Update 0.23.0 - OSS release

.dockerignore

@@ -1,6 +1,7 @@
 docker
-**/.git
-llm_ptq/saved_models*
+examples/**/.git
+examples/llm_ptq/saved_models*
+**/experimental
 
 ##### Copied from .gitignore #####
 # Byte-compiled / optimized / DLL files

.pre-commit-config.yaml

@@ -0,0 +1,145 @@
+# NOTE: Make sure to update version in dev requirements (setup.py) as well!
+exclude: >
+  (?x)^(
+      experimental/.*|
+  )$
+
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.6.0
+    hooks:
+      - id: trailing-whitespace
+      - id: mixed-line-ending
+        args: [--fix=lf]
+      - id: end-of-file-fixer
+      - id: check-merge-conflict
+      - id: requirements-txt-fixer
+      - id: debug-statements
+      - id: check-json
+        exclude: ^.vscode/.*.json # vscode files can take comments
+      - id: check-yaml
+        args: [--allow-multiple-documents]
+      - id: check-toml
+      - id: check-added-large-files
+        args: [--maxkb=500, --enforce-all]
+        exclude: >
+          (?x)^(
+              examples/diffusers/quantization/assets/.*.png|
+              examples/diffusers/cache_diffusion/assets/.*.png|
+          )$
+
+  - repo: https://github.com/executablebooks/mdformat
+    rev: 0.7.17
+    hooks:
+      - id: mdformat
+
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.6.4
+    hooks:
+      - id: ruff
+        args: [--fix, --exit-non-zero-on-fix]
+      - id: ruff-format
+
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.11.2
+    hooks:
+      - id: mypy
+
+  - repo: https://github.com/pre-commit/mirrors-clang-format
+    rev: v16.0.4
+    hooks:
+      - id: clang-format
+        types_or: [c++, c, c#, cuda, java, javascript, objective-c, proto] # no json!
+        args: ["--style={ColumnLimit: 100}"]
+
+  - repo: https://github.com/pre-commit/pygrep-hooks
+    rev: v1.10.0
+    hooks:
+      - id: rst-backticks
+      - id: rst-directive-colons
+      - id: rst-inline-touching-normal
+
+  - repo: https://github.com/jumanjihouse/pre-commit-hook-yamlfmt
+    rev: 0.2.3
+    hooks:
+      - id: yamlfmt
+        args: [--mapping=2, --sequence=4, --offset=2, --implicit_start, --implicit_end, --preserve-quotes]
+        exclude: ^.github/workflows/
+
+  # Instructions to change license file if ever needed:
+  # https://github.com/Lucas-C/pre-commit-hooks#removing-old-license-and-replacing-it-with-a-new-one
+  - repo: https://github.com/Lucas-C/pre-commit-hooks
+    rev: v1.5.5
+    hooks:
+      # Default hook for Apache 2.0 in core python files
+      - id: insert-license
+        alias: insert-license-py
+        args:
+          - --license-filepath
+          - ./LICENSE
+          - --comment-style
+          - "#"
+          - --allow-past-years
+        types: [python]
+        # NOTE: Exclude files that have copyright or license headers from another company or individual
+        # since we want to keep those above the license header added by this hook.
+        # Instead, we should manually add the license header to those files after the original header.
+        exclude: >
+          (?x)^(
+              modelopt/onnx/quantization/operators.py|
+              modelopt/onnx/quantization/ort_patching.py|
+              modelopt/torch/export/transformer_engine.py|
+              modelopt/torch/quantization/export_onnx.py|
+              modelopt/torch/quantization/plugins/attention.py|
+              modelopt/torch/speculative/plugins/transformers.py|
+              modelopt/torch/speculative/eagle/utils.py|
+              modelopt/torch/_deploy/utils/onnx_utils.py|
+              examples/chained_optimizations/bert_prune_distill_quantize.py|
+              examples/diffusers/quantization/onnx_utils/export.py|
+              examples/diffusers/cache_diffusion/pipeline/models/sdxl.py|
+              examples/llm_eval/gen_model_answer.py|
+              examples/llm_eval/humaneval.py|
+              examples/llm_eval/lm_eval_hf.py|
+              examples/llm_eval/mmlu.py|
+              examples/llm_eval/modeling.py|
+              examples/llm_sparsity/finetune.py|
+              examples/llm_qat/main.py|
+              examples/speculative_decoding/main.py|
+              examples/speculative_decoding/medusa_utils.py|
+              examples/speculative_decoding/vllm_generate.py|
+          )$
+
+      # Default hook for Apache 2.0 in core c/c++/cuda files
+      - id: insert-license
+        alias: insert-license-c
+        args:
+          - --license-filepath
+          - ./LICENSE
+          - --comment-style
+          - "/*| *| */"
+          - --allow-past-years
+        types_or: [c++, cuda, c]
+
+      # Default hook for Apache 2.0 in shell files
+      - id: insert-license
+        alias: insert-license-sh
+        args:
+          - --license-filepath
+          - ./LICENSE
+          - --comment-style
+          - "#"
+          - --allow-past-years
+        types_or: [shell]
+
+  - repo: https://github.com/keith/pre-commit-buildifier
+    rev: 6.4.0
+    hooks:
+      - id: buildifier
+      - id: buildifier-lint
+
+  - repo: https://github.com/PyCQA/bandit
+    rev: 1.7.9
+    hooks:
+      - id: bandit
+        args: ["-c", "pyproject.toml", "-q"]
+        additional_dependencies: ["bandit[toml]"]

.vscode/extensions.json

@@ -0,0 +1,28 @@
+{
+	// See https://go.microsoft.com/fwlink/?LinkId=827846 to learn about workspace recommendations.
+	// Extension identifier format: ${publisher}.${name}. Example: vscode.csharp
+	// List of extensions which should be recommended for users of this workspace.
+	"recommendations": [
+		"ms-vscode.cpptools",
+		"ms-azuretools.vscode-docker",
+		"tamasfe.even-better-toml",
+		"GitHub.copilot",
+		"GitLab.gitlab-workflow",
+		"eamodio.gitlens",
+		"VisualStudioExptTeam.vscodeintellicode",
+		"ms-toolsai.jupyter",
+		"ms-python.vscode-pylance",
+		"ms-python.python",
+		"ms-vscode-remote.remote-ssh",
+		"ms-vscode.remote-explorer",
+		"charliermarsh.ruff",
+		"redhat.vscode-yaml",
+	],
+	// List of extensions recommended by VS Code that should not be recommended for users of this workspace.
+	"unwantedRecommendations": [
+		"ms-python.black-formatter",
+		"ms-python.mypy-type-checker",
+		"ms-python.pylint",
+		"ms-python.flake8",
+	]
+}

.vscode/settings.json

@@ -0,0 +1,43 @@
+// VSCode workspace settings for modelopt
+{
+    "editor.rulers": [
+        100,
+        120
+    ], // 100 for black auto-formatter, 120 for hard limit in ruff
+    "[python]": {
+        "editor.defaultFormatter": "charliermarsh.ruff",
+        "editor.formatOnSave": true,
+        "editor.codeActionsOnSave": {
+            "source.fixAll": "explicit"
+        },
+    },
+    "files.exclude": {
+        "build": true,
+    },
+    "files.watcherExclude": {
+        ".ipynb_checkpoints": true,
+        ".mypy_cache": true,
+        ".pytest_cache": true,
+        ".ruff_cache": true,
+        ".tox": true,
+        "**/__pycache__/**": true,
+        "**/*.pyc": true,
+        "**/runs": true,
+        "build": true
+    },
+    "[yaml]": {
+        "editor.defaultFormatter": "redhat.vscode-yaml",
+    },
+    "yaml.format.enable": true,
+    "yaml.format.printWidth": 150,
+    "yaml.format.bracketSpacing": false,
+    "yaml.customTags": [
+        "!reference sequence"
+    ],
+    "python.testing.pytestEnabled": true,
+    "python.testing.pytestArgs": [
+        "./tests",
+        "--no-cov",
+    ],
+    "evenBetterToml.schema.enabled": false, // disable toml/json schema since we have custom fields
+}

CHANGELOG-Windows.rst

@@ -0,0 +1,18 @@
+===================================
+Model Optimizer Changelog (Windows)
+===================================
+
+0.19 (2024-11-18)
+^^^^^^^^^^^^^^^^^
+
+**New Features**
+
+- This is the first official release of TensorRT Model Optimizer for Windows
+- **ONNX INT4 Quantization:** :meth:`modelopt.onnx.quantization.quantize_int4 <modelopt.onnx.quantization.int4.quantize>` now supports ONNX INT4 quantization for DirectML and TensorRT* deployment. See :ref:`Support_Matrix` for details about supported features and models.
+- **LLM Quantization with Olive:** Enabled LLM quantization through Olive, streamlining model optimization workflows. Refer `example <https://github.com/microsoft/Olive/tree/main/examples/phi3#quantize-models-with-nvidia-tensorrt-model-optimizer>`_
+- **DirectML Deployment Guide:** Added DML deployment guide. Refer :ref:`DirectML_Deployment`.
+- **MMLU Benchmark for Accuracy Evaluations:** Introduced `MMLU benchmarking <https://github.com/NVIDIA/TensorRT-Model-Optimizer/tree/main/examples/windows/accuracy_benchmark/README.md>`_ for accuracy evaluation of ONNX models on DirectML (DML).
+- **Published quantized ONNX models collection:** Published quantized ONNX models at HuggingFace `NVIDIA collections <https://huggingface.co/collections/nvidia/optimized-onnx-models-for-nvidia-rtx-gpus-67373fe7c006ebc1df310613>`_.
+
+
+\* *This version includes experimental features such as TensorRT deployment of ONNX INT4 models, PyTorch quantization and sparsity. These are currently unverified on Windows.*