deb": 4, "dpkg": 4, "cat": 4, "reqs_deb_common": 4, "txt": 4, "xarg": 4, "reqs_deb_torch_common": 4, "reqs_deb_onnx_common": 4, "reqs_deb_tf_gpu": 4, "reqs_deb_torch_gpu": 4, "reqs_deb_onnx_gpu": 4, "option": [4, 6, 7, 12, 15, 16, 18, 19, 20, 32, 34, 36], "uninstal": 4, "cach": 4, "dir": 4, "9": [4, 7, 10], "onnxruntime_v": 4, "c": [4, 24], "import": [4, 6, 7, 8, 9, 10, 12, 13, 15, 16, 17, 18, 19, 22, 23], "print": [4, 6, 7, 17, 19, 32], "__version__": 4, "ln": 4, "": [4, 6, 12, 16, 17, 18, 19, 23, 24, 25, 27, 28, 30, 31, 32, 33, 35, 36, 40, 42], "gnu": 4, "libjpeg": 4, "so": [4, 17, 25, 29, 32], "chose": 4, "between": [4, 12, 17, 31, 32, 34, 36], "class": [6, 8, 12, 13, 15, 18, 19], "v2": [6, 7, 8, 9, 10, 11, 12, 13, 15, 16, 17, 18, 19], "nn": [6, 7, 11, 12, 16, 17, 18, 19, 29, 37], "arg": [6, 7, 10, 12, 15, 17, 18], "kwarg": [6, 7, 10, 17, 18], "mixin": [6, 17], "quantiz": [6, 8, 11, 13, 15, 16, 20, 21, 22, 24, 26, 28, 32, 37, 39], "function": [6, 10, 11, 12, 17, 19, 20, 25, 28, 29, 32, 36, 37, 39, 40], "top": [6, 23, 39], "regular": [6, 17, 20, 30, 36], "specif": [6, 12, 17, 19, 21, 22, 26, 29, 30, 31, 34, 37], "input": [6, 7, 8, 9, 11, 12, 13, 15, 17, 18, 19, 23, 25, 28, 32, 34, 36, 38, 41, 42], "output": [6, 7, 12, 17, 18, 19, 23, 28, 31, 32, 34, 36, 37, 38, 41, 42], "paramet": [6, 7, 8, 9, 10, 11, 12, 13, 17, 18, 19, 22, 23, 28, 29, 30, 31, 32, 33, 34, 40], "tensor": [6, 7, 8, 9, 12, 13, 15, 17, 18, 19, 20, 23, 29, 30, 32, 34, 35, 36, 37], "its": [6, 10, 15, 16, 17, 19, 23, 26, 32, 36, 42], "held": [6, 17, 19], "quantizerbas": [6, 17, 18], "object": [6, 10, 11, 12, 15, 17, 18, 19, 22, 30, 33, 36], "dure": [6, 11, 15, 17, 19, 20, 26, 28, 30, 33, 34, 36, 39, 40], "method": [6, 12, 15, 17, 19, 25, 28, 30, 35, 36], "inherit": [6, 17], "layer": [6, 11, 12, 15, 17, 19, 20, 21, 22, 23, 24, 27, 29, 30, 32, 34, 35, 36, 37, 38, 39, 40, 41, 42], "oper": [6, 17, 19, 29, 30, 31, 34, 35], "none": [6, 7, 8, 9, 11, 12, 15, 17, 19, 39], "behav": [6, 17, 35], "exactli": [6, 17, 36], "same": [6, 10, 12, 17, 18, 22, 31, 34, 40], "parent": [6, 17], "input_quant": [6, 17, 19], "modulelist": [6, 17, 19], "output_quant": [6, 17, 19], "param_quant": [6, 12, 17, 19], "moduledict": [6, 17, 19], "map": [6, 7, 10, 12, 17, 25, 32, 34], "associ": [6, 17, 30], "exampl": [6, 7, 8, 9, 10, 11, 12, 13, 17, 18, 19, 20, 24, 26, 30, 32, 34, 35, 36, 37, 42], "qlinear": [6, 17], "quantizedlinear": [6, 12, 17, 19], "in_featur": [6, 17, 19], "out_featur": [6, 17, 19], "bia": [6, 8, 9, 17, 19, 20, 23, 30, 31, 34, 35, 37], "true": [6, 7, 8, 9, 10, 12, 13, 17, 18, 19, 29, 34], "weight": [6, 11, 12, 13, 15, 17, 19, 20, 22, 24, 28, 30, 31, 32, 33, 34, 35, 36, 40], "abstract": [6, 17, 18], "should": [6, 12, 15, 17, 19, 24], "perform": [6, 7, 12, 15, 17, 18, 19, 21, 22, 23, 24, 25, 28, 30, 31, 32, 33, 35], "logic": [6, 17, 37], "param": [6, 12, 17, 18, 34], "call": [6, 8, 9, 10, 12, 17, 19, 30, 32, 34, 36, 37, 38, 41], "pass": [6, 12, 15, 16, 17, 19, 26, 29, 31, 32, 33, 35, 36, 37, 39], "__quant_init__": [6, 17], "initi": [6, 7, 8, 9, 17, 18, 20, 33, 36], "invok": [6, 17, 28, 30, 39, 40], "right": [6, 7, 8, 9, 17, 18, 42], "after": [6, 13, 15, 17, 19, 20, 21, 22, 24, 28, 30, 35, 39, 40], "__init__": [6, 17, 19], "structur": [6, 17, 28], "size": [6, 7, 12, 15, 17, 18, 20, 29, 38, 41], "initializd": [6, 17], "custom": [6, 17, 35, 36], "overridden": [6, 17, 34], "length": [6, 12, 17], "given": [6, 11, 12, 13, 17, 21, 25, 28, 31], "set_kernel": 6, "kernel": [6, 12, 23, 38, 41], "instanc": [6, 39], "In": [6, 12, 17, 19, 20, 24, 25, 28, 30, 31, 33, 34, 36, 39, 40, 42], "gener": [6, 7, 12, 15, 18, 19, 28, 30, 32, 33, 34, 35, 36], "signatur": [6, 7], "equival": [6, 7, 8, 9, 12, 19], "return": [6, 10, 11, 12, 13, 15, 16, 18, 19, 21, 25, 26, 32, 36], "quantizedtensor": [6, 7, 10, 18], "take": [6, 12, 19, 25, 28, 30, 31, 33, 35, 42], "keyword": 6, "argument": [6, 8, 9, 12], "output_encod": 6, "onc": [6, 22, 23, 28, 32, 33, 36], "within": [6, 10, 17, 24, 32, 36], "compute_encod": [6, 7, 8, 9, 10, 11, 13, 15, 16, 17, 18, 19], "context": [6, 17, 19], "callabl": [6, 12], "underli": [6, 35], "q": [6, 7, 8, 9, 10, 17, 18, 36], "def": [6, 15, 19], "int_multipli": 6, "b": [6, 7, 18], "encod": [6, 7, 10, 12, 15, 16, 18, 19, 20, 22, 30, 32, 33, 37], "enc": 6, "affin": [6, 10, 12, 15, 16, 17, 18, 19], "rais": 6, "notimplementederror": 6, "q_output": 6, "quantized_repr": [6, 10], "offset": [6, 7, 12, 13, 15, 18, 30, 32, 33, 36], "dq_output": 6, "scale": [6, 7, 8, 9, 10, 12, 15, 18, 22, 30, 31, 32, 33, 36], "qmult": 6, "quantizedmultipli": [6, 17], "classmethod": 6, "set_default_kernel": 6, "cl": [6, 37], "ha": [6, 10, 12, 15, 19, 24, 25, 30, 31, 33, 36, 39, 42], "been": [6, 10, 11, 12, 15, 36, 42], "get_kernel": 6, "enter": [6, 17, 21], "observ": [6, 13, 17, 18, 19, 28, 31, 32, 36], "upon": [6, 17, 19], "exit": [6, 17, 19], "symmetr": [6, 7, 10, 12, 13, 17, 18, 19, 34, 36], "fals": [6, 7, 10, 12, 13, 15, 17, 18, 19, 29, 34], "randn": [6, 7, 10, 13, 17, 18], "is_initi": [6, 7, 8, 9, 17, 18], "from_modul": 6, "creat": [6, 11, 13, 15, 16, 17, 19, 20, 22, 28, 29, 30, 33, 36], "result": [6, 10, 12, 13, 15, 20, 21, 23, 24, 26, 28, 31, 32, 33, 34, 36], "attribut": [6, 17, 32], "origin": [6, 17, 19, 23, 24, 25, 30, 31, 32, 36, 39], "assign": [6, 7, 17, 18], "float": [6, 8, 10, 12, 13, 16, 30, 32, 35, 36, 40], "point": [6, 10, 12, 16, 26, 30, 32, 35, 36, 40], "linear": [6, 12, 17, 19, 22, 23], "quantized_linear": 6, "get_default_kernel": 6, "type": [6, 10, 11, 12, 15, 17, 18, 28, 30, 32, 34, 36, 39], "current": [6, 27, 41], "doe": [6, 19, 23, 25, 27, 30, 35, 36], "retriev": 6, "implement": [6, 29, 30, 35], "module_cl": 6, "decor": 6, "regist": [6, 18], "definit": [6, 19, 30], "even": 6, "though": [6, 12, 34], "aimet": [6, 15, 17, 19, 26, 29, 34], "subpackag": 6, "conv2d": [6, 12, 17, 19, 23, 28, 37, 42], "awar": [6, 20, 22, 26, 28, 30, 35, 36], "quantizationsimmodel": [6, 11, 12, 15, 16, 19, 20, 22], "throw": 6, "runtim": [6, 12, 15, 16, 19, 24, 26, 28, 30, 32, 34, 36, 37], "error": [6, 21, 30, 32, 33, 35, 36], "when": [6, 12, 15, 16, 17, 19, 20, 28, 30, 31, 32, 33, 34, 35, 36, 39, 40, 42], "encount": [6, 19], "defin": [6, 12, 17, 19, 30, 32, 34, 36], "ask": 6, "doesn": [6, 33], "know": 6, "declar": 6, "subclass": [6, 13], "As": [6, 12, 15, 21, 24, 25, 31, 32, 36], "maskedadd": 6, "self": [6, 10, 19], "mask": 6, "valu": [6, 7, 8, 9, 10, 11, 12, 13, 15, 18, 19, 20, 23, 24, 25, 28, 30, 31, 32, 33, 34, 36, 38, 40, 41], "befor": [6, 11, 17, 19, 20, 21, 22, 28, 30, 32, 33, 36, 40], "typic": [6, 12, 17, 19, 24, 30, 32, 33, 36], "quantizedmaskedadd": 6, "matter": 6, "super": [6, 19], "input_qtzr": 6, "_": [6, 7, 11, 16, 17, 18, 19, 30], "don": [6, 20, 32], "boolean": 6, "value_qtzr": 6, "output_qtzr": 6, "shape": [7, 8, 9, 10, 12, 13, 17, 18, 19, 32], "precis": [7, 8, 9, 16, 18, 30], "out": [7, 8, 9, 18], "clamp": [7, 8, 9, 18, 36], "left": [7, 8, 9, 18, 25, 42], "lceil": [7, 8, 9, 18], "frac": [7, 8, 9, 18], "rfloor": [7, 8, 9, 18], "qmin": [7, 18, 36], "qmax": [7, 18, 36], "where": [7, 8, 9, 15, 18, 19, 22, 25, 32, 38, 39, 41, 42], "deriv": [7, 18, 36], "learnabl": [7, 18], "theta_": [7, 18], "min": [7, 11, 13, 18, 19, 32, 36], "max": [7, 8, 9, 11, 13, 18, 19, 28, 31, 32, 36], "block": [7, 12, 15, 18], "begin": [7, 18, 34], "pmatrix": [7, 18], "b_0": [7, 18], "b_1": [7, 12, 18], "cdot": [7, 18], "b_": [7, 18], "d": [7, 18], "end": [7, 18, 19, 28], "equat": [7, 12, 18, 36], "further": [7, 10, 12, 18, 19, 20, 23, 26, 28], "out_": [7, 18], "j_0": [7, 18], "j_": [7, 18], "input_": [7, 18], "scale_": [7, 18], "i_0": [7, 18], "i_": [7, 18], "offset_": [7, 18], "text": [7, 18], "quad": [7, 18, 36], "forall_": [7, 18], "leq": [7, 18], "i_d": [7, 18], "lfloor": [7, 8, 9, 18], "j_d": [7, 18], "b_d": [7, 18], "tupl": [7, 12, 13, 15, 18], "bitwidth": [7, 8, 9, 10, 12, 15, 17, 18, 19, 22, 30, 35, 36], "int": [7, 8, 9, 12, 13, 18], "bool": [7, 12, 13, 18], "asymmetr": [7, 13, 18, 34, 36], "encoding_analyz": [7, 8, 9, 13, 18], "encodinganalyz": [7, 8, 9, 13, 18], "analyz": [7, 16, 17, 18, 21, 23, 29, 32, 39, 40], "calibr": [7, 11, 12, 13, 15, 16, 17, 18, 19, 30, 32, 33, 35, 36], "absolut": [7, 18], "block_siz": [7, 12, 18], "cannot": [7, 18], "until": [7, 18, 21], "properli": [7, 18, 19], "statist": [7, 8, 9, 11, 13, 17, 18, 19, 22, 30, 32, 40], "manual": [7, 18, 21, 28], "129": [7, 18, 29], "255": [7, 10, 18], "122": [7, 18], "192": [7, 18], "106": [7, 18], "94": [7, 18], "145": [7, 18], "181": [7, 18], "144": [7, 18], "194": [7, 18], "74": [7, 18], "86": [7, 18], "150": [7, 18], "33": [7, 18], "103": [7, 18], "37": [7, 18], "111": [7, 18], "237": [7, 18], "218": [7, 18], "49": [7, 18], "155": [7, 18], "179": [7, 18], "66": [7, 18, 24], "89": [7, 18], "110": [7, 18], "17": [7, 13, 18], "36": [7, 18], "83": [7, 18], "grad_fn": [7, 10, 18], "aliasbackward0": [7, 10, 18], "ones_lik": [7, 18], "187": [7, 18], "186": [7, 18], "131": [7, 18], "203": [7, 18], "80": [7, 13, 18], "143": [7, 18], "152": [7, 18], "226": [7, 18], "55": [7, 18], "172": [7, 18], "207": [7, 18], "146": [7, 18], "216": [7, 18], "238": [7, 18], "141": [7, 18], "178": [7, 18], "188": [7, 18], "63": [7, 18], "59": [7, 18], "19": [7, 13, 18], "162": [7, 18], "30": [7, 18], "109": [7, 18], "quantizedequant": [7, 9, 10, 12, 17, 18, 19], "fake": [7, 8, 9, 18, 19], "dequant": [7, 10, 18], "overlin": [7, 18], "qdq": [7, 8, 9, 18], "dequantizedtensor": [7, 10, 18], "2771": [7, 18], "3038": [7, 18], "0819": [7, 18], "9700": [7, 18], "9487": [7, 18], "1307": [7, 18], "7894": [7, 18], "1709": [7, 18], "2212": [7, 18], "7741": [7, 18], "0295": [7, 18], "2265": [7, 18], "0564": [7, 18], "6177": [7, 18], "0386": [7, 18], "0176": [7, 18], "6054": [7, 18], "8836": [7, 18], "1232": [7, 18], "8229": [7, 18], "5540": [7, 18], "3992": [7, 18], "2363": [7, 18], "2546": [7, 18], "0036": [7, 18], "2355": [7, 18], "1741": [7, 18], "6079": [7, 18], "6247": [7, 18], "0115": [7, 18], "2458": [7, 18], "9157": [7, 18], "4694": [7, 18], "0639": [7, 18], "2568": [7, 18], "0680": [7, 18], "6695": [7, 18], "7932": [7, 18], "1889": [7, 18], "0158": [7, 18], "5695": [7, 18], "5220": [7, 18], "1977": [7, 18], "4475": [7, 18], "0424": [7, 18], "1128": [7, 18], "8796": [7, 18], "1060": [7, 18], "5897": [7, 18], "6196": [7, 18], "9961": [7, 18], "0549": [7, 18], "6431": [7, 18], "0039": [7, 18], "8706": [7, 18], "4706": [7, 18], "2353": [7, 18], "8078": [7, 18], "3451": [7, 18], "1176": [7, 18], "4549": [7, 18], "0471": [7, 18], "5255": [7, 18], "4157": [7, 18], "0784": [7, 18], "5333": [7, 18], "1647": [7, 18], "2118": [7, 18], "2196": [7, 18], "9176": [7, 18], "9490": [7, 18], "7765": [7, 18], "4784": [7, 18], "6039": [7, 18], "3137": [7, 18], "3216": [7, 18], "8000": [7, 18], "4392": [7, 18], "4863": [7, 18], "overload": 7, "list": [7, 12, 15, 17, 18, 25, 27, 29, 34], "sign": [7, 36], "rceil": 7, "posit": 7, "integ": [7, 12, 20, 30, 32], "rang": [7, 11, 13, 19, 20, 22, 25, 30, 31, 32, 33, 35, 36, 37, 40], "over": [7, 13, 17, 20, 25, 28, 40], "neg": [7, 12], "num_step": [7, 13], "num": 7, "_step": 7, "step": [7, 13, 15, 16, 19, 20, 21, 22, 23, 24, 25, 28, 30, 31, 33, 35], "maximum": [7, 8, 9, 13], "arang": 7, "start": [7, 19, 20, 24, 34, 36], "05": [7, 19], "0000e": 7, "01": [7, 20], "5000e": 7, "02": 7, "1921e": 7, "08": 7, "4": [7, 10, 12, 19, 22, 25, 30, 35, 42], "6": [7, 12, 13, 15, 33, 35], "00": 7, "0500e": 7, "1000e": 7, "1500e": 7, "2000e": 7, "2500e": 7, "15": [7, 28, 33], "14": [7, 19], "quantize_dequant": 7, "0000": [7, 10], "0667": 7, "1333": 7, "2000": [7, 10], "2667": 7, "3333": 7, "4000": [7, 10], "4667": 7, "6000": [7, 10], "6667": 7, "7333": 7, "8667": 7, "9333": 7, "exponent_bit": [8, 9, 12], "mantissa_bit": [8, 9, 12], "dtype": [8, 9, 10, 12, 15], "simul": [8, 9, 12, 15, 16, 17, 19, 26, 30, 33, 37], "cast": [8, 9], "expon": [8, 9, 12], "mantissa": [8, 9, 12], "x_c": [8, 9], "log_2": [8, 9], "ieee": [8, 9, 28, 31], "standard": [8, 9, 17], "represent": [8, 9, 10], "_max": [8, 9], "mutual": [8, 9, 12], "exclus": [8, 9, 12], "repres": [8, 9, 10, 17, 18, 19, 25, 31, 32, 33, 36], "determin": [8, 9, 12, 17, 19, 21, 30, 31, 32, 40], "dynam": [8, 9, 31, 36, 37, 40], "finer": [8, 9, 12], "8998": [8, 9], "0947": [8, 9], "0891": [8, 9], "1727": [8, 9], "unlik": [8, 9], "affinequant": [8, 9], "floatquant": [8, 9], "without": [8, 9, 10, 11, 12, 15, 21, 30, 33, 36, 42], "is_bfloat16": [8, 9], "8984": [8, 9], "0859": [8, 9], "1729": [8, 9], "minmaxencodinganalyz": [8, 9, 13], "float16": [8, 9, 12], "is_float16": [8, 9], "8994": [8, 9], "0889": [8, 9], "alia": [8, 9], "floatquantizedequant": 9, "hold": [10, 12, 15, 17, 34, 35], "store": [10, 12, 15], "along": [10, 12, 19, 33, 36], "encodingbas": [10, 18], "inform": [10, 15, 30], "necessari": [10, 12, 19, 39], "back": [10, 19, 34], "real": [10, 39], "produc": [10, 11, 12, 13, 25, 32], "rtype": 10, "57": 10, "312": 10, "153": 10, "205": 10, "set_rang": 10, "128": [10, 12, 19], "127": 10, "x_q": 10, "26": 10, "23": [10, 13], "x_dq": 10, "3000": 10, "equal": [10, 12, 20, 21, 24, 25, 29, 30, 32, 35, 36, 40], "data": [10, 11, 12, 13, 15, 16, 19, 20, 22, 27, 31, 32, 33, 35, 36], "abl": [10, 19], "carri": 10, "gradient": 10, "thu": 10, "autograd": 10, "allow": [10, 12, 21, 28, 35, 36, 37, 39], "backpropag": 10, "requires_grad": 10, "38": [10, 28], "28": 10, "40": 10, "int8": [10, 33, 36, 40], "subsequ": [10, 15, 29, 31, 34], "well": [10, 12, 15, 28, 31, 32], "about": [10, 19, 26, 32], "wa": [10, 28], "With": [10, 30, 33], "convert": [10, 19, 21, 30, 40], "loss": [10, 16, 19, 20, 26, 28, 30, 32, 36], "39": [10, 19], "51": 10, "521": 10, "41": 10, "quant_dequ": 10, "x_qdq": 10, "52": 10, "68": 10, "97": 10, "uint8": 10, "featur": [11, 12, 15, 20, 21, 22, 28, 31, 32, 35, 36, 37, 39, 40], "under": [11, 12, 15, 32, 34], "heavi": [11, 12, 15, 39, 40], "chang": [11, 12, 15, 19, 20, 28, 32, 33, 34, 36, 40, 42], "occur": [11, 12, 15], "notic": [11, 12, 15], "futur": [11, 12, 15], "visualization_tool": 11, "visualize_stat": 11, "sim": [11, 12, 15, 16, 19, 33, 36], "dummy_input": [11, 12, 15, 19], "save_path": 11, "quant_stats_visu": 11, "interact": 11, "view": [11, 16, 19, 22, 26, 29, 31, 32, 39], "stat": [11, 13], "collect": [11, 12, 25, 32], "expect": [11, 13, 15, 19, 28, 30, 32], "plot": [11, 32], "activ": [11, 12, 15, 17, 19, 30, 32, 33, 34, 35, 36], "quantsim": [11, 12, 15, 16, 30, 33, 34, 37], "includ": [11, 12, 22, 25, 32, 33, 34, 36, 37, 39], "adjust": [11, 12, 20, 22, 23, 24, 30, 31, 35], "threshold": [11, 17, 21], "flag": [11, 18], "whose": [11, 12, 31, 34], "exce": 11, "tabl": [11, 39], "exceed": 11, "save": [11, 15, 19, 36, 40], "quant_schem": [11, 15], "quantschem": [11, 15, 21], "post_training_tf": [11, 15], "data_load": [11, 15, 16, 19], "sampl": [11, 16, 17, 19, 23, 31, 32, 33, 36], "trace": 11, "str": [11, 15], "known": [12, 26], "like": [12, 15, 16, 19, 21, 26, 28, 30, 32, 33, 34], "grid": 12, "counterpart": [12, 17], "process": [12, 13, 16, 19, 21, 23, 25, 26, 28, 31, 36], "particular": [12, 30, 34], "choos": [12, 23, 24, 28], "come": [12, 28, 33], "cover": [12, 36], "whole": [12, 36], "split": 12, "describ": [12, 28, 29, 30, 31, 34, 35, 36, 39], "sever": [12, 17, 24, 32], "pro": 12, "con": 12, "per": [12, 15, 17, 22, 31, 32, 34, 35, 36, 37, 39], "entir": [12, 19, 28], "singl": [12, 20, 25, 28, 31], "benefit": [12, 20], "less": [12, 13, 23, 25, 34], "storag": 12, "space": 12, "drawback": 12, "outlier": [12, 32, 36], "affect": [12, 22, 34], "channel": [12, 15, 17, 22, 24, 25, 27, 28, 31, 32, 34, 35, 36, 37, 38, 40, 41, 42], "individu": [12, 22, 25, 30, 32, 34, 35], "dimens": [12, 15, 17, 35, 38, 41], "compar": [12, 15, 19, 30, 32, 33, 40], "would": [12, 13, 34, 37], "influenc": 12, "resid": [12, 37], "chunk": 12, "across": [12, 31, 32, 40], "improv": [12, 19, 24, 28, 30, 33, 35, 40], "granular": [12, 28, 35, 36, 40], "found": [12, 33, 36], "isol": 12, "optim": [12, 15, 19, 20, 21, 26, 28, 30, 33, 36, 37, 39], "cost": [12, 25, 28, 33], "increas": [12, 25, 31], "favor": 12, "possibl": [12, 19, 25, 32, 34, 35], "similarli": [12, 15, 35], "lead": [12, 20, 22, 31, 35], "better": [12, 20, 21, 28, 30, 31, 33], "accuraci": [12, 16, 19, 20, 21, 24, 25, 26, 28, 30, 31, 32, 33, 35, 36, 37, 40, 42], "part": [12, 28, 31, 32], "basi": 12, "instanti": [12, 15, 19, 39], "relationship": 12, "actual": 12, "being": [12, 23], "rule": [12, 34], "must": [12, 15, 17, 21, 22, 24, 26, 27, 30, 32, 34, 42], "match": [12, 23, 28, 32, 34, 35, 36, 42], "most": [12, 19, 34], "long": [12, 15], "b_2": 12, "b_n": 12, "s_1": 12, "s_2": 12, "s_n": 12, "satisfi": [12, 19, 21], "n": [12, 19, 37], "word": 12, "evenli": 12, "divid": [12, 17, 24, 33], "valid": [12, 21, 30, 37], "sinc": [12, 22, 24, 36], "divis": 12, "permit": 12, "essenti": [12, 16], "invalid": 12, "combin": [12, 21, 24, 28, 30, 31], "3d": 12, "infer": [12, 15, 16, 19, 22, 24, 26, 31, 33, 36, 37], "while": [12, 17, 20, 25, 29, 33, 35], "arbitrari": 12, "experiment": [12, 28], "purpos": 12, "restrict": [12, 29], "place": [12, 15, 34], "constraint": 12, "still": [12, 30, 35], "themselv": [12, 33], "code": [12, 19, 20], "show": [12, 15, 16, 19, 22, 25, 26, 31, 35], "how": [12, 15, 17, 19, 28, 30, 31, 32, 34, 35, 36, 38, 41], "configur": [12, 15, 19, 27, 37], "convolut": [12, 19, 22, 23, 24, 28, 35, 38, 41, 42], "conv_1": 12, "refer": [12, 15, 17, 20, 36], "quantizedconv2d": [12, 17, 19], "work": [12, 28, 31], "too": 12, "linear_1": 12, "scheme": [12, 13, 21, 22, 28, 32], "lower": [12, 25, 30, 35], "thei": [12, 35, 39], "lie": 12, "higher": [12, 13, 22, 25, 33, 35], "leverag": 12, "than": [12, 15, 19, 24, 27, 33, 34], "due": [12, 31], "fact": 12, "expans": [12, 28], "factor": [12, 13, 24, 28, 31], "fashion": 12, "groupedblockquantizedequant": 12, "introduc": [12, 17, 30, 34, 36], "decompressed_bw": 12, "expand": 12, "greater": [12, 24, 25], "block_group": 12, "togeth": 12, "except": 12, "make": [12, 17, 29, 30], "easier": 12, "config_util": 12, "set_blockwise_quantization_for_weight": 12, "consist": [12, 25, 36], "either": [12, 20, 42], "A": [12, 20, 24, 25, 28, 30, 32, 33, 36], "union": [12, 15], "arrai": 12, "in_channel": [12, 19], "out_channel": [12, 19], "conv": [12, 27, 34, 37, 38, 41, 42], "input_channel": 12, "conv2": [12, 19], "linear1": 12, "dim": [12, 19], "lambda": 12, "isinst": 12, "util": [12, 19, 22, 30], "certain": [12, 28, 29, 34], "Of": 12, "signific": [12, 35], "second": [12, 17, 34], "subset": [12, 20, 22, 32, 42], "switch": 12, "docstr": 12, "instead": [12, 15, 30, 31, 42], "4d": 12, "2d": [12, 23, 28, 42], "handl": 12, "mention": 12, "assist": 12, "transform": [12, 15, 19, 37], "set_activation_quantizers_to_float": 12, "set_grouped_blockwise_quantization_for_weight": 12, "decompress": 12, "bw": 12, "experi": [12, 28], "similar": [12, 31, 33, 36], "addition": 12, "effect": [12, 17, 19, 22, 30, 32, 36], "larger": [12, 38, 41], "reduc": [12, 15, 17, 28, 30, 31, 33, 35, 37, 42], "write": [12, 15], "snippet": [12, 15], "format": [12, 15, 18, 21, 27], "encoding_vers": [12, 15], "exported_model": [12, 15], "present": [12, 15, 19, 31], "gather": 13, "is_symmetr": [13, 34], "reset_stat": 13, "reset": 13, "intern": [13, 28, 31, 34], "update_stat": 13, "input_tensor": 13, "involv": [13, 19, 30, 35], "track": [13, 32], "calcul": [13, 17, 25, 31, 32, 33, 36], "100": [13, 15, 19], "math": [13, 19], "pow": 13, "0991": 13, "3696": 13, "_minmaxrang": 13, "1721": 13, "2592": 13, "sqnrencodinganalyz": 13, "num_bin": 13, "2048": [13, 15], "asymmetric_delta_candid": 13, "symmetric_delta_candid": 13, "101": 13, "offset_candid": 13, "21": 13, "max_parallel": 13, "gamma": 13, "sqnr": [13, 36], "record": 13, "histogram": [13, 30, 32, 36, 37], "lowest": [13, 23], "delta": [13, 36], "search": [13, 33, 34], "mode": [13, 18, 29, 30, 34], "parallel": 13, "memori": [13, 24, 28, 38, 41, 42], "usag": [13, 16], "faster": [13, 26], "clip": [13, 34, 36], "nois": [13, 19, 30, 31, 32, 33, 34], "percentil": 13, "3612": 13, "8497": 13, "_histogram": 13, "bin_edg": 13, "8907": 13, "3625": 13, "8343": 13, "3061": 13, "7779": 13, "2497": 13, "2784": 13, "8066": 13, "3348": 13, "8630": 13, "3912": 13, "7080": 13, "2438": 13, "percentileencodinganalyz": 13, "largest": 13, "smallest": 13, "1188": 13, "3368": 13, "27": 13, "5710": 13, "0989": 13, "6269": 13, "1548": 13, "6827": 13, "2106": 13, "2614": 13, "7335": 13, "2056": 13, "6776": 13, "1497": 13, "gptvq_weight": 15, "apply_gptvq": 15, "gptvq_param": 15, "param_encoding_path": 15, "module_names_to_exclud": 15, "block_level_module_nam": 15, "file_name_prefix": 15, "config_file_path": 15, "round": [15, 16, 20, 30, 32, 36], "separ": [15, 22, 32, 35, 37], "qat": [15, 19, 20, 22, 26, 30, 35, 36, 37], "dummi": [15, 32], "pars": 15, "graph": [15, 29, 30, 36, 39], "devic": [15, 16, 19, 36], "gptvqparamet": 15, "dataclass": 15, "exclud": 15, "leaf": [15, 37], "prefix": [15, 17], "filenam": 15, "forward_fn": 15, "row_axi": 15, "col_axi": 15, "rows_per_block": 15, "cols_per_block": 15, "256": [15, 19, 32], "vector_dim": 15, "vector_bw": 15, "vector_strid": 15, "index_bw": 15, "num_of_kmeans_iter": 15, "assignment_chunk_s": 15, "carrier": 15, "dataload": [15, 19, 32], "wise": [15, 35], "explicitli": [15, 42], "load": [15, 28], "pretrain": [15, 33, 36], "opt": 15, "125m": 15, "packag": [15, 37], "optforcausallm": 15, "from_pretrain": 15, "facebook": 15, "now": [15, 19, 37], "gptvq_applied_model": 15, "zero": [15, 36, 37], "lm_head": 15, "gptvq_opt": 15, "default_param_bw": [15, 19], "default_output_bw": [15, 19], "load_encod": 15, "allow_overwrit": [15, 18], "through": [15, 17, 19, 31, 32, 36], "here": [15, 19, 30, 33, 34], "vector": 15, "index": [15, 17, 37], "blockwis": 15, "lpbq": 15, "tool": [16, 19, 31, 40, 42], "compress": [16, 23, 26, 37, 38, 40, 41, 42], "deploi": [16, 36], "edg": [16, 26], "fix": [16, 26, 30, 35, 36, 37], "post": [16, 19, 20, 21, 26, 28, 33, 36, 37], "fine": [16, 24, 26, 30, 33, 36], "tune": [16, 24, 26, 30, 33, 36], "techniqu": [16, 19, 21, 23, 24, 26, 30, 32, 33, 35, 36, 37, 38, 41], "minim": [16, 26, 30, 36], "incur": [16, 26, 32], "pictur": 16, "high": [16, 20, 24, 25, 26, 31, 37, 40], "level": [16, 24, 25, 26, 30, 35, 39], "workflow": [16, 19, 24, 26], "low": [16, 20, 22, 28, 30, 31], "recov": [16, 26, 35, 36], "lost": [16, 26, 36], "via": [16, 24, 36], "torchscript": 16, "target": [16, 22, 24, 25, 26, 28, 30, 35, 36, 37], "neural": [16, 19, 21, 24, 26, 28, 30, 33, 35, 36, 41], "sdk": [16, 19, 26], "instal": [16, 26, 37, 39], "sample_input": [16, 19], "sample_output": 16, "out_dir": 16, "quantized_model": 16, "quickstart": 16, "guid": [16, 24, 31, 35, 37], "depth": [16, 24, 35], "adapt": [16, 19, 20, 30, 32, 37], "adaround": [16, 21, 30, 35, 37], "quantizationmixin": [16, 17], "product": [16, 24, 26], "technologi": [16, 26], "subsidiari": [16, 26], "network": [17, 19, 21, 24, 25, 28, 30, 33, 35, 36, 39, 41], "extra": 17, "serv": [17, 39], "drop": [17, 21, 24, 28, 31, 32, 33, 35, 36], "nativ": 17, "quantizedsoftmax": [17, 19], "softmax": [17, 19], "full": 17, "behavior": [17, 19, 26], "control": [17, 36], "descript": [17, 20, 29], "dict": [17, 18], "By": [17, 20, 28, 36], "mean": [17, 19, 32, 34, 36], "respect": [17, 32], "per_channel_quant": [17, 34], "elementwis": [17, 37], "multipli": [17, 24, 28], "qmul": 17, "sens": 17, "share": 17, "indic": [17, 24, 42], "qadd": 17, "quantizedadd": 17, "first": [17, 19, 28, 30, 33, 35], "disabl": [17, 25, 28, 32, 34, 36], "them": [17, 19, 28], "calibration_data_load": 17, "adaptiveavgpool1d": 17, "quantizedadaptiveavgpool1d": 17, "adaptiveavgpool2d": 17, "quantizedadaptiveavgpool2d": 17, "adaptiveavgpool3d": 17, "quantizedadaptiveavgpool3d": 17, "adaptivemaxpool1d": 17, "quantizedadaptivemaxpool1d": 17, "adaptivemaxpool2d": 17, "quantizedadaptivemaxpool2d": 17, "adaptivemaxpool3d": 17, "quantizedadaptivemaxpool3d": 17, "alphadropout": 17, "quantizedalphadropout": 17, "avgpool1d": 17, "quantizedavgpool1d": 17, "avgpool2d": 17, "quantizedavgpool2d": 17, "avgpool3d": 17, "quantizedavgpool3d": 17, "batchnorm1d": 17, "quantizedbatchnorm1d": 17, "batchnorm2d": [17, 19], "quantizedbatchnorm2d": 17, "batchnorm3d": 17, "quantizedbatchnorm3d": 17, "celu": 17, "quantizedcelu": 17, "channelshuffl": 17, "quantizedchannelshuffl": 17, "constantpad1d": 17, "quantizedconstantpad1d": 17, "constantpad2d": 17, "quantizedconstantpad2d": 17, "constantpad3d": 17, "quantizedconstantpad3d": 17, "conv1d": [17, 37], "quantizedconv1d": 17, "conv3d": 17, "quantizedconv3d": 17, "convtranspose1d": [17, 37], "quantizedconvtranspose1d": 17, "convtranspose2d": 17, "quantizedconvtranspose2d": 17, "convtranspose3d": 17, "quantizedconvtranspose3d": 17, "dropout": 17, "quantizeddropout": 17, "dropout2d": 17, "quantizeddropout2d": 17, "dropout3d": 17, "quantizeddropout3d": 17, "elu": 17, "quantizedelu": 17, "featurealphadropout": 17, "quantizedfeaturealphadropout": 17, "flatten": 17, "quantizedflatten": 17, "fold": [17, 20, 21, 22, 30, 31, 32, 37], "quantizedfold": 17, "fractionalmaxpool2d": 17, "quantizedfractionalmaxpool2d": 17, "fractionalmaxpool3d": 17, "quantizedfractionalmaxpool3d": 17, "gelu": 17, "quantizedgelu": 17, "glu": 17, "quantizedglu": 17, "groupnorm": 17, "quantizedgroupnorm": 17, "hardshrink": 17, "quantizedhardshrink": 17, "hardsigmoid": 17, "quantizedhardsigmoid": 17, "hardswish": 17, "quantizedhardswish": 17, "hardtanh": 17, "quantizedhardtanh": 17, "instancenorm1d": 17, "quantizedinstancenorm1d": 17, "instancenorm2d": 17, "quantizedinstancenorm2d": 17, "instancenorm3d": 17, "quantizedinstancenorm3d": 17, "lppool1d": 17, "quantizedlppool1d": 17, "lppool2d": 17, "quantizedlppool2d": 17, "layernorm": 17, "quantizedlayernorm": 17, "leakyrelu": 17, "quantizedleakyrelu": 17, "localresponsenorm": 17, "quantizedlocalresponsenorm": 17, "logsigmoid": 17, "quantizedlogsigmoid": 17, "logsoftmax": 17, "quantizedlogsoftmax": 17, "maxpool1d": 17, "quantizedmaxpool1d": 17, "maxpool2d": 17, "quantizedmaxpool2d": 17, "maxpool3d": 17, "quantizedmaxpool3d": 17, "maxunpool1d": 17, "quantizedmaxunpool1d": 17, "maxunpool2d": 17, "quantizedmaxunpool2d": 17, "maxunpool3d": 17, "quantizedmaxunpool3d": 17, "mish": 17, "quantizedmish": 17, "prelu": 17, "quantizedprelu": 17, "pixelshuffl": 17, "quantizedpixelshuffl": 17, "pixelunshuffl": 17, "quantizedpixelunshuffl": 17, "rrelu": 17, "quantizedrrelu": 17, "relu": [17, 19, 31, 34, 42], "quantizedrelu": [17, 19], "relu6": [17, 31], "quantizedrelu6": 17, "reflectionpad1d": 17, "quantizedreflectionpad1d": 17, "reflectionpad2d": 17, "quantizedreflectionpad2d": 17, "replicationpad1d": 17, "quantizedreplicationpad1d": 17, "replicationpad2d": 17, "quantizedreplicationpad2d": 17, "replicationpad3d": 17, "quantizedreplicationpad3d": 17, "selu": 17, "quantizedselu": 17, "silu": 17, "quantizedsilu": 17, "sigmoid": 17, "quantizedsigmoid": 17, "softmax2d": 17, "quantizedsoftmax2d": 17, "softmin": 17, "quantizedsoftmin": 17, "softplu": 17, "quantizedsoftplu": 17, "softshrink": 17, "quantizedsoftshrink": 17, "softsign": 17, "quantizedsoftsign": 17, "tanh": 17, "quantizedtanh": 17, "tanhshrink": 17, "quantizedtanhshrink": 17, "quantizedthreshold": 17, "unflatten": 17, "quantizedunflatten": 17, "unfold": 17, "quantizedunfold": 17, "upsampl": [17, 29], "quantizedupsampl": 17, "upsamplingbilinear2d": 17, "quantizedupsamplingbilinear2d": 17, "upsamplingnearest2d": 17, "quantizedupsamplingnearest2d": 17, "zeropad2d": 17, "quantizedzeropad2d": 17, "bceloss": 17, "quantizedbceloss": 17, "bcewithlogitsloss": 17, "quantizedbcewithlogitsloss": 17, "bilinear": [17, 29], "quantizedbilinear": 17, "ctcloss": 17, "quantizedctcloss": 17, "cosinesimilar": 17, "quantizedcosinesimilar": 17, "crossentropyloss": [17, 19], "quantizedcrossentropyloss": 17, "hingeembeddingloss": 17, "quantizedhingeembeddingloss": 17, "huberloss": 17, "quantizedhuberloss": 17, "kldivloss": 17, "quantizedkldivloss": 17, "l1loss": 17, "quantizedl1loss": 17, "mseloss": 17, "quantizedmseloss": 17, "multilabelmarginloss": 17, "quantizedmultilabelmarginloss": 17, "multilabelsoftmarginloss": 17, "quantizedmultilabelsoftmarginloss": 17, "multimarginloss": 17, "quantizedmultimarginloss": 17, "nllloss": 17, "quantizednllloss": 17, "nllloss2d": 17, "quantizednllloss2d": 17, "pairwisedist": 17, "quantizedpairwisedist": 17, "poissonnllloss": 17, "quantizedpoissonnllloss": 17, "smoothl1loss": 17, "quantizedsmoothl1loss": 17, "softmarginloss": 17, "quantizedsoftmarginloss": 17, "cosineembeddingloss": 17, "quantizedcosineembeddingloss": 17, "gaussiannllloss": 17, "quantizedgaussiannllloss": 17, "marginrankingloss": 17, "quantizedmarginrankingloss": 17, "tripletmarginloss": 17, "quantizedtripletmarginloss": 17, "tripletmarginwithdistanceloss": 17, "quantizedtripletmarginwithdistanceloss": 17, "embed": [17, 28, 35], "quantizedembed": 17, "embeddingbag": 17, "quantizedembeddingbag": 17, "gru": [17, 37], "quantizedgru": 17, "rnn": [17, 37], "quantizedrnn": 17, "grucel": 17, "quantizedgrucel": 17, "rnncell": 17, "quantizedrnncel": 17, "lstm": [17, 37], "quantizedlstm": 17, "lstmcell": 17, "quantizedlstmcel": 17, "cumsum": 17, "quantizedcumsum": 17, "sin": 17, "quantizedsin": 17, "co": 17, "quantizedco": 17, "rsqrt": 17, "quantizedrsqrt": 17, "reshap": 17, "quantizedreshap": 17, "matmul": [17, 37], "quantizedmatmul": 17, "subtract": 17, "quantizedsubtract": 17, "quantizeddivid": 17, "bmm": 17, "quantizedbmm": 17, "baddbmm": 17, "quantizedbaddbmm": 17, "addmm": 17, "quantizedaddmm": 17, "concat": [17, 37], "quantizedconcat": 17, "allow_overwit": 18, "get_encod": 18, "get_legacy_encod": 18, "register_quantization_paramet": 18, "set_legacy_encod": 18, "tutori": 19, "simpl": 19, "intend": 19, "It": [19, 22, 23, 25, 33, 42], "meant": 19, "demonstr": 19, "state": 19, "art": 19, "eval": [19, 25, 28, 39], "loop": [19, 35], "evalu": [19, 21, 25, 28, 30, 32, 33, 36, 39], "clearli": 19, "what": [19, 39], "happen": 19, "let": 19, "special": 19, "look": [19, 21], "torchvis": 19, "is_avail": 19, "els": [19, 31], "loader": [19, 20], "cifar10_train_data": 19, "dataset": [19, 30, 31, 36], "fashionmnist": 19, "tmp": 19, "cifar10": 19, "totensor": 19, "cifar10_test_data": 19, "train_load": 19, "batch_siz": 19, "shuffl": 19, "test_load": 19, "conv1": 19, "kernel_s": 19, "pad": 19, "stride": 19, "bn_1": 19, "bn_2": 19, "total": [19, 25, 36], "argmax": 19, "sum": 19, "few": [19, 24], "epoch": [19, 26, 28, 33], "establish": 19, "baselin": [19, 25, 28, 33], "send": 19, "loss_fn": 19, "adam": 19, "lr": 19, "1e": [19, 33], "batch_idx": 19, "enumer": 19, "backward": 19, "zero_grad": 19, "fp_accuraci": 19, "91": 19, "70999908447266": 19, "accur": 19, "coupl": 19, "care": [19, 28], "conform": 19, "guidelin": [19, 30, 33], "wherea": [19, 36], "incorrectli": 19, "ignor": 19, "previou": [19, 24, 35], "complet": [19, 22, 35], "redefin": 19, "thankfulli": 19, "model_prepar": 19, "incompat": 19, "fulli": [19, 27, 28, 41], "prepared_model": 19, "prepare_model": 19, "fp_accuracy_prepar": 19, "assert": 19, "2024": 19, "07": 19, "747": 19, "info": [19, 37], "806": 19, "modelprepar": 19, "ad": [19, 27, 34, 37], "node": [19, 33, 36], "module_relu": 19, "module_relu_1": 19, "module_softmax": 19, "graphmodul": 19, "ep": 19, "momentum": 19, "track_running_stat": 19, "12544": 19, "getattr_1": 19, "getitem": 19, "debug": [19, 35], "graph_modul": 19, "print_read": 19, "distinct": 19, "adjac": [19, 34], "whenev": 19, "unnecessari": [19, 42], "good": [19, 20, 28], "idea": 19, "batch_norm_fold": 19, "iter": [19, 20, 31], "fold_all_batch_norm": 19, "input_shap": 19, "ident": 19, "passthrough": 19, "previous": 19, "had": 19, "impact": [19, 25, 35], "readi": [19, 35], "e": [19, 22], "therefor": [19, 24, 31], "theoret": 19, "could": [19, 42], "practic": [19, 28], "usual": [19, 28, 33, 36], "500": [19, 20, 31, 32], "1000": [19, 20, 31, 32], "estim": [19, 30, 31], "idx": 19, "break": 19, "quantized_accuraci": 19, "1500015258789": 19, "noth": 19, "everi": [19, 25, 28, 33, 40], "discuss": [19, 24, 36], "advanc": 19, "re": [19, 30], "One": 19, "op": [19, 34, 36, 37], "repeat": [19, 23], "post_qat_accuraci": 19, "92": 19, "05333709716797": 19, "happi": 19, "export_path": 19, "model_nam": 19, "fashion_mnist_model": 19, "sent": 19, "nearest": 20, "illustr": [20, 23, 25, 30, 36, 38, 39, 41, 42], "figur": [20, 23, 25, 35, 38, 39, 41, 42], "unlabel": [20, 30, 32], "far": 20, "decid": [20, 39], "whether": [20, 25, 33], "closer": 20, "fp32": [20, 26, 31, 32, 33, 35, 36], "width": [20, 35, 36, 38, 41, 42], "freez": 20, "terminologi": 20, "abbrevi": 20, "bc": 20, "bnf": 20, "batch": [20, 30, 31, 32], "norm": [20, 30, 31, 32], "cle": [20, 21, 30, 35, 37], "cross": [20, 21, 29, 30, 32, 35, 40], "hbf": 20, "sequenc": [20, 21, 22, 29, 34], "help": [20, 25, 28, 30, 31, 32, 33, 35, 40], "might": [20, 32, 35], "speed": [20, 28, 31, 33, 37], "Not": [20, 25], "expos": [20, 32], "stabl": 20, "mani": [20, 24, 31], "often": [20, 21, 28, 33], "approxim": [20, 24, 31, 32], "16x": 20, "1024": [20, 29], "10000": 20, "caution": 20, "avoid": [20, 24], "beta": 20, "warm": 20, "period": 20, "kera": [20, 22, 26, 30, 31, 32, 34, 36, 37], "offer": 21, "suit": 21, "best": [21, 24, 28, 30, 36], "toler": [21, 24], "soon": 21, "reach": 21, "stop": 21, "try": [21, 23, 24, 28, 30, 35], "prone": 21, "consum": [21, 28], "prepar": [21, 30, 37], "check": [21, 30, 33, 35], "friendli": [21, 30, 31], "preprat": 21, "proce": 21, "three": [21, 24, 40], "batchnorm": [21, 31, 42], "effort": 21, "manner": 21, "fail": [21, 29, 30], "goal": 21, "small": [22, 26, 30], "preceed": 22, "learn": [22, 28, 30, 33, 36, 37], "pcq": [22, 32], "scenario": [22, 42], "decreas": 22, "main": [22, 34, 37, 40], "issu": [22, 26, 29, 35, 37, 39, 40], "depthwis": [22, 37], "oscil": 22, "quant": 22, "diagram": [22, 26, 36], "cp": [23, 24, 25, 42], "occurr": 23, "explain": [23, 28, 31, 36], "ratio": [23, 24], "magnitud": 23, "upstream": [23, 42], "gain": [23, 24, 28], "connect": [23, 27, 28, 41], "residu": 23, "sometim": [23, 28, 31, 32], "prevent": [23, 29], "regress": 23, "random": [23, 32], "against": 23, "outlin": 24, "svd": [24, 25, 27, 28, 37], "spatial": [24, 25, 27, 28, 37], "prune": [24, 25, 27, 28, 37, 42], "accumul": [24, 28], "mac": [24, 28, 38, 41], "reduct": [24, 30], "uncompress": 24, "algorithm": [24, 25, 28, 35, 42], "overal": [24, 25, 35], "latenc": 24, "bandwidth": 24, "vari": [24, 31, 40], "websit": 24, "At": [24, 39], "half": 24, "unknown": 24, "ssvd": 24, "f0": 24, "65": 24, "75": 24, "yield": [24, 35, 36], "pick": [24, 25], "2b": 24, "rel": [24, 35, 40], "sai": 24, "veri": [24, 28, 32, 40], "larg": [24, 33, 38, 41], "revisit": 24, "close": [24, 36], "resnet": 24, "50": 24, "assess": 25, "sensit": [25, 30, 32, 35, 36, 37], "find": [25, 30, 32, 33, 36], "maintain": [25, 28], "highest": 25, "dictionari": [25, 28, 34], "column": 25, "score": [25, 28, 39], "unmodifi": 25, "compris": 25, "candid": [25, 28], "omit": [25, 34], "monoton": 25, "fit": 25, "procedur": [25, 39], "curv": 25, "account": [25, 30, 33, 35], "constant": [25, 30], "interpol": 25, "solut": [25, 33, 35], "accept": [25, 31, 35], "suggest": [25, 28, 31], "vice": [25, 35, 36], "versa": [25, 35, 36], "fall": [25, 34], "drastic": 25, "softwar": 26, "framework": [26, 30, 34, 36], "meta": [26, 30], "checkpoint": [26, 30], "h5": [26, 30], "hardwar": [26, 30, 31, 36], "ptq": [26, 30, 32, 33], "redund": 26, "smaller": [26, 35, 38, 41], "limit": 27, "dilat": 27, "modules_to_ignor": 27, "depthwiseconv2d": 27, "last": 27, "librari": 28, "littl": 28, "variou": [28, 30, 35, 36, 37, 40], "singular": [28, 38, 41], "decomposit": [28, 38, 41], "guidebook": 28, "summari": 28, "phase": 28, "inspect": 28, "choic": [28, 36], "greedi": [28, 39], "decompos": [28, 38, 41], "fc": [28, 41], "ml": [28, 30, 31], "give": 28, "tri": [28, 30], "caus": [28, 29, 30, 34, 35], "sharp": 28, "rate": [28, 33], "decai": 28, "respons": 28, "Then": 28, "slow": 28, "someth": 28, "itself": [28, 36, 38], "searcher": 28, "Or": 28, "fewer": 28, "wors": 28, "strike": 28, "balanc": 28, "major": 28, "But": 28, "seem": [28, 30], "xiangyu": 28, "zhang": 28, "jianhua": 28, "zou": 28, "kaim": 28, "he": 28, "jian": 28, "sun": 28, "deep": 28, "classif": 28, "detect": 28, "transact": 28, "pattern": 28, "analysi": [28, 35], "intellig": 28, "vol": 28, "pp": 28, "1943": 28, "1955": 28, "oct": 28, "2016": 28, "yihui": 28, "confer": [28, 31], "vision": [28, 31], "iccv": [28, 31], "venic": 28, "2017": 28, "1398": 28, "1406": 28, "jaderberg": 28, "andrea": 28, "vedaldi": 28, "andrew": 28, "zisserman": 28, "british": 28, "jan": 28, "2014": 28, "andrei": 28, "kuzmin": 28, "marku": [28, 31], "nagel": [28, 31], "saurabh": 28, "pitr": 28, "sandeep": 28, "pendyam": 28, "tijmen": [28, 31], "blankevoort": [28, 31], "taxonomi": 28, "cross_layer_equ": 29, "equalize_model": 29, "potenti": [29, 39, 40], "workaround": 29, "applic": 29, "primit": 29, "sure": 29, "rewrit": 29, "slice": 29, "written": [29, 30], "statement": 29, "align_corn": 29, "deconvolut": 29, "dconvolut": 29, "deeplabv3": 29, "address": [29, 35, 39], "releas": 29, "howev": [30, 31], "briefli": 30, "move": 30, "retrain": 30, "becaus": 30, "pipelin": [30, 33, 35, 36], "suffici": [30, 32, 33, 36], "fast": 30, "easi": 30, "insert": [30, 36], "robust": 30, "longer": [30, 33], "_aimet": 30, "trainabl": 30, "bias": 30, "remain": [30, 31, 36], "reflect": [30, 36], "autoqu": [30, 33, 37], "integr": 30, "standalon": 30, "consecut": [30, 31], "bn": [30, 32, 37], "deprec": 30, "quantanalyz": [30, 37], "autom": 30, "understand": [30, 40], "prep": 30, "attempt": [30, 31], "accord": 30, "complainc": 30, "align": 30, "flow": [30, 35, 36], "put": 30, "retri": 30, "continu": [30, 31, 33, 35], "warn": 30, "hand": 30, "ref": 30, "satisfactori": [30, 35], "onto": 30, "item": 30, "pb": 30, "trial": [30, 35], "diagnost": 30, "becom": 31, "design": 31, "paper": 31, "2019": 31, "arxiv": 31, "ab": 31, "1906": 31, "04721": 31, "surround": 31, "highlight": [31, 39, 40], "big": 31, "discrep": 31, "off": 31, "wide": 31, "varianc": 31, "seen": [31, 32], "significantli": 31, "quantizaion": 31, "shown": [31, 32, 35, 42], "distribut": [31, 35, 36], "did": 31, "shift": 31, "empir": 31, "analyt": [31, 39], "extract": 31, "bottleneck": [31, 35], "hybrid": 31, "approach": [31, 36], "mart": 31, "van": 31, "baalen": 31, "seoul": 31, "octob": 31, "analys": 32, "area": 32, "hotspot": 32, "callback": [32, 36], "mse": [32, 36], "label": [32, 33], "metric": [32, 36], "relat": [32, 36], "doc": 32, "normal": 32, "benefici": 32, "situat": 32, "log": 32, "pinpoint": 32, "culprit": 32, "again": [32, 33], "per_layer_quant_en": 32, "per_layer_quant_dis": 32, "axi": 32, "directli": [32, 36], "min_max_rang": 32, "folder": 32, "enhanc": [32, 36], "delet": 32, "displai": [32, 39, 40], "activations_pdf": 32, "weights_pdf": 32, "squar": [32, 36], "monitor": 32, "contribut": [32, 35], "read": 32, "per_layer_mse_loss": 32, "presenc": 33, "hyperparamet": 33, "converg": 33, "hyper": 33, "schedul": 33, "fuse": [34, 36], "placement": 34, "config": [34, 37], "six": 34, "turn": 34, "op_typ": 34, "empti": 34, "is_output_quant": 34, "is_quant": 34, "strict_symmetr": 34, "unsigned_symmetr": 34, "outsid": 34, "strict": [34, 36], "unsign": [34, 36], "rather": 34, "throughout": [34, 40], "gemm": 34, "is_input_quant": 34, "keep": 34, "convent": 34, "supergroup": [34, 37], "made": 34, "op_list": 34, "member": 34, "sequenti": [34, 35], "branch": 34, "those": 34, "entri": 34, "string": 34, "model_input": 34, "model_output": 34, "insight": [35, 39, 40], "why": 35, "underperform": 35, "chart": 35, "confid": 35, "independ": 35, "kept": 35, "toward": 35, "uneven": 35, "global": 35, "restor": 35, "consid": [35, 38, 41], "rest": 35, "inner": 35, "token": 35, "bert": 35, "reveal": 35, "problemat": [35, 40], "problem": 35, "resort": 35, "revert": 35, "power": 35, "mitig": 36, "recogn": 36, "copi": 36, "ingest": 36, "feed": 36, "000": 36, "de": 36, "hook": 36, "intercept": 36, "four": 36, "textrm": 36, "dfrac": 36, "elimin": 36, "extrem": 36, "induc": 36, "signal": 36, "satur": 36, "erro": 36, "static": 36, "alongsid": 36, "just": [36, 42], "settabl": 36, "non": [36, 39], "intermedi": 36, "slim": 37, "backslash": 37, "io": 37, "user_guid": 37, "api_doc": 37, "quantizablemultiheadattent": 37, "kyuykim": 37, "multi": 37, "mangal": 37, "geunle": 37, "bug": 37, "correctli": 37, "klhsieh": 37, "akhobar": 37, "multiheadattent": 37, "ashvkuma": 37, "mha": 37, "pdf": 37, "abil": 37, "fp16": 37, "minor": 37, "stand": 37, "adaptiveround": 37, "recurr": 37, "\ud835\udc5a": [38, 41], "\ud835\udc5b": [38, 41], "\u210e": [38, 41], "\ud835\udc64": [38, 41], "height": [38, 41, 42], "\ud835\udc58": [38, 41], "rank": [38, 41], "degre": [38, 41], "augment": 39, "progress": [39, 40], "computation": [39, 40], "task": [39, 40], "arrang": 39, "websocket": 39, "listen": 39, "5006": 39, "compress_model": 39, "display_eval_scor": 39, "display_comp_ratio_plot": 39, "visualizecompress": 39, "lot": 40, "term": 41, "anoth": [41, 42], "lose": 42, "much": 42, "volum": 42, "hxwx8": 42, "hxwx5": 42, "preced": 42, "propag": 42, "That": 42, "downstream": 42, "denot": 42, "green": 42, "side": 42, "action": 42, "taken": 42, "pink": 42, "color": 42, "orang": 42, "Its": 42}, "objects": {"aimet_torch.gptvq.defs": [[15, 0, 1, "", "GPTVQParameters"]], "aimet_torch.gptvq.gptvq_weight.GPTVQ": [[15, 1, 1, "", "apply_gptvq"]], "aimet_torch.v2.nn": [[17, 0, 1, "", "QuantizationMixin"]], "aimet_torch.v2.nn.QuantizationMixin": [[17, 2, 1, "", "__quant_init__"], [17, 2, 1, "", "compute_encodings"], [17, 2, 1, "", "forward"], [6, 2, 1, "", "from_module"], [6, 2, 1, "", "get_default_kernel"], [6, 2, 1, "", "get_kernel"], [6, 2, 1, "", "implements"], [17, 3, 1, "", "input_quantizers"], [17, 3, 1, "", "output_quantizers"], [17, 3, 1, "", "param_quantizers"], [6, 2, 1, "", "set_default_kernel"], [6, 2, 1, "", "set_kernel"]], "aimet_torch.v2.quantization": [[7, 4, 0, "-", "affine"], [9, 4, 0, "-", "float"]], "aimet_torch.v2.quantization.affine": [[7, 0, 1, "", "Quantize"], [7, 0, 1, "", "QuantizeDequantize"], [7, 1, 1, "", "dequantize"], [7, 1, 1, "", "quantize"], [7, 1, 1, "", "quantize_dequantize"]], "aimet_torch.v2.quantization.affine.quantizer": [[18, 0, 1, "", "Quantize"], [18, 0, 1, "", "QuantizeDequantize"], [18, 0, 1, "", "QuantizerBase"]], "aimet_torch.v2.quantization.affine.quantizer.Quantize": [[18, 2, 1, "", "forward"]], "aimet_torch.v2.quantization.affine.quantizer.QuantizeDequantize": [[18, 2, 1, "", "forward"]], "aimet_torch.v2.quantization.affine.quantizer.QuantizerBase": [[18, 2, 1, "", "allow_overwrite"], [18, 2, 1, "", "compute_encodings"], [18, 2, 1, "", "get_encoding"], [18, 2, 1, "", "get_legacy_encodings"], [18, 2, 1, "", "is_initialized"], [18, 2, 1, "", "register_quantization_parameter"], [18, 2, 1, "", "set_legacy_encodings"]], "aimet_torch.v2.quantization.encoding_analyzer": [[13, 0, 1, "", "EncodingAnalyzer"], [13, 0, 1, "", "MinMaxEncodingAnalyzer"], [13, 0, 1, "", "PercentileEncodingAnalyzer"], [13, 0, 1, "", "SqnrEncodingAnalyzer"]], "aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer": [[13, 2, 1, "", "compute_encodings"], [13, 2, 1, "", "reset_stats"], [13, 2, 1, "", "update_stats"]], "aimet_torch.v2.quantization.float": [[9, 0, 1, "", "FloatQuantizeDequantize"], [9, 0, 1, "", "QuantizeDequantize"]], "aimet_torch.v2.quantization.tensor": [[10, 0, 1, "", "DequantizedTensor"], [10, 0, 1, "", "QuantizedTensor"]], "aimet_torch.v2.quantization.tensor.DequantizedTensor": [[10, 2, 1, "", "dequantize"], [10, 2, 1, "", "quantize"], [10, 2, 1, "", "quantized_repr"]], "aimet_torch.v2.quantization.tensor.QuantizedTensor": [[10, 2, 1, "", "dequantize"], [10, 2, 1, "", "quantize"], [10, 2, 1, "", "quantized_repr"]], "aimet_torch.v2.quantsim.config_utils": [[12, 1, 1, "", "set_activation_quantizers_to_float"], [12, 1, 1, "", "set_blockwise_quantization_for_weights"], [12, 1, 1, "", "set_grouped_blockwise_quantization_for_weights"]], "aimet_torch.v2.visualization_tools": [[11, 1, 1, "", "visualize_stats"]]}, "objtypes": {"0": "py:class", "1": "py:function", "2": "py:method", "3": "py:attribute", "4": "py:module"}, "objnames": {"0": ["py", "class", "Python class"], "1": ["py", "function", "Python function"], "2": ["py", "method", "Python method"], "3": ["py", "attribute", "Python attribute"], "4": ["py", "module", "Python module"]}, "titleterms": {"aimet": [2, 3, 4, 16, 20, 21, 22, 23, 24, 25, 27, 28, 30, 31, 32, 33, 35, 36, 37, 38, 39, 40, 41, 42], "instal": [2, 3, 4], "quick": 2, "releas": [2, 3, 4, 26, 37], "packag": [2, 3, 4], "system": 2, "requir": [2, 32], "advanc": 2, "instruct": 2, "docker": 3, "set": 3, "variant": [3, 13], "us": [3, 20, 28, 30], "prebuilt": 3, "imag": 3, "build": 3, "local": 3, "start": [3, 16, 39], "contain": 3, "from": [3, 4], "pypi": [3, 4], "environ": [3, 4], "setup": [3, 4], "prerequisit": [4, 19], "gpu": 4, "pytorch": [4, 16, 19, 29, 30, 40], "2": [4, 19, 37], "1": [4, 19, 37], "13": [4, 37], "onnx": 4, "tensorflow": [4, 40], "common": 4, "debian": 4, "torch": 4, "replac": 4, "pillow": 4, "simd": 4, "onnxruntim": 4, "post": [4, 14, 30, 31], "step": 4, "quantizationmixin": 6, "quantiz": [7, 9, 10, 12, 14, 17, 18, 19, 30, 31, 33, 34, 35, 36, 40], "affin": 7, "class": [7, 9, 10, 17], "function": 7, "floatquantizedequant": 8, "quantizedequant": 8, "float": [9, 19], "tensor": 10, "visual": [11, 39, 40], "tool": [11, 30], "blockwis": 12, "low": 12, "power": 12, "lpbq": 12, "top": [12, 15, 17, 18], "level": [12, 15, 17, 18], "api": [12, 15, 16, 17, 18, 20, 21, 22, 31, 32, 36], "export": [12, 19], "encod": [13, 17, 36], "analyz": 13, "train": [14, 19, 30, 31, 33], "gptvq": 15, "paramet": [15, 20, 36], "code": 15, "exampl": [15, 16], "ai": [16, 26], "model": [16, 19, 26, 28, 29, 30], "effici": [16, 26], "toolkit": [16, 26], "document": 16, "get": 16, "featur": [16, 24, 26, 30], "descript": [16, 32], "modul": 17, "configur": [17, 34, 36], "comput": 17, "quickstart": 19, "guid": [19, 26], "overal": 19, "flow": [19, 31], "prepar": 19, "point": 19, "batchnorm": 19, "fold": 19, "fine": [19, 28], "tune": [19, 28], "awar": [19, 33], "quantsim": [19, 36], "adaround": 20, "case": [20, 28, 30], "hyper": 20, "guidelin": [20, 29], "autoqu": 21, "overview": [21, 22, 25, 26, 28, 31, 32, 33, 34, 36, 39, 40, 42], "workflow": [21, 22, 30, 33, 36], "batch": 22, "norm": 22, "re": 22, "estim": 22, "bn": 22, "channel": 23, "prune": 23, "procedur": 23, "select": [23, 25, 28], "winnow": [23, 42], "weight": [23, 41], "reconstruct": 23, "compress": [24, 25, 28, 39], "guidebook": 24, "greedi": 25, "ratio": [25, 28, 39], "how": [25, 42], "work": [25, 42], "per": [25, 28], "layer": [25, 28, 31], "explor": 25, "user": [26, 31], "more": 26, "inform": 26, "toc": 26, "tree": 26, "known": 27, "issu": 27, "option": 28, "techniqu": [28, 31], "rank": 28, "round": 28, "note": [28, 37], "faq": [28, 31], "refer": [28, 31], "debug": 30, "analysi": [30, 32], "cross": 31, "equal": 31, "quantanalyz": 32, "detail": 32, "qat": 33, "mode": 33, "recommend": 33, "simul": [34, 36], "file": 34, "structur": 34, "modifi": 34, "section": 34, "diagnost": 35, "nois": 36, "determin": 36, "scheme": 36, "oper": 36, "22": 37, "0": 37, "21": 37, "20": 37, "19": 37, "py37": 37, "18": 37, "17": 37, "16": 37, "14": 37, "spatial": 38, "svd": [38, 41], "design": 39, "bokeh": 39, "server": 39, "session": 39}, "envversion": {"sphinx.domains.c": 2, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 8, "sphinx.domains.index": 1, "sphinx.domains.javascript": 2, "sphinx.domains.math": 2, "sphinx.domains.python": 3, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "nbsphinx": 4, "sphinx.ext.intersphinx": 1, "sphinx.ext.viewcode": 1, "sphinx": 57}, "alltitles": {"AIMET Installation": [[2, "aimet-installation"]], "Quick Install": [[2, "quick-install"]], "Release Packages": [[2, "release-packages"]], "System Requirements": [[2, "system-requirements"]], "Advanced Installation Instructions": [[2, "advanced-installation-instructions"]], "AIMET Installation in Docker": [[3, "aimet-installation-in-docker"]], "Set variant": [[3, "set-variant"]], "Use prebuilt docker image": [[3, "use-prebuilt-docker-image"]], "Build docker image locally": [[3, "build-docker-image-locally"]], "Start docker container": [[3, "start-docker-container"]], "Install AIMET packages": [[3, "install-aimet-packages"], [4, "install-aimet-packages"]], "From PyPI": [[3, "from-pypi"], [4, "from-pypi"]], "From Release Package": [[3, "from-release-package"], [4, "from-release-package"]], "Environment setup": [[3, "environment-setup"], [4, "environment-setup"]], "AIMET Installation and Setup": [[4, "aimet-installation-and-setup"]], "Install prerequisite packages": [[4, "install-prerequisite-packages"]], "Install GPU packages": [[4, "install-gpu-packages"]], "Install GPU packages for PyTorch 2.1 or PyTorch 1.13 or ONNX or TensorFlow": [[4, "install-gpu-packages-for-pytorch-2-1-or-pytorch-1-13-or-onnx-or-tensorflow"]], "Install common debian packages": [[4, "install-common-debian-packages"]], "Install tensorflow GPU debian packages": [[4, "install-tensorflow-gpu-debian-packages"]], "Install torch GPU debian packages": [[4, "install-torch-gpu-debian-packages"]], "Install ONNX GPU debian packages": [[4, "install-onnx-gpu-debian-packages"]], "Replace Pillow with Pillow-SIMD": [[4, "replace-pillow-with-pillow-simd"]], "Replace onnxruntime with onnxruntime-gpu": [[4, "replace-onnxruntime-with-onnxruntime-gpu"]], "Post installation steps": [[4, "post-installation-steps"]], "QuantizationMixin": [[6, "quantizationmixin"]], "quantization.affine": [[7, "module-aimet_torch.v2.quantization.affine"]], "Classes": [[7, "classes"], [9, "classes"], [10, "classes"]], "Functions": [[7, "functions"]], "FloatQuantizeDequantize": [[8, "floatquantizedequantize"]], "QuantizeDequantize": [[8, "quantizedequantize"]], "quantization.float": [[9, "module-aimet_torch.v2.quantization.float"]], "quantization.tensor": [[10, "quantization-tensor"]], "Visualization Tools": [[11, "visualization-tools"]], "Blockwise Quantization": [[12, "blockwise-quantization"]], "Low Power Blockwise Quantization (LPBQ)": [[12, "low-power-blockwise-quantization-lpbq"]], "Top Level API": [[12, "top-level-api"], [15, "top-level-api"]], "Export": [[12, "export"]], "Encoding Analyzers": [[13, "encoding-analyzers"]], "Variants": [[13, "variants"]], "Post-Training Quantization": [[14, "post-training-quantization"], [30, "post-training-quantization"]], "GPTVQ": [[15, "gptvq"]], "GPTVQ Parameters": [[15, "gptvq-parameters"]], "Code Example": [[15, "code-example"]], "AIMET: AI Model Efficiency Toolkit Documentation": [[16, "aimet-ai-model-efficiency-toolkit-documentation"]], "Getting Started": [[16, "getting-started"]], "Examples": [[16, null]], "Feature Descriptions": [[16, null]], "AIMET PyTorch API": [[16, null]], "Quantized Modules": [[17, "quantized-modules"]], "Top-level API": [[17, "top-level-api"], [18, "top-level-api"]], "Configuration": [[17, "configuration"]], "Computing Encodings": [[17, "computing-encodings"]], "Quantized Module Classes": [[17, "quantized-module-classes"]], "Quantizers": [[18, "quantizers"]], "Quickstart Guide": [[19, "quickstart-guide"]], "Overall flow": [[19, "overall-flow"]], "PyTorch prerequisites": [[19, "pytorch-prerequisites"]], "Prepare the floating point model for quantization": [[19, "prepare-the-floating-point-model-for-quantization"]], "1) Model preparation": [[19, "model-preparation"]], "2) BatchNorm fold": [[19, "batchnorm-fold"]], "Quantize the model": [[19, "quantize-the-model"]], "Fine-tune the model with quantization aware training": [[19, "fine-tune-the-model-with-quantization-aware-training"]], "Export the quantsim model": [[19, "export-the-quantsim-model"]], "AIMET AdaRound": [[20, "aimet-adaround"]], "AdaRound use cases": [[20, "adaround-use-cases"]], "AdaRound hyper parameters guidelines": [[20, "adaround-hyper-parameters-guidelines"]], "AdaRound API": [[20, "adaround-api"]], "AIMET AutoQuant": [[21, "aimet-autoquant"]], "Overview": [[21, "overview"], [22, "overview"], [25, "overview"], [26, "overview"], [28, "overview"], [31, "overview"], [32, "overview"], [33, "overview"], [34, "overview"], [36, "overview"], [39, "overview"], [40, "overview"], [42, "overview"]], "Workflow": [[21, "workflow"], [22, "workflow"]], "AutoQuant API": [[21, "autoquant-api"]], "AIMET Batch Norm Re-estimation": [[22, "aimet-batch-norm-re-estimation"]], "BN Re-estimation API": [[22, "bn-re-estimation-api"]], "AIMET channel pruning": [[23, "aimet-channel-pruning"]], "Procedure": [[23, "procedure"]], "Channel selection": [[23, "channel-selection"]], "Winnowing": [[23, "winnowing"]], "Weight reconstruction": [[23, "weight-reconstruction"]], "AIMET Compression Features Guidebook": [[24, "aimet-compression-features-guidebook"]], "AIMET greedy compression ratio selection": [[25, "aimet-greedy-compression-ratio-selection"]], "How it works": [[25, "how-it-works"]], "Per-layer exploration": [[25, "per-layer-exploration"]], "Compression ratio selection": [[25, "compression-ratio-selection"], [28, "compression-ratio-selection"]], "AI Model Efficiency Toolkit User Guide": [[26, "ai-model-efficiency-toolkit-user-guide"]], "Features": [[26, "features"]], "More Information": [[26, "more-information"]], "Release Information": [[26, "release-information"]], "toc tree": [[26, "toc-tree"]], "AIMET Known Issues": [[27, "aimet-known-issues"]], "AIMET model compression": [[28, "aimet-model-compression"]], "Use Case": [[28, "use-case"]], "Model compression": [[28, "model-compression"]], "Optional techniques": [[28, "optional-techniques"]], "Rank Rounding": [[28, "rank-rounding"]], "Per-layer fine-tuning": [[28, "per-layer-fine-tuning"]], "NOTE": [[28, null]], "FAQs": [[28, "faqs"], [31, "faqs"]], "References": [[28, "references"], [31, "references"]], "Model Guidelines for PyTorch": [[29, "model-guidelines-for-pytorch"]], "AIMET model quantization": [[30, "aimet-model-quantization"]], "Use cases": [[30, "use-cases"]], "AIMET quantization features": [[30, "aimet-quantization-features"]], "Debugging and Analysis Tools": [[30, "debugging-and-analysis-tools"]], "AIMET quantization workflow": [[30, "aimet-quantization-workflow"]], "PyTorch": [[30, "pytorch"], [40, "pytorch"]], "Debugging": [[30, "debugging"]], "AIMET post-training quantization techniques": [[31, "aimet-post-training-quantization-techniques"]], "User Flow": [[31, "user-flow"]], "Cross-Layer Equalization API": [[31, "cross-layer-equalization-api"]], "AIMET QuantAnalyzer": [[32, "aimet-quantanalyzer"]], "Requirements": [[32, "requirements"]], "Detailed analysis descriptions": [[32, "detailed-analysis-descriptions"]], "QuantAnalyzer API": [[32, "quantanalyzer-api"]], "AIMET quantization aware training": [[33, "aimet-quantization-aware-training"]], "QAT workflow": [[33, "qat-workflow"]], "QAT modes": [[33, "qat-modes"]], "Recommendations for quantization-aware training": [[33, "recommendations-for-quantization-aware-training"]], "Quantization simulation configuration": [[34, "quantization-simulation-configuration"]], "Configuration file structure": [[34, "configuration-file-structure"]], "Modifying configuration file sections": [[34, "modifying-configuration-file-sections"]], "AIMET quantization diagnostics": [[35, "aimet-quantization-diagnostics"]], "AIMET quantization simulation": [[36, "aimet-quantization-simulation"]], "QuantSim workflow": [[36, "quantsim-workflow"]], "Simulating quantization noise": [[36, "simulating-quantization-noise"]], "Determining quantization parameters (encodings)": [[36, "determining-quantization-parameters-encodings"]], "Quantization schemes": [[36, "quantization-schemes"]], "Configuring quantization simulation operations": [[36, "configuring-quantization-simulation-operations"]], "Quantization Simulation APIs": [[36, "quantization-simulation-apis"]], "AIMET Release Notes": [[37, "aimet-release-notes"]], "1.22.2": [[37, "id1"]], "1.22.1": [[37, "id2"]], "1.22.0": [[37, "id3"]], "1.21.0": [[37, "id4"]], "1.20.0": [[37, "id5"]], "1.19.1.py37": [[37, "py37"]], "1.19.1": [[37, "id6"]], "1.18.0.py37": [[37, "id7"]], "1.18.0": [[37, "id8"]], "1.17.0.py37": [[37, "id9"]], "1.17.0": [[37, "id10"]], "1.16.2.py37": [[37, "id11"]], "1.16.2": [[37, "id12"]], "1.16.1.py37": [[37, "id13"]], "1.16.1": [[37, "id14"]], "1.16.0": [[37, "id15"]], "1.14.0": [[37, "id16"]], "1.13.0": [[37, "id17"]], "AIMET spatial SVD": [[38, "aimet-spatial-svd"]], "AIMET visualization": [[39, "aimet-visualization"]], "Design": [[39, "design"]], "Compression": [[39, "compression"]], "Starting a Bokeh server session": [[39, "starting-a-bokeh-server-session"]], "Visualizing compression ratios": [[39, "visualizing-compression-ratios"]], "AIMET visualization for quantization": [[40, "aimet-visualization-for-quantization"]], "Quantization": [[40, "quantization"]], "TensorFlow": [[40, "tensorflow"]], "AIMET weight SVD": [[41, "aimet-weight-svd"]], "AIMET winnowing": [[42, "aimet-winnowing"]], "Winnowing overview": [[42, "winnowing-overview"]], "How winnowing works": [[42, "how-winnowing-works"]]}, "indexentries": {"quantizationmixin (class in aimet_torch.v2.nn)": [[6, "aimet_torch.v2.nn.QuantizationMixin"], [17, "aimet_torch.v2.nn.QuantizationMixin"]], "__quant_init__() (aimet_torch.v2.nn.quantizationmixin method)": [[6, "aimet_torch.v2.nn.QuantizationMixin.__quant_init__"], [17, "aimet_torch.v2.nn.QuantizationMixin.__quant_init__"]], "compute_encodings() (aimet_torch.v2.nn.quantizationmixin method)": [[6, "aimet_torch.v2.nn.QuantizationMixin.compute_encodings"], [17, "aimet_torch.v2.nn.QuantizationMixin.compute_encodings"]], "forward() (aimet_torch.v2.nn.quantizationmixin method)": [[6, "aimet_torch.v2.nn.QuantizationMixin.forward"], [17, "aimet_torch.v2.nn.QuantizationMixin.forward"]], "from_module() (aimet_torch.v2.nn.quantizationmixin class method)": [[6, "aimet_torch.v2.nn.QuantizationMixin.from_module"]], "get_default_kernel() (aimet_torch.v2.nn.quantizationmixin class method)": [[6, "aimet_torch.v2.nn.QuantizationMixin.get_default_kernel"]], "get_kernel() (aimet_torch.v2.nn.quantizationmixin method)": [[6, "aimet_torch.v2.nn.QuantizationMixin.get_kernel"]], "implements() (aimet_torch.v2.nn.quantizationmixin class method)": [[6, "aimet_torch.v2.nn.QuantizationMixin.implements"]], "input_quantizers (aimet_torch.v2.nn.quantizationmixin attribute)": [[6, "aimet_torch.v2.nn.QuantizationMixin.input_quantizers"], [17, "aimet_torch.v2.nn.QuantizationMixin.input_quantizers"]], "output_quantizers (aimet_torch.v2.nn.quantizationmixin attribute)": [[6, "aimet_torch.v2.nn.QuantizationMixin.output_quantizers"], [17, "aimet_torch.v2.nn.QuantizationMixin.output_quantizers"]], "param_quantizers (aimet_torch.v2.nn.quantizationmixin attribute)": [[6, "aimet_torch.v2.nn.QuantizationMixin.param_quantizers"], [17, "aimet_torch.v2.nn.QuantizationMixin.param_quantizers"]], "set_default_kernel() (aimet_torch.v2.nn.quantizationmixin class method)": [[6, "aimet_torch.v2.nn.QuantizationMixin.set_default_kernel"]], "set_kernel() (aimet_torch.v2.nn.quantizationmixin method)": [[6, "aimet_torch.v2.nn.QuantizationMixin.set_kernel"]], "quantize (class in aimet_torch.v2.quantization.affine)": [[7, "aimet_torch.v2.quantization.affine.Quantize"]], "quantizedequantize (class in aimet_torch.v2.quantization.affine)": [[7, "aimet_torch.v2.quantization.affine.QuantizeDequantize"]], "aimet_torch.v2.quantization.affine": [[7, "module-aimet_torch.v2.quantization.affine"]], "dequantize() (in module aimet_torch.v2.quantization.affine)": [[7, "aimet_torch.v2.quantization.affine.dequantize"]], "module": [[7, "module-aimet_torch.v2.quantization.affine"], [9, "module-aimet_torch.v2.quantization.float"]], "quantize() (in module aimet_torch.v2.quantization.affine)": [[7, "aimet_torch.v2.quantization.affine.quantize"]], "quantize_dequantize() (in module aimet_torch.v2.quantization.affine)": [[7, "aimet_torch.v2.quantization.affine.quantize_dequantize"]], "floatquantizedequantize (class in aimet_torch.v2.quantization.float)": [[8, "aimet_torch.v2.quantization.float.FloatQuantizeDequantize"], [9, "aimet_torch.v2.quantization.float.FloatQuantizeDequantize"]], "quantizedequantize (class in aimet_torch.v2.quantization.float)": [[8, "aimet_torch.v2.quantization.float.QuantizeDequantize"], [9, "aimet_torch.v2.quantization.float.QuantizeDequantize"]], "aimet_torch.v2.quantization.float": [[9, "module-aimet_torch.v2.quantization.float"]], "dequantizedtensor (class in aimet_torch.v2.quantization.tensor)": [[10, "aimet_torch.v2.quantization.tensor.DequantizedTensor"]], "quantizedtensor (class in aimet_torch.v2.quantization.tensor)": [[10, "aimet_torch.v2.quantization.tensor.QuantizedTensor"]], "dequantize() (aimet_torch.v2.quantization.tensor.dequantizedtensor method)": [[10, "aimet_torch.v2.quantization.tensor.DequantizedTensor.dequantize"]], "dequantize() (aimet_torch.v2.quantization.tensor.quantizedtensor method)": [[10, "aimet_torch.v2.quantization.tensor.QuantizedTensor.dequantize"]], "quantize() (aimet_torch.v2.quantization.tensor.dequantizedtensor method)": [[10, "aimet_torch.v2.quantization.tensor.DequantizedTensor.quantize"]], "quantize() (aimet_torch.v2.quantization.tensor.quantizedtensor method)": [[10, "aimet_torch.v2.quantization.tensor.QuantizedTensor.quantize"]], "quantized_repr() (aimet_torch.v2.quantization.tensor.dequantizedtensor method)": [[10, "aimet_torch.v2.quantization.tensor.DequantizedTensor.quantized_repr"]], "quantized_repr() (aimet_torch.v2.quantization.tensor.quantizedtensor method)": [[10, "aimet_torch.v2.quantization.tensor.QuantizedTensor.quantized_repr"]], "visualize_stats() (in module aimet_torch.v2.visualization_tools)": [[11, "aimet_torch.v2.visualization_tools.visualize_stats"]], "set_activation_quantizers_to_float() (in module aimet_torch.v2.quantsim.config_utils)": [[12, "aimet_torch.v2.quantsim.config_utils.set_activation_quantizers_to_float"]], "set_blockwise_quantization_for_weights() (in module aimet_torch.v2.quantsim.config_utils)": [[12, "aimet_torch.v2.quantsim.config_utils.set_blockwise_quantization_for_weights"]], "set_grouped_blockwise_quantization_for_weights() (in module aimet_torch.v2.quantsim.config_utils)": [[12, "aimet_torch.v2.quantsim.config_utils.set_grouped_blockwise_quantization_for_weights"]], "encodinganalyzer (class in aimet_torch.v2.quantization.encoding_analyzer)": [[13, "aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer"]], "minmaxencodinganalyzer (class in aimet_torch.v2.quantization.encoding_analyzer)": [[13, "aimet_torch.v2.quantization.encoding_analyzer.MinMaxEncodingAnalyzer"]], "percentileencodinganalyzer (class in aimet_torch.v2.quantization.encoding_analyzer)": [[13, "aimet_torch.v2.quantization.encoding_analyzer.PercentileEncodingAnalyzer"]], "sqnrencodinganalyzer (class in aimet_torch.v2.quantization.encoding_analyzer)": [[13, "aimet_torch.v2.quantization.encoding_analyzer.SqnrEncodingAnalyzer"]], "compute_encodings() (aimet_torch.v2.quantization.encoding_analyzer.encodinganalyzer method)": [[13, "aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.compute_encodings"]], "reset_stats() (aimet_torch.v2.quantization.encoding_analyzer.encodinganalyzer method)": [[13, "aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.reset_stats"]], "update_stats() (aimet_torch.v2.quantization.encoding_analyzer.encodinganalyzer method)": [[13, "aimet_torch.v2.quantization.encoding_analyzer.EncodingAnalyzer.update_stats"]], "gptvqparameters (class in aimet_torch.gptvq.defs)": [[15, "aimet_torch.gptvq.defs.GPTVQParameters"]], "apply_gptvq() (in module aimet_torch.gptvq.gptvq_weight.gptvq)": [[15, "aimet_torch.gptvq.gptvq_weight.GPTVQ.apply_gptvq"]], "quantize (class in aimet_torch.v2.quantization.affine.quantizer)": [[18, "aimet_torch.v2.quantization.affine.quantizer.Quantize"]], "quantizedequantize (class in aimet_torch.v2.quantization.affine.quantizer)": [[18, "aimet_torch.v2.quantization.affine.quantizer.QuantizeDequantize"]], "quantizerbase (class in aimet_torch.v2.quantization.affine.quantizer)": [[18, "aimet_torch.v2.quantization.affine.quantizer.QuantizerBase"]], "allow_overwrite() (aimet_torch.v2.quantization.affine.quantizer.quantizerbase method)": [[18, "aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.allow_overwrite"]], "compute_encodings() (aimet_torch.v2.quantization.affine.quantizer.quantizerbase method)": [[18, "aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.compute_encodings"]], "forward() (aimet_torch.v2.quantization.affine.quantizer.quantize method)": [[18, "aimet_torch.v2.quantization.affine.quantizer.Quantize.forward"]], "forward() (aimet_torch.v2.quantization.affine.quantizer.quantizedequantize method)": [[18, "aimet_torch.v2.quantization.affine.quantizer.QuantizeDequantize.forward"]], "get_encoding() (aimet_torch.v2.quantization.affine.quantizer.quantizerbase method)": [[18, "aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.get_encoding"]], "get_legacy_encodings() (aimet_torch.v2.quantization.affine.quantizer.quantizerbase method)": [[18, "aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.get_legacy_encodings"]], "is_initialized() (aimet_torch.v2.quantization.affine.quantizer.quantizerbase method)": [[18, "aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.is_initialized"]], "register_quantization_parameter() (aimet_torch.v2.quantization.affine.quantizer.quantizerbase method)": [[18, "aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.register_quantization_parameter"]], "set_legacy_encodings() (aimet_torch.v2.quantization.affine.quantizer.quantizerbase method)": [[18, "aimet_torch.v2.quantization.affine.quantizer.QuantizerBase.set_legacy_encodings"]]}})
\ No newline at end of file