From b5871e20f180694fd1973f90ee6e4fcbb952a927 Mon Sep 17 00:00:00 2001 From: Matthias Reso <13337103+mreso@users.noreply.github.com> Date: Fri, 28 Feb 2025 12:07:13 -0800 Subject: [PATCH] Add limited maintenance notice (#3395) --- CODE_OF_CONDUCT.md | 4 +++ CONTRIBUTING.md | 4 +++ README.md | 4 +++ SECURITY.md | 4 +++ benchmarks/README.md | 4 +++ benchmarks/add_jmeter_test.md | 14 +++++--- benchmarks/jmeter.md | 4 +++ benchmarks/sample_report.md | 4 +++ binaries/README.md | 36 ++++++++++--------- binaries/conda/README.md | 7 ++-- cpp/README.md | 4 +++ docker/README.md | 4 +++ docs/FAQs.md | 4 +++ docs/README.md | 4 +++ docs/Troubleshooting.md | 4 +++ docs/batch_inference_with_ts.md | 4 +++ docs/code_coverage.md | 4 +++ docs/configuration.md | 4 +++ docs/custom_service.md | 14 +++++--- docs/default_handlers.md | 4 +++ docs/genai_use_cases.md | 6 +++- docs/getting_started.md | 4 +++ docs/github_actions.md | 4 +++ docs/grpc_api.md | 4 +++ docs/hardware_support/amd_support.md | 4 +++ .../hardware_support/apple_silicon_support.md | 4 +++ docs/hardware_support/linux_aarch64.md | 4 +++ docs/hardware_support/nvidia_mps.md | 4 +++ docs/inference_api.md | 4 +++ docs/internals.md | 12 ++++--- docs/large_model_inference.md | 4 +++ docs/llm_deployment.md | 4 +++ docs/logging.md | 4 +++ docs/management_api.md | 4 +++ docs/metrics.md | 4 +++ docs/metrics_api.md | 4 +++ docs/model_api_control.md | 4 +++ docs/model_loading.md | 4 +++ docs/model_zoo.md | 12 ++++--- docs/performance_checklist.md | 4 +++ docs/performance_guide.md | 4 +++ docs/request_envelopes.md | 4 +++ docs/rest_api.md | 4 +++ docs/server.md | 4 +++ docs/snapshot.md | 14 +++++--- docs/token_authorization_api.md | 4 +++ docs/torchserve_on_win_native.md | 4 +++ docs/torchserve_on_wsl.md | 4 +++ docs/use_cases.md | 4 +++ docs/workflow_inference_api.md | 4 +++ docs/workflow_management_api.md | 4 +++ docs/workflows.md | 14 +++++--- .../README.md | 4 +++ examples/Huggingface_Transformers/README.md | 4 +++ .../Huggingface_Transformers/torchscript.md | 4 +++ examples/LLM/llama/README.md | 4 +++ examples/LLM/llama/chat_app/Readme.md | 4 +++ examples/MMF-activity-recognition/README.md | 4 +++ examples/README.md | 4 +++ examples/Workflows/README.md | 4 +++ .../dog_breed_classification/README.md | 4 +++ .../nmt_transformers_pipeline/README.md | 4 +++ examples/asr_rnnt_emformer/README.md | 10 ++++-- examples/benchmarking/resnet50/README.md | 4 +++ .../cloud_storage_stream_inference/README.md | 4 +++ examples/cloudformation/README.md | 4 +++ examples/cpp/aot_inductor/bert/README.md | 4 +++ examples/cpp/aot_inductor/llama2/README.md | 4 +++ examples/cpp/aot_inductor/resnet/README.md | 4 +++ examples/cpp/babyllama/README.md | 4 +++ examples/cpp/llamacpp/README.md | 4 +++ examples/custom_endpoint_plugin/README.md | 13 ++++--- examples/custom_metrics/README.md | 4 +++ examples/dcgan_fashiongen/Readme.md | 4 +++ examples/diffusers/Readme.md | 4 +++ examples/image_classifier/README.md | 5 ++- examples/image_classifier/alexnet/README.md | 4 +++ .../image_classifier/densenet_161/README.md | 4 +++ examples/image_classifier/mnist/Docker.md | 4 +++ examples/image_classifier/mnist/README.md | 4 +++ .../near_real_time_video/README.md | 4 +++ .../resnet_152_batch/README.md | 4 +++ examples/image_classifier/resnet_18/README.md | 4 +++ .../resnet_18/ReactJSExample/README.md | 4 +++ .../image_classifier/squeezenet/README.md | 6 +++- examples/image_classifier/vgg_16/README.md | 4 +++ examples/image_segmenter/README.md | 4 +++ examples/image_segmenter/deeplabv3/README.md | 4 +++ examples/image_segmenter/fcn/README.md | 4 +++ examples/instruction_embedding/README.md | 4 +++ .../intel_extension_for_pytorch/README.md | 4 +++ .../Huggingface_accelerate/Readme.md | 4 +++ .../Huggingface_accelerate/llama/Readme.md | 4 +++ .../large_models/Huggingface_pippy/Readme.md | 4 +++ examples/large_models/deepspeed/Readme.md | 4 +++ .../large_models/deepspeed_mii/LLM/Readme.md | 4 +++ examples/large_models/deepspeed_mii/Readme.md | 4 +++ .../large_models/diffusion_fast/README.md | 4 +++ examples/large_models/gpt_fast/README.md | 4 +++ .../gpt_fast_mixtral_moe/README.md | 4 +++ .../large_models/inferentia2/llama/Readme.md | 4 +++ .../llama/continuous_batching/Readme.md | 4 +++ .../inferentia2/llama/streamer/Readme.md | 4 +++ .../large_models/inferentia2/opt/Readme.md | 4 +++ examples/large_models/ipex_llm_int8/README.md | 6 +++- .../segment_anything_fast/README.md | 4 +++ examples/large_models/tp_llama/README.md | 4 +++ examples/large_models/trt_llm/llama/README.md | 4 +++ examples/large_models/trt_llm/lora/README.md | 4 +++ examples/large_models/vllm/Readme.md | 4 +++ examples/large_models/vllm/llama3/Readme.md | 4 +++ examples/large_models/vllm/lora/Readme.md | 4 +++ examples/large_models/vllm/mistral/Readme.md | 4 +++ examples/micro_batching/README.md | 4 +++ examples/nmt_transformer/README.md | 4 +++ examples/nvidia_dali/README.md | 4 +++ examples/object_detector/README.md | 4 +++ examples/object_detector/fast-rcnn/README.md | 4 +++ examples/object_detector/maskrcnn/README.md | 4 +++ .../object_detector/yolo/yolov8/README.md | 4 +++ examples/pt2/README.md | 4 +++ examples/pt2/torch_compile/README.md | 4 +++ examples/pt2/torch_compile_hpu/README.md | 4 +++ examples/pt2/torch_compile_openvino/README.md | 4 +++ .../stable_diffusion/README.md | 4 +++ .../pt2/torch_export_aot_compile/README.md | 4 +++ examples/pt2/torch_inductor_caching/README.md | 4 +++ examples/speech2text_wav2vec2/README.md | 4 +++ examples/stateful/sequence_batching/Readme.md | 4 +++ .../sequence_continuous_batching/Readme.md | 4 +++ examples/text_classification/README.md | 4 +++ .../README.md | 4 +++ .../SpeechT5/README.md | 4 +++ .../WaveGlow/README.md | 4 +++ .../torch_tensorrt/torchcompile/T5/README.md | 4 +++ .../torchcompile/resnet50/README.md | 4 +++ examples/torch_tensorrt/torchscript/README.md | 4 +++ examples/torchrec_dlrm/README.md | 4 +++ .../usecases/RAG_based_LLM_serving/Deploy.md | 4 +++ .../usecases/RAG_based_LLM_serving/README.md | 4 +++ .../llm_diffusion_serving_app/README.md | 18 ++++++---- examples/xgboost_classfication/README.md | 4 +++ frontend/README.md | 4 +++ kubernetes/AKS/README.md | 4 +++ kubernetes/EKS/README.md | 4 +++ kubernetes/GKE/README.md | 12 ++++--- kubernetes/README.md | 4 +++ kubernetes/autoscale.md | 6 +++- .../FasterTransformer_HuggingFace_Bert.md | 4 +++ kubernetes/examples/mnist/MNIST.md | 4 +++ kubernetes/kserve/README.md | 4 +++ kubernetes/kserve/developer_guide.md | 4 +++ kubernetes/kserve/examples/gpt_fast/README.md | 4 +++ kubernetes/kserve/examples/mnist/MNIST.md | 4 +++ kubernetes/kserve/image_transformer/README.md | 4 +++ .../kserve/kf_request_json/v1/README.md | 4 +++ .../kserve/kf_request_json/v2/bert/README.md | 4 +++ .../kserve/kf_request_json/v2/mnist/README.md | 4 +++ kubernetes/kserve/kserve_wrapper/README.md | 4 +++ model-archiver/README.md | 6 +++- plugins/docs/README.md | 18 ++++++---- plugins/docs/ddb_endpoint.md | 12 ++++--- test/README.md | 8 +++-- test/data_file_config.md | 4 +++ .../preprocess/built-in/Readme.md | 4 +++ ts/tests/README.md | 4 +++ workflow-archiver/README.md | 8 +++-- 167 files changed, 751 insertions(+), 86 deletions(-) diff --git a/CODE_OF_CONDUCT.md b/CODE_OF_CONDUCT.md index 566caaaea0..e832c5abb8 100644 --- a/CODE_OF_CONDUCT.md +++ b/CODE_OF_CONDUCT.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Code of Conduct ## Our Pledge diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index 952bb1fb5b..2b209fe57e 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + ## Contributing to TorchServe ### Merging your code diff --git a/README.md b/README.md index 200dcc5269..ae75d436cd 100644 --- a/README.md +++ b/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # ❗ANNOUNCEMENT: Security Changes❗ TorchServe now enforces token authorization enabled and model API control disabled by default. These security features are intended to address the concern of unauthorized API calls and to prevent potential malicious code from being introduced to the model server. Refer the following documentation for more information: [Token Authorization](https://github.com/pytorch/serve/blob/master/docs/token_authorization_api.md), [Model API control](https://github.com/pytorch/serve/blob/master/docs/model_api_control.md) diff --git a/SECURITY.md b/SECURITY.md index c1426afa64..08ce56d067 100644 --- a/SECURITY.md +++ b/SECURITY.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Security Policy ## Supported Versions diff --git a/benchmarks/README.md b/benchmarks/README.md index c555599cfe..65ba6d468c 100644 --- a/benchmarks/README.md +++ b/benchmarks/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Torchserve Model Server Benchmarking The benchmarks measure the performance of TorchServe on various models and benchmarks. It supports either a number of built-in models or a custom model passed in as a path or URL to the .mar file. It also runs various benchmarks using these models (see benchmarks section below). The benchmarks are executed in the user machine through a python3 script in case of jmeter and a shell script in case of apache benchmark. TorchServe is run on the same machine in a docker instance to avoid network latencies. The benchmark must be run from within `serve/benchmarks` diff --git a/benchmarks/add_jmeter_test.md b/benchmarks/add_jmeter_test.md index 4f8e790909..2d5bc7ea7b 100644 --- a/benchmarks/add_jmeter_test.md +++ b/benchmarks/add_jmeter_test.md @@ -1,16 +1,20 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + ## Adding a new test plan for torchserve A new Jmeter test plan for torchserve benchmark can be added as follows: * Assuming you know how to create a jmeter test plan. If not then please use this jmeter [guide](https://jmeter.apache.org/usermanual/build-test-plan.html) * Here, we will show you how 'MMS Benchmarking Image Input Model Test Plan' plan can be added. -This test plan does following: - +This test plan does following: + * Register a model - `default is resnet-18` * Scale up to add workers for inference * Send Inference request in a loop * Unregister a model - + (NOTE - This is an existing plan in `serve/benchmarks`) * Open jmeter GUI e.g. on macOS, type `jmeter` on commandline @@ -63,7 +67,7 @@ You can create variables or use them directly in your test plan. * input_filepath - input image file for prediction * min_workers - minimum workers to be launch for serving inference request -NOTE - +NOTE - * In above, screenshot, some variables/input box are partially displayed. You can view details by opening an existing test cases from serve/benchmarks/jmx for details. -* Apart from above argument, you can define custom arguments specific to you test plan if needed. Refer `benchmark.py` for details \ No newline at end of file +* Apart from above argument, you can define custom arguments specific to you test plan if needed. Refer `benchmark.py` for details diff --git a/benchmarks/jmeter.md b/benchmarks/jmeter.md index d0c639a293..70898ec60b 100644 --- a/benchmarks/jmeter.md +++ b/benchmarks/jmeter.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Benchmarking with JMeter ## Installation diff --git a/benchmarks/sample_report.md b/benchmarks/sample_report.md index 9899f030ed..91e1bd5ffc 100644 --- a/benchmarks/sample_report.md +++ b/benchmarks/sample_report.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + TorchServe Benchmark on gpu =========================== diff --git a/binaries/README.md b/binaries/README.md index f1ab370d99..8fac43b52b 100644 --- a/binaries/README.md +++ b/binaries/README.md @@ -1,4 +1,8 @@ -# Building TorchServe and Torch-Model-Archiver release binaries +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + +# Building TorchServe and Torch-Model-Archiver release binaries 1. Make sure all the dependencies are installed ##### Linux and macOS: ```bash @@ -10,8 +14,8 @@ python .\ts_scripts\install_dependencies.py --environment=dev ``` > For GPU with Cuda 10.2, make sure add the `--cuda cu102` arg to the above command - - + + 2. To build a `torchserve` and `torch-model-archiver` wheel execute: ##### Linux and macOS: ```bash @@ -22,23 +26,23 @@ python .\binaries\build.py ``` - > If the scripts detect a conda environment, it also builds torchserve conda packages + > If the scripts detect a conda environment, it also builds torchserve conda packages > For additional info on conda builds refer to [this readme](conda/README.md) 3. Build outputs are located at ##### Linux and macOS: - Wheel files - `dist/torchserve-*.whl` + `dist/torchserve-*.whl` `model-archiver/dist/torch_model_archiver-*.whl` `workflow-archiver/dist/torch_workflow_archiver-*.whl` - Conda pacakages - `binaries/conda/output/*` - + `binaries/conda/output/*` + ##### Windows: - Wheel files - `dist\torchserve-*.whl` - `model-archiver\dist\torch_model_archiver-*.whl` - `workflow-archiver\dist\torch_workflow_archiver-*.whl` + `dist\torchserve-*.whl` + `model-archiver\dist\torch_model_archiver-*.whl` + `workflow-archiver\dist\torch_workflow_archiver-*.whl` - Conda pacakages `binaries\conda\output\*` @@ -74,7 +78,7 @@ ```bash conda install --channel ./binaries/conda/output -y torchserve torch-model-archiver torch-workflow-archiver ``` - + ##### Windows: Conda install is currently not supported. Please use pip install command instead. @@ -147,9 +151,9 @@ exec bash python3 binaries/build.py cd binaries/ - python3 upload.py --upload-pypi-packages --upload-conda-packages + python3 upload.py --upload-pypi-packages --upload-conda-packages ``` -4. To upload *.whl files to S3 bucket, run the following command: +4. To upload *.whl files to S3 bucket, run the following command: Note: `--nightly` option puts the *.whl files in a subfolder named 'nightly' in the specified bucket ``` python s3_binary_upload.py --s3-bucket --s3-backup-bucket --nightly @@ -157,7 +161,7 @@ ## Uploading packages to production torchserve account -As a first step binaries and docker containers need to be available in some staging environment. In that scenario the binaries can just be `wget`'d and then uploaded using the instructions below and the docker staging environment just needs a 1 line code change in https://github.com/pytorch/serve/blob/master/docker/promote-docker.sh#L8 +As a first step binaries and docker containers need to be available in some staging environment. In that scenario the binaries can just be `wget`'d and then uploaded using the instructions below and the docker staging environment just needs a 1 line code change in https://github.com/pytorch/serve/blob/2a0ce756b179677f905c3216b9c8427cd530a129/docker/promote-docker.sh#L8 ### pypi Binaries should show up here: https://pypi.org/project/torchserve/ @@ -182,7 +186,7 @@ anaconda upload -u pytorch ## docker Binaries should show up here: https://hub.docker.com/r/pytorch/torchserve -Change the staging org to your personal docker or test docker account https://github.com/pytorch/serve/blob/master/docker/promote-docker.sh#L8 +Change the staging org to your personal docker or test docker account https://github.com/pytorch/serve/blob/2a0ce756b179677f905c3216b9c8427cd530a129/docker/promote-docker.sh#L8 ### Direct upload @@ -197,7 +201,7 @@ For an official release our tags include `pytorch/torchserve/-cp ## Direct upload Kserve To build the Kserve docker image follow instructions from [kubernetes/kserve](../kubernetes/kserve/README.md) -When tagging images for an official release make sure to tag with the following format `pytorch/torchserve-kfs/-cpu` and `pytorch/torchserve-kfs/-gpu`. +When tagging images for an official release make sure to tag with the following format `pytorch/torchserve-kfs/-cpu` and `pytorch/torchserve-kfs/-gpu`. ### Uploading from staging account diff --git a/binaries/conda/README.md b/binaries/conda/README.md index d0696f6b8f..36f1812c6e 100644 --- a/binaries/conda/README.md +++ b/binaries/conda/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Building conda packages 1. To build conda packages you must first produce wheels for the project, see [this readme](../README.md) for more details on building `torchserve` and `torch-model-archiver` wheel files. @@ -9,7 +13,7 @@ ``` # Build all packages python build_packages.py - + # Selectively build packages python build_packages.py --ts-wheel=/path/to/torchserve.whl --ma-wheel=/path/to/torch_model_archiver_wheel --wa-wheel=/path/to/torch_workflow_archiver_wheel ``` @@ -21,4 +25,3 @@ The built conda packages are available in the `output` directory Anaconda packages are both OS specific and python version specific so copying them one by one from a test/staging environment like https://anaconda.org/pytorch/torchserve/ to an official environment like https://anaconda.org/torchserve-staging can be fiddly Instead you can run `anaconda copy torchserve-staging// --to-owner pytorch` - diff --git a/cpp/README.md b/cpp/README.md index 9c722ed2e0..8c7e4a0423 100644 --- a/cpp/README.md +++ b/cpp/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # TorchServe CPP (Experimental Release) ## Requirements * C++17 diff --git a/docker/README.md b/docker/README.md index 9e5ca8a229..7ddd9d01a0 100644 --- a/docker/README.md +++ b/docker/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + ## Security Changes TorchServe now enforces token authorization enabled and model API control disabled by default. Refer the following documentation for more information: [Token Authorization](https://github.com/pytorch/serve/blob/master/docs/token_authorization_api.md), [Model API control](https://github.com/pytorch/serve/blob/master/docs/model_api_control.md) diff --git a/docs/FAQs.md b/docs/FAQs.md index 348414d765..1629c614df 100644 --- a/docs/FAQs.md +++ b/docs/FAQs.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # FAQ'S Contents of this document. * [General](#general) diff --git a/docs/README.md b/docs/README.md index 25baa813fe..d4ba5fc200 100644 --- a/docs/README.md +++ b/docs/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # ❗ANNOUNCEMENT: Security Changes❗ TorchServe now enforces token authorization enabled and model API control disabled by default. These security features are intended to address the concern of unauthorized API calls and to prevent potential malicious code from being introduced to the model server. Refer the following documentation for more information: [Token Authorization](https://github.com/pytorch/serve/blob/master/docs/token_authorization_api.md), [Model API control](https://github.com/pytorch/serve/blob/master/docs/model_api_control.md) diff --git a/docs/Troubleshooting.md b/docs/Troubleshooting.md index edb7d48246..88457f5dc4 100644 --- a/docs/Troubleshooting.md +++ b/docs/Troubleshooting.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + ## Troubleshooting Guide Refer to this section for common issues faced while deploying your Pytorch models using Torchserve and their corresponding troubleshooting steps. diff --git a/docs/batch_inference_with_ts.md b/docs/batch_inference_with_ts.md index 3ff04be63b..3b17d5e232 100644 --- a/docs/batch_inference_with_ts.md +++ b/docs/batch_inference_with_ts.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Batch Inference with TorchServe ## Contents of this Document diff --git a/docs/code_coverage.md b/docs/code_coverage.md index 7f5082cc70..4c5fb4f34b 100644 --- a/docs/code_coverage.md +++ b/docs/code_coverage.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Code Coverage ## To check branch stability run the sanity suite as follows diff --git a/docs/configuration.md b/docs/configuration.md index d9fe733ab5..49fb09b333 100644 --- a/docs/configuration.md +++ b/docs/configuration.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Advanced configuration The default settings form TorchServe should be sufficient for most use cases. However, if you want to customize TorchServe, the configuration options described in this topic are available. diff --git a/docs/custom_service.md b/docs/custom_service.md index 2a40625503..bb88a0c046 100755 --- a/docs/custom_service.md +++ b/docs/custom_service.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Custom Service ## Contents of this Document @@ -257,12 +261,12 @@ Refer [waveglow_handler](https://github.com/pytorch/serve/blob/master/examples/t Torchserve returns the captum explanations for Image Classification, Text Classification and BERT models. It is achieved by placing the below request: `POST /explanations/{model_name}` -The explanations are written as a part of the explain_handle method of base handler. The base handler invokes this explain_handle_method. The arguments that are passed to the explain handle methods are the pre-processed data and the raw data. It invokes the get insights function of the custom handler that returns the captum attributions. The user should write his own get_insights functionality to get the explanations +The explanations are written as a part of the explain_handle method of base handler. The base handler invokes this explain_handle_method. The arguments that are passed to the explain handle methods are the pre-processed data and the raw data. It invokes the get insights function of the custom handler that returns the captum attributions. The user should write his own get_insights functionality to get the explanations -For serving a custom handler the captum algorithm should be initialized in the initialize functions of the handler +For serving a custom handler the captum algorithm should be initialized in the initialize functions of the handler The user can override the explain_handle function in the custom handler. -The user should define their get_insights method for custom handler to get Captum Attributions. +The user should define their get_insights method for custom handler to get Captum Attributions. The above ModelHandler class should have the following methods with captum functionality. @@ -292,7 +296,7 @@ The above ModelHandler class should have the following methods with captum funct else : model_output = self.explain_handle(model_input, data) return model_output - + # Present in the base_handler, so override only when neccessary def explain_handle(self, data_preprocess, raw_data): """Captum explanations handler @@ -323,7 +327,7 @@ The above ModelHandler class should have the following methods with captum funct def get_insights(self,**kwargs): """ Functionality to get the explanations. - Called from the explain_handle method + Called from the explain_handle method """ pass ``` diff --git a/docs/default_handlers.md b/docs/default_handlers.md index cc365c74cc..14a91763ab 100644 --- a/docs/default_handlers.md +++ b/docs/default_handlers.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # TorchServe default inference handlers TorchServe provides following inference handlers out of box. It's expected that the models consumed by each support batched inference. diff --git a/docs/genai_use_cases.md b/docs/genai_use_cases.md index 7492ed62f5..a488bff174 100644 --- a/docs/genai_use_cases.md +++ b/docs/genai_use_cases.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # TorchServe GenAI use cases and showcase This document shows interesting usecases with TorchServe for Gen AI deployments. @@ -8,4 +12,4 @@ In this blog, we show how to deploy a RAG Endpoint using TorchServe, increase th ## [Multi-Image Generation Streamlit App: Chaining Llama & Stable Diffusion using TorchServe, torch.compile & OpenVINO](https://pytorch.org/serve/llm_diffusion_serving_app.html) -This Multi-Image Generation Streamlit app is designed to generate multiple images based on a provided text prompt. Instead of using Stable Diffusion directly, this app chains Llama and Stable Diffusion to enhance the image generation process. This multi-image generation use case exemplifies the powerful synergy of cutting-edge AI technologies: TorchServe, OpenVINO, Torch.compile, Meta-Llama, and Stable Diffusion. +This Multi-Image Generation Streamlit app is designed to generate multiple images based on a provided text prompt. Instead of using Stable Diffusion directly, this app chains Llama and Stable Diffusion to enhance the image generation process. This multi-image generation use case exemplifies the powerful synergy of cutting-edge AI technologies: TorchServe, OpenVINO, Torch.compile, Meta-Llama, and Stable Diffusion. diff --git a/docs/getting_started.md b/docs/getting_started.md index 79b27c4447..606773ca4c 100644 --- a/docs/getting_started.md +++ b/docs/getting_started.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Getting started ## Install TorchServe and torch-model-archiver diff --git a/docs/github_actions.md b/docs/github_actions.md index 14ac2b2688..5490e9a2a7 100644 --- a/docs/github_actions.md +++ b/docs/github_actions.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # GitHub Actions for TorchServe ## Steps to create github actions diff --git a/docs/grpc_api.md b/docs/grpc_api.md index a41387ebb9..58700dea84 100644 --- a/docs/grpc_api.md +++ b/docs/grpc_api.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # TorchServe gRPC API __Note__: Current TorchServe gRPC does not support workflow. diff --git a/docs/hardware_support/amd_support.md b/docs/hardware_support/amd_support.md index 55de40f6d4..daf89d4308 100644 --- a/docs/hardware_support/amd_support.md +++ b/docs/hardware_support/amd_support.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # AMD Support TorchServe can be run on any combination of operating system and device that is diff --git a/docs/hardware_support/apple_silicon_support.md b/docs/hardware_support/apple_silicon_support.md index 6e0f479b8a..5e8686d7de 100644 --- a/docs/hardware_support/apple_silicon_support.md +++ b/docs/hardware_support/apple_silicon_support.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Apple Silicon Support ## What is supported diff --git a/docs/hardware_support/linux_aarch64.md b/docs/hardware_support/linux_aarch64.md index 5e13410c83..f185af5beb 100644 --- a/docs/hardware_support/linux_aarch64.md +++ b/docs/hardware_support/linux_aarch64.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # TorchServe on linux aarch64 - Experimental TorchServe has been tested to be working on linux aarch64 for some of the examples. diff --git a/docs/hardware_support/nvidia_mps.md b/docs/hardware_support/nvidia_mps.md index 063b62db53..f2a4787171 100644 --- a/docs/hardware_support/nvidia_mps.md +++ b/docs/hardware_support/nvidia_mps.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Running TorchServe with NVIDIA MPS In order to deploy ML models, TorchServe spins up each worker in a separate processes, thus isolating each worker from the others. Each process creates its own CUDA context to execute its kernels and access the allocated memory. diff --git a/docs/inference_api.md b/docs/inference_api.md index 2ac0250745..bcb1ef6c25 100644 --- a/docs/inference_api.md +++ b/docs/inference_api.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # [Inference API](#inference-api) Inference API is listening on port 8080 and only accessible from localhost by default. To change the default setting, see [TorchServe Configuration](configuration.md). diff --git a/docs/internals.md b/docs/internals.md index b27c00fba7..27a240185d 100644 --- a/docs/internals.md +++ b/docs/internals.md @@ -1,6 +1,10 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + ## TorchServe internals -TorchServe was designed a multi model inferencing framework. A production grade inferencing framework needs both APIs to request inferences but also APIs to manage models all the while keeping track of logs. TorchServe manages several worker processes that are dynamically assigned to different models with the behavior of those workers determined by a handler file and a model store where weights are loaded from. +TorchServe was designed a multi model inferencing framework. A production grade inferencing framework needs both APIs to request inferences but also APIs to manage models all the while keeping track of logs. TorchServe manages several worker processes that are dynamically assigned to different models with the behavior of those workers determined by a handler file and a model store where weights are loaded from. ## TorchServe Architecture ![Architecture Diagram](https://user-images.githubusercontent.com/880376/83180095-c44cc600-a0d7-11ea-97c1-23abb4cdbe4d.jpg) @@ -45,7 +49,7 @@ https://github.com/pytorch/serve/blob/master/ts/arg_parser.py https://github.com/pytorch/serve/blob/master/ts/context.py -* Context object of incoming request - keeps model relevant worker information +* Context object of incoming request - keeps model relevant worker information https://github.com/pytorch/serve/blob/master/ts/model_server.py @@ -56,7 +60,7 @@ https://github.com/pytorch/serve/blob/master/ts/model_server.py https://github.com/pytorch/serve/blob/master/ts/model_loader.py * Model loader -* Uses manifest file to find handler and envelope and starts the service +* Uses manifest file to find handler and envelope and starts the service * Loads either default handler or custom handler * Request envelopes which make it easier to interact with other systems like Seldon, KFserving, Google cloud AI platform @@ -68,7 +72,7 @@ https://github.com/pytorch/serve/blob/master/ts/model_loader.py https://github.com/pytorch/serve/blob/8903ca1fb059eab3c1e8eccdee1376d4ff52fb67/frontend/server/src/main/java/org/pytorch/serve/wlm/WorkerStateListener.java -* Takes care of closing workers +* Takes care of closing workers https://github.com/pytorch/serve/blob/8903ca1fb059eab3c1e8eccdee1376d4ff52fb67/frontend/server/src/main/java/org/pytorch/serve/wlm/WorkerState.java diff --git a/docs/large_model_inference.md b/docs/large_model_inference.md index 173f002177..e264801eea 100644 --- a/docs/large_model_inference.md +++ b/docs/large_model_inference.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Serving large models with Torchserve This document explain how Torchserve supports large model serving, here large model refers to the models that are not able to fit into one gpu so they need be split in multiple partitions over multiple gpus. diff --git a/docs/llm_deployment.md b/docs/llm_deployment.md index 2a7bfc8742..dc653b7b58 100644 --- a/docs/llm_deployment.md +++ b/docs/llm_deployment.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # LLM Deployment with TorchServe This document describes how to easily serve large language models (LLM) like Meta-Llama3 with TorchServe. diff --git a/docs/logging.md b/docs/logging.md index c2bc58a857..bf92d63822 100644 --- a/docs/logging.md +++ b/docs/logging.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Logging in Torchserve In this document we explain logging in TorchServe. We also explain how to modify the behavior of logging in the model server. diff --git a/docs/management_api.md b/docs/management_api.md index ed14849e21..7ab88b2914 100644 --- a/docs/management_api.md +++ b/docs/management_api.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # [Management API](#management-api) TorchServe provides the following APIs that allows you to manage models at runtime: diff --git a/docs/metrics.md b/docs/metrics.md index 707afaa1ce..79726ecf93 100644 --- a/docs/metrics.md +++ b/docs/metrics.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # [TorchServe Metrics](#torchserve-metrics) ## Contents diff --git a/docs/metrics_api.md b/docs/metrics_api.md index 6028dc5b1b..4062b4173b 100644 --- a/docs/metrics_api.md +++ b/docs/metrics_api.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Metrics API Metrics API is a http API that is used to fetch metrics in the prometheus format. It is listening on port 8082 and only accessible from localhost by default. To change the default setting, see [TorchServe Configuration](configuration.md). The metrics endpoint is enabled by default and returns Prometheus formatted metrics when [metrics_mode](https://github.com/pytorch/serve/blob/master/docs/metrics.md) configuration is set to `prometheus`. You can query metrics using curl requests or point a [Prometheus Server](#prometheus-server) to the endpoint and use [Grafana](#grafana) for dashboards. diff --git a/docs/model_api_control.md b/docs/model_api_control.md index 8406a100cb..f29ced02ec 100644 --- a/docs/model_api_control.md +++ b/docs/model_api_control.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Model API Control TorchServe now disables the use of model API (specifically registering and deleting models) by default. The use of these APIs can be enabled through command line or config.properties file. diff --git a/docs/model_loading.md b/docs/model_loading.md index 8881f53878..087f998cc0 100644 --- a/docs/model_loading.md +++ b/docs/model_loading.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # How to load a model in TorchServe There are multiple ways to load to model in TorchServe. The below flowchart tries to simplify the process and shows the various options diff --git a/docs/model_zoo.md b/docs/model_zoo.md index f5072ed11c..526bc7fb97 100644 --- a/docs/model_zoo.md +++ b/docs/model_zoo.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Model Zoo This page lists model archives that are pre-trained and pre-packaged, ready to be served for inference with TorchServe. @@ -21,7 +25,7 @@ To propose a model for inclusion, please submit a [pull request](https://github. | FCN ResNet 101 | Image Segmentation | COCO | 193 MB | [.mar](https://torchserve.pytorch.org/mar_files/fcn_resnet_101.mar) | [persons.jpg](https://github.com/pytorch/serve/blob/master/examples/image_segmenter/persons.jpg?raw=true) |Eager| | DeepLabV3 ResNet 101 | Image Segmentation | COCO | 217 MB | [.mar](https://torchserve.pytorch.org/mar_files/deeplabv3_resnet_101_eager.mar) | [persons.jpg](https://github.com/pytorch/serve/blob/master/examples/image_segmenter/persons.jpg) |Eager| | BERT token classification | Token Classification | AG_NEWS | 384.7 MB | [.mar](https://torchserve.pytorch.org/mar_files/bert_token_classification_no_torchscript.mar) | [sample_text.txt](https://github.com/pytorch/serve/blob/master/examples/text_classification/sample_text.txt) |Eager| -| BERT sequence classification | Sequence Classification | AG_NEWS | 386.8 MB | [.mar](https://torchserve.pytorch.org/mar_files/bert_seqc_without_torchscript.mar) | [sample_text.txt](https://github.com/pytorch/serve/blob/master/examples/text_classification/sample_text.txt) |Eager| +| BERT sequence classification | Sequence Classification | AG_NEWS | 386.8 MB | [.mar](https://torchserve.pytorch.org/mar_files/bert_seqc_without_torchscript.mar) | [sample_text.txt](https://github.com/pytorch/serve/blob/master/examples/text_classification/sample_text.txt) |Eager| | AlexNet Scripted | Image Classification | ImageNet | 216 MB | [.mar](https://torchserve.pytorch.org/mar_files/alexnet_scripted.mar) | [kitten.jpg](https://github.com/pytorch/serve/blob/master/examples/image_classifier/kitten.jpg?raw=true) |Torchscripted | | Densenet161 Scripted| Image Classification | ImageNet | 105 MB | [.mar](https://torchserve.pytorch.org/mar_files/densenet161_scripted.mar) | [kitten.jpg](https://github.com/pytorch/serve/blob/master/examples/image_classifier/kitten.jpg?raw=true) |Torchscripted | | Resnet18 Scripted| Image Classification | ImageNet | 42 MB | [.mar](https://torchserve.pytorch.org/mar_files/resnet-18_scripted.mar) | [kitten.jpg](https://github.com/pytorch/serve/blob/master/examples/image_classifier/kitten.jpg?raw=true) |Torchscripted | @@ -33,9 +37,9 @@ To propose a model for inclusion, please submit a [pull request](https://github. | FCN ResNet 101 Scripted | Image Segmentation | COCO | 193 MB | [.mar](https://torchserve.pytorch.org/mar_files/fcn_resnet_101_scripted.mar) | [persons.jpg](https://github.com/pytorch/serve/blob/master/examples/image_segmenter/persons.jpg?raw=true) |Torchscripted | | DeepLabV3 ResNet 101 Scripted | Image Segmentation | COCO | 217 MB | [.mar](https://torchserve.pytorch.org/mar_files/deeplabv3_resnet_101_scripted.mar) | [persons.jpg](https://github.com/pytorch/serve/blob/master/examples/image_segmenter/persons.jpg) |Torchscripted | | MMF activity recognition | Activity Recognition | Charades | 549 MB | [.mar](https://torchserve.pytorch.org/mar_files/MMF_activity_recognition_v2.mar) | [372CC.mp4](https://mmfartifacts.s3-us-west-2.amazonaws.com/372CC.mp4) | Torchscripted | -| BERT sequence classification CPU | Sequence Classification | AG_NEWS | 386.9 MB | [.mar](https://torchserve.pytorch.org/mar_files/BERTSeqClassification_torchscript.mar) | [sample_text.txt](https://github.com/pytorch/serve/blob/master/examples/Huggingface_Transformers/Seq_classification_artifacts/sample_text.txt) |Torchscripted| -| BERT sequence classification mGPU | Sequence Classification | CAPTUM | 386.9 MB | [.mar](https://torchserve.pytorch.org/mar_files/BERTSeqClassification_mgpu.mar) | [sample_text_captum_input.txt](https://github.com/pytorch/serve/blob/master/examples/Huggingface_Transformers/Seq_classification_artifacts/sample_text_captum_input.txt) |Torchscripted| -| BERT sequence classification | Sequence Classification | AG_NEWS | 386.8 MB | [.mar](https://torchserve.pytorch.org/mar_files/BERTSeqClassification.mar) | [sample_text.txt](https://github.com/pytorch/serve/blob/master/examples/Huggingface_Transformers/Seq_classification_artifacts/sample_text.txt) |Torchscripted| +| BERT sequence classification CPU | Sequence Classification | AG_NEWS | 386.9 MB | [.mar](https://torchserve.pytorch.org/mar_files/BERTSeqClassification_torchscript.mar) | [sample_text.txt](https://github.com/pytorch/serve/blob/master/examples/Huggingface_Transformers/Seq_classification_artifacts/sample_text.txt) |Torchscripted| +| BERT sequence classification mGPU | Sequence Classification | CAPTUM | 386.9 MB | [.mar](https://torchserve.pytorch.org/mar_files/BERTSeqClassification_mgpu.mar) | [sample_text_captum_input.txt](https://github.com/pytorch/serve/blob/master/examples/Huggingface_Transformers/Seq_classification_artifacts/sample_text_captum_input.txt) |Torchscripted| +| BERT sequence classification | Sequence Classification | AG_NEWS | 386.8 MB | [.mar](https://torchserve.pytorch.org/mar_files/BERTSeqClassification.mar) | [sample_text.txt](https://github.com/pytorch/serve/blob/master/examples/Huggingface_Transformers/Seq_classification_artifacts/sample_text.txt) |Torchscripted| | dog breed classification | Image Classification | ImageNet | 1.1 KB | [.war](https://torchserve.s3.amazonaws.com/war_files/dog_breed_wf.war) | [kitten_small.jpg](https://raw.githubusercontent.com/pytorch/serve/master/docs/images/kitten_small.jpg) | Workflow | Refer [example](https://github.com/pytorch/serve/tree/master/examples) for more details on above models. diff --git a/docs/performance_checklist.md b/docs/performance_checklist.md index 2fa365e8aa..c0ef99bafd 100644 --- a/docs/performance_checklist.md +++ b/docs/performance_checklist.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Model Inference Optimization Checklist This checklist describes some steps that should be completed when diagnosing model inference performance issues. Some of these suggestions are only applicable to NLP models (e.g., ensuring the input is not over-padded and sequence bucketing), but the general principles are useful for other models too. diff --git a/docs/performance_guide.md b/docs/performance_guide.md index af817c1966..d5da040f07 100644 --- a/docs/performance_guide.md +++ b/docs/performance_guide.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # [Performance Guide](#performance-guide) In case you're interested in optimizing the memory usage, latency or throughput of a PyTorch model served with TorchServe, this is the guide for you. diff --git a/docs/request_envelopes.md b/docs/request_envelopes.md index 443e2be5fb..85dfddbd7f 100644 --- a/docs/request_envelopes.md +++ b/docs/request_envelopes.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Request Envelopes Many model serving systems provide a signature for request bodies. Examples include: diff --git a/docs/rest_api.md b/docs/rest_api.md index 8f826acff3..a747119ea9 100644 --- a/docs/rest_api.md +++ b/docs/rest_api.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # TorchServe REST API TorchServe uses a RESTful API for both inference and management calls. The API is compliant with the [OpenAPI specification 3.0](https://swagger.io/specification/). diff --git a/docs/server.md b/docs/server.md index 6d68d4bf0c..fef4bfa465 100644 --- a/docs/server.md +++ b/docs/server.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Running TorchServe ## Contents of this Document diff --git a/docs/snapshot.md b/docs/snapshot.md index 0cd320ac0d..e03a6705cd 100644 --- a/docs/snapshot.md +++ b/docs/snapshot.md @@ -1,14 +1,18 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # TorchServe model snapshot TorchServe preserves server runtime configuration across sessions such that a TorchServe instance experiencing either a planned or unplanned service stop can restore its state upon restart. - + __Note:__ Current snapshot does not support workflow. A TorchServe's snapshot consists of following: - Server configuration, which comprises: Which models are running, which versions of those models, and how many workers are active for each model. - Default server configuration used while starting TorchServe the first time. - + The snapshot is taken at following instances - - After successful startup, the server stores its current configuration in a timestamped snapshot file ./logs/config/-startup.cfg @@ -22,7 +26,7 @@ User can use snapshots to restore the TorchServe's state as follows : - If no config file is supplied with `--ts-config-file` flag while starting TorchServe, last snapshot in ./logs/configs is used for startup. - If no config file is supplied with `--ts-config-file` flag and no snapshots are available, TorchServe starts with default configurations. - The user restarts the server specifying this config file: `torchserve --start --model-store --ts-config ` - + If the user wishes to start without this resiliency feature, the user can start the server with : @@ -30,8 +34,8 @@ If the user wishes to start without this resiliency feature, the user can start This prevents to server from storing config snapshot files. -The snapshots are by default in `{LOG_LOCATION}\config` directory, where `{LOG_LOCATION}` is a system environment variable that can be used by TorchServe. If this variable is not set, the snapshot is stored in `.\log\config` directory +The snapshots are by default in `{LOG_LOCATION}\config` directory, where `{LOG_LOCATION}` is a system environment variable that can be used by TorchServe. If this variable is not set, the snapshot is stored in `.\log\config` directory -**Note** : +**Note** : 1. Models passed in --models parameter while starting TorchServe are ignored if restoring from a snapshot. 2. For windows, if shutdown snapshot file is not generated then you can use last snapshot file. diff --git a/docs/token_authorization_api.md b/docs/token_authorization_api.md index fbed95cc38..647bd02348 100644 --- a/docs/token_authorization_api.md +++ b/docs/token_authorization_api.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # TorchServe token authorization API TorchServe now enforces token authorization by default diff --git a/docs/torchserve_on_win_native.md b/docs/torchserve_on_win_native.md index 89b84ba242..b3e3022af2 100644 --- a/docs/torchserve_on_win_native.md +++ b/docs/torchserve_on_win_native.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # TorchServe on Windows ## Contents of this Document diff --git a/docs/torchserve_on_wsl.md b/docs/torchserve_on_wsl.md index 8723e9c347..3cda32ef53 100644 --- a/docs/torchserve_on_wsl.md +++ b/docs/torchserve_on_wsl.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # TorchServe on Windows Subsystem for Linux (WSL) * Ubuntu 18.0.4 diff --git a/docs/use_cases.md b/docs/use_cases.md index 16fab7dfaf..19f2b9286c 100644 --- a/docs/use_cases.md +++ b/docs/use_cases.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Torchserve Use Cases Torchserve can be used for different use cases. In order to make it convenient for users, some of them have been documented here. diff --git a/docs/workflow_inference_api.md b/docs/workflow_inference_api.md index 383f01ef6f..c28bf657b4 100644 --- a/docs/workflow_inference_api.md +++ b/docs/workflow_inference_api.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Workflow Inference API Workflow Inference API is listening on port 8080 and only accessible from localhost by default. To change the default setting, see [TorchServe Configuration](configuration.md). diff --git a/docs/workflow_management_api.md b/docs/workflow_management_api.md index 6fb04647f3..6da69d3fae 100644 --- a/docs/workflow_management_api.md +++ b/docs/workflow_management_api.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Management API TorchServe provides the following APIs that allows you to manage workflows at runtime: diff --git a/docs/workflows.md b/docs/workflows.md index b1341c1104..7eb046873d 100644 --- a/docs/workflows.md +++ b/docs/workflows.md @@ -1,10 +1,14 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # TorchServe Workflows -TorchServe can be used for serving ensemble of Pytorch models packaged as mar files and Python functions through Workflow APIs. +TorchServe can be used for serving ensemble of Pytorch models packaged as mar files and Python functions through Workflow APIs. It utilizes [REST based APIs](rest_api.md) for workflow management and predictions. -A Workflow is served on TorchServe using a workflow-archive(.war) which comprises of following: +A Workflow is served on TorchServe using a workflow-archive(.war) which comprises of following: ## Workflow Specification file @@ -31,7 +35,7 @@ models: min-workers: 1 #override the global params max-workers: 2 batch-size: 4 - + m2: url : model2.mar @@ -41,7 +45,7 @@ models: m4: url : model4.mar - + dag: pre_processing : [m1] m1 : [m2] @@ -140,4 +144,4 @@ def postprocess(data, context): * Workflow scale/updates is not supported through APIs. User will need to unregister the workflow and re-register with the required changes * Snapshots are not supported for workflows and related models are not captured in the workflow * Workflow versioning is not supported -* Workflows registration having public model URL with mar file names which are already registered will fail. \ No newline at end of file +* Workflows registration having public model URL with mar file names which are already registered will fail. diff --git a/examples/FasterTransformer_HuggingFace_Bert/README.md b/examples/FasterTransformer_HuggingFace_Bert/README.md index 20af07bccb..ee374c2582 100644 --- a/examples/FasterTransformer_HuggingFace_Bert/README.md +++ b/examples/FasterTransformer_HuggingFace_Bert/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + ## Faster Transformer Batch inferencing with Transformers faces two challenges diff --git a/examples/Huggingface_Transformers/README.md b/examples/Huggingface_Transformers/README.md index 9607013d77..5772e0959a 100644 --- a/examples/Huggingface_Transformers/README.md +++ b/examples/Huggingface_Transformers/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + ## Serving Huggingface Transformers using TorchServe In this example, we show how to serve a fine tuned or off the shelf Transformer model from [huggingface](https://huggingface.co/docs/transformers/index) using TorchServe. diff --git a/examples/Huggingface_Transformers/torchscript.md b/examples/Huggingface_Transformers/torchscript.md index 42a9e3ba79..f4b48fc9c1 100644 --- a/examples/Huggingface_Transformers/torchscript.md +++ b/examples/Huggingface_Transformers/torchscript.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Torchscript Support [Torchscript](https://pytorch.org/docs/stable/jit.html#creating-torchscript-code) along with Pytorch JIT are designed to provide portability and performance for Pytorch models. Torchscript is a static subset of Python language that capture the structure of Pytorch programs and JIT uses this structure for optimization. diff --git a/examples/LLM/llama/README.md b/examples/LLM/llama/README.md index 452a8d2aea..9b049b269b 100644 --- a/examples/LLM/llama/README.md +++ b/examples/LLM/llama/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Meta Llama: Next generation of Meta's Language Model ![Llama](./images/llama.png) diff --git a/examples/LLM/llama/chat_app/Readme.md b/examples/LLM/llama/chat_app/Readme.md index 063cca8504..82be67f168 100644 --- a/examples/LLM/llama/chat_app/Readme.md +++ b/examples/LLM/llama/chat_app/Readme.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # TorchServe Llama Chatapp diff --git a/examples/MMF-activity-recognition/README.md b/examples/MMF-activity-recognition/README.md index 42bc5ff53c..b0e2d41d26 100644 --- a/examples/MMF-activity-recognition/README.md +++ b/examples/MMF-activity-recognition/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + ### MultiModal (MMF) Framework Multi modality learning helps the AI solutions to get signals from different input sources such as language, video, audio and combine their results to improve the inferences. diff --git a/examples/README.md b/examples/README.md index de42112514..f7fb2a8fc2 100644 --- a/examples/README.md +++ b/examples/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # [Examples showcasing TorchServe Features and Integrations](#torchserve-internals) ## Security Changes diff --git a/examples/Workflows/README.md b/examples/Workflows/README.md index b08ab3ecb9..35a138b87c 100644 --- a/examples/Workflows/README.md +++ b/examples/Workflows/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # [Workflow examples](#workflow-examples) Workflows can be used to compose an ensemble of Pytorch models and Python functions and package them in a `war` file. A workflow is executed as a DAG where the nodes can be either Pytorch models packaged as `mar` files or function nodes specified in the workflow handler file. The DAG can be used to define both sequential or parallel pipelines. diff --git a/examples/Workflows/dog_breed_classification/README.md b/examples/Workflows/dog_breed_classification/README.md index 2babc69336..7335206ccb 100644 --- a/examples/Workflows/dog_breed_classification/README.md +++ b/examples/Workflows/dog_breed_classification/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Workflow pipeline example for classifying dog breed This workflow uses two models, first to classify if an image is of a dog or a cat. If it is a dog the second model does breed classification. diff --git a/examples/Workflows/nmt_transformers_pipeline/README.md b/examples/Workflows/nmt_transformers_pipeline/README.md index 5c2d733c0a..7415886bb4 100644 --- a/examples/Workflows/nmt_transformers_pipeline/README.md +++ b/examples/Workflows/nmt_transformers_pipeline/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Workflow pipeline example using nmt transformer nlp model This example uses the existing [nmt_transformers](../../nmt_transformer) standalone example to create a workflow. We use three models, in two examples to demonstrate stringing them together in a workflow. diff --git a/examples/asr_rnnt_emformer/README.md b/examples/asr_rnnt_emformer/README.md index c77d88801c..2f29e36c9d 100644 --- a/examples/asr_rnnt_emformer/README.md +++ b/examples/asr_rnnt_emformer/README.md @@ -1,11 +1,15 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + ### ASR (Automated Speech Recognition) Example In this example we use torchserve to serve a ASR model that convert wav to text. There are four steps in this process. First we download a pretrained emformer model and save it to JIT format; Second we start model server, create the model archive; Third we configure the model server with 1 worker; Last we send a wav file to the model endpoint to get text prediction. #### Steps to run: -- 1. Save asr model to jit format. +- 1. Save asr model to jit format. ```bash -./00_save_jit_model.sh +./00_save_jit_model.sh ``` - 2. Create model archive ```bash @@ -14,7 +18,7 @@ In this example we use torchserve to serve a ASR model that convert wav to text. output: 2023-01-10T20:46:39,660 [INFO ] pool-3-thread-2 TS_METRICS - MemoryUtilization.Percent:3.2|Level:Host|hostname:ip-172-31-15-90,timestamp:1673383599 ``` -- 3. Configure model server. register model and add workers. +- 3. Configure model server. register model and add workers. ```bash ./02_configure_server.sh diff --git a/examples/benchmarking/resnet50/README.md b/examples/benchmarking/resnet50/README.md index 39721f6954..fdaf3e1473 100644 --- a/examples/benchmarking/resnet50/README.md +++ b/examples/benchmarking/resnet50/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Benchmark ResNet50 and profile the detailed split of PredictionTime diff --git a/examples/cloud_storage_stream_inference/README.md b/examples/cloud_storage_stream_inference/README.md index 8606b39861..7b5c33fa5d 100644 --- a/examples/cloud_storage_stream_inference/README.md +++ b/examples/cloud_storage_stream_inference/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Using fsspec to stream data from cloud storage providers for batch inference This example shows how to use fsspec to stream large amount of data from cloud storage like s3, google cloud storage, azure cloud etc. and use it to create requests to torchserve for large scale batch inference with a large batch size. diff --git a/examples/cloudformation/README.md b/examples/cloudformation/README.md index a14f2a6719..cde80596b5 100644 --- a/examples/cloudformation/README.md +++ b/examples/cloudformation/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Cloudformation Templates Torchserve provides configurable cloudformation templates to spin up AWS instances running torchserve. diff --git a/examples/cpp/aot_inductor/bert/README.md b/examples/cpp/aot_inductor/bert/README.md index c9243b94c4..cf77b223a8 100644 --- a/examples/cpp/aot_inductor/bert/README.md +++ b/examples/cpp/aot_inductor/bert/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + This example uses AOTInductor to compile the [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) into an so file (see script [aot_compile_export.py](aot_compile_export.py)). In PyTorch 2.2, the supported `MAX_SEQ_LENGTH` in this script is 511. Then, this example loads model and runs prediction using libtorch. The handler C++ source code for this examples can be found [here](src). diff --git a/examples/cpp/aot_inductor/llama2/README.md b/examples/cpp/aot_inductor/llama2/README.md index 3c789c8c0e..e1a54f842e 100644 --- a/examples/cpp/aot_inductor/llama2/README.md +++ b/examples/cpp/aot_inductor/llama2/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + This example uses Bert Maher's [llama2.so](https://github.com/bertmaher/llama2.so/) which is a fork of Andrej Karpathy's [llama2.c](https://github.com/karpathy/llama2.c). It uses AOTInductor to compile the model into an so file which is then executed using libtorch. The handler C++ source code for this examples can be found [here](src/). diff --git a/examples/cpp/aot_inductor/resnet/README.md b/examples/cpp/aot_inductor/resnet/README.md index ba507da7e6..a115871c8b 100644 --- a/examples/cpp/aot_inductor/resnet/README.md +++ b/examples/cpp/aot_inductor/resnet/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + This example uses AOTInductor to compile the Resnet50 into an so file which is then executed using libtorch. The handler C++ source code for this examples can be found [here](src). diff --git a/examples/cpp/babyllama/README.md b/examples/cpp/babyllama/README.md index 85e410172e..e6a2d804cc 100644 --- a/examples/cpp/babyllama/README.md +++ b/examples/cpp/babyllama/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + ## BabyLlama example This example is adapted from https://github.com/karpathy/llama2.c. The handler C++ source code for this examples can be found [here](./src/). diff --git a/examples/cpp/llamacpp/README.md b/examples/cpp/llamacpp/README.md index 195d4e17b2..5b20207424 100644 --- a/examples/cpp/llamacpp/README.md +++ b/examples/cpp/llamacpp/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + ## Llama.cpp example This example used [llama.cpp](https://github.com/ggerganov/llama.cpp) to deploy a Llama-2-7B-Chat model using the TorchServe C++ backend. diff --git a/examples/custom_endpoint_plugin/README.md b/examples/custom_endpoint_plugin/README.md index d96048cba7..6b8ad9f8d6 100644 --- a/examples/custom_endpoint_plugin/README.md +++ b/examples/custom_endpoint_plugin/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Torchserve custom endpoint plugin In this example, we demonstrate how to create a custom HTTP API endpoint plugin for TorchServe. Endpoint plugins enable us to dynamically add custom functionality to TorchServe at start time, without having to rebuild TorchServe. For more details on endpoint plugins and TorchServe SDK, refer to the following links: @@ -52,17 +56,17 @@ Run the commands given in the following steps from the root directory of the rep $ cd plugins $ ./gradlew clean build $ cd .. - ``` + ``` - Step 6: Create two example model archives to test the plugin with ```bash $ mkdir -p model_store $ torch-model-archiver --model-name mnist --version 1.0 --model-file examples/image_classifier/mnist/mnist.py --serialized-file examples/image_classifier/mnist/mnist_cnn.pt --handler examples/image_classifier/mnist/mnist_handler.py - $ mv mnist.mar ./model_store + $ mv mnist.mar ./model_store ``` - ```bash + ```bash $ wget https://download.pytorch.org/models/resnet18-f37072fd.pth $ torch-model-archiver --model-name resnet-18 --version 1.0 --model-file ./examples/image_classifier/resnet_18/model.py --serialized-file resnet18-f37072fd.pth --handler image_classifier --extra-files ./examples/image_classifier/index_to_name.json $ mv resnet-18.mar ./model_store @@ -98,7 +102,7 @@ Run the commands given in the following steps from the root directory of the rep The `model-ready` endpoint reports that the models are not ready since there are no workers that have loaded the models and ready to serve inference requests. - Step 9: Scale up workers for one of the models and test the custom endpoint - + ```bash $ curl -X PUT "http://localhost:8081/models/mnist?min_worker=1&synchronous=true" { @@ -142,4 +146,3 @@ Run the commands given in the following steps from the root directory of the rep ```bash $ torchserve --stop ``` - diff --git a/examples/custom_metrics/README.md b/examples/custom_metrics/README.md index f6da045e8d..e6675f3f14 100644 --- a/examples/custom_metrics/README.md +++ b/examples/custom_metrics/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Torchserve custom metrics with prometheus support In this example, we show how to use a pre-trained custom MNIST model and export custom metrics using prometheus. diff --git a/examples/dcgan_fashiongen/Readme.md b/examples/dcgan_fashiongen/Readme.md index c8898e1ea2..88a04e3622 100644 --- a/examples/dcgan_fashiongen/Readme.md +++ b/examples/dcgan_fashiongen/Readme.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # GAN(Generative Adversarial Networks) models using TorchServe - In this example we will demonstrate how to serve a GAN model using TorchServe. - We have used a pretrained DCGAN model from [facebookresearch/pytorch_GAN_zoo](https://github.com/facebookresearch/pytorch_GAN_zoo) diff --git a/examples/diffusers/Readme.md b/examples/diffusers/Readme.md index 97ee301ccb..66617874d0 100644 --- a/examples/diffusers/Readme.md +++ b/examples/diffusers/Readme.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Running Stable diffusion model using Huggingface Diffusers in Torchserve. ### Step 1: Download model diff --git a/examples/image_classifier/README.md b/examples/image_classifier/README.md index f577ede512..d696f91aaa 100644 --- a/examples/image_classifier/README.md +++ b/examples/image_classifier/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + #### Image classification examples: * [Image Classification with AlexNet](alexnet) @@ -7,4 +11,3 @@ * [Image Classification with VGG16](vgg_16) * [Batch image classification with Resnet152 using custom handerl](resnet_152_batch) * [Digit recognition with MNIST using a custom handler](mnist) - diff --git a/examples/image_classifier/alexnet/README.md b/examples/image_classifier/alexnet/README.md index 41392c5ce9..76bdb88882 100644 --- a/examples/image_classifier/alexnet/README.md +++ b/examples/image_classifier/alexnet/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + ### Sample commands to create a alexnet model archive, register it on TorchServe and run image prediction Run the commands given in following steps from the parent directory of the root of the repository. For example, if you cloned the repository into /home/my_path/serve, run the steps from /home/my_path/serve diff --git a/examples/image_classifier/densenet_161/README.md b/examples/image_classifier/densenet_161/README.md index 911db41dca..dd6f1cb702 100644 --- a/examples/image_classifier/densenet_161/README.md +++ b/examples/image_classifier/densenet_161/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + #### TorchServe inference with torch.compile of densenet161 model This example shows how to take eager model of `densenet161`, configure TorchServe to use `torch.compile` and run inference using `torch.compile` diff --git a/examples/image_classifier/mnist/Docker.md b/examples/image_classifier/mnist/Docker.md index e734e831e0..11dda8716f 100644 --- a/examples/image_classifier/mnist/Docker.md +++ b/examples/image_classifier/mnist/Docker.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Digit recognition model with MNIST dataset using Docker container In this example, we show how to use a pre-trained custom MNIST model to performing real time Digit recognition with TorchServe. diff --git a/examples/image_classifier/mnist/README.md b/examples/image_classifier/mnist/README.md index cac021fb9f..cd7df84c79 100644 --- a/examples/image_classifier/mnist/README.md +++ b/examples/image_classifier/mnist/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Digit recognition model with MNIST dataset In this example, we show how to use a pre-trained custom MNIST model to performing real time Digit recognition with TorchServe. diff --git a/examples/image_classifier/near_real_time_video/README.md b/examples/image_classifier/near_real_time_video/README.md index 3c97a535d9..2cd8ccde12 100644 --- a/examples/image_classifier/near_real_time_video/README.md +++ b/examples/image_classifier/near_real_time_video/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # On-premise Near Real-Time Video Inference Consider a use-case where we have cameras connected to edge devices. These devices are connected to a compute cluster where TorchServe is running. Each edge device has a computer vision pipeline running, where we read frames from the camera and we need to perform tasks as Image Classification, Pose Estimation, Activity Recognition etc on the read frames. In order to make efficient use of hardware resources, we might want to do batching of the frames for efficient inference diff --git a/examples/image_classifier/resnet_152_batch/README.md b/examples/image_classifier/resnet_152_batch/README.md index 327fa7c31c..24521f2864 100644 --- a/examples/image_classifier/resnet_152_batch/README.md +++ b/examples/image_classifier/resnet_152_batch/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + #### TorchServe inference with torch.compile of Resnet152 batch image classifier: Run the commands given in following steps from the root directory of the repository. For example, if you cloned the repository into /home/my_path/serve, run the steps from /home/my_path/serve diff --git a/examples/image_classifier/resnet_18/README.md b/examples/image_classifier/resnet_18/README.md index 9799f072fb..66600b0d49 100644 --- a/examples/image_classifier/resnet_18/README.md +++ b/examples/image_classifier/resnet_18/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + #### Sample commands to create a resnet-18 eager mode model archive, register it on TorchServe and run image prediction Run the commands given in following steps from the parent directory of the root of the repository. For example, if you cloned the repository into /home/my_path/serve, run the steps from /home/my_path/serve diff --git a/examples/image_classifier/resnet_18/ReactJSExample/README.md b/examples/image_classifier/resnet_18/ReactJSExample/README.md index 7e466c8a89..9a2f293cc4 100644 --- a/examples/image_classifier/resnet_18/ReactJSExample/README.md +++ b/examples/image_classifier/resnet_18/ReactJSExample/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + Instructions diff --git a/examples/image_classifier/squeezenet/README.md b/examples/image_classifier/squeezenet/README.md index e6c6855008..23ca6572e6 100644 --- a/examples/image_classifier/squeezenet/README.md +++ b/examples/image_classifier/squeezenet/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + #### Sample commands to create a squeezenet eager mode model archive, register it on TorchServe and run image prediction Run the commands given in following steps from the parent directory of the root of the repository. For example, if you cloned the repository into /home/my_path/serve, run the steps from /home/my_path/serve @@ -45,7 +49,7 @@ produces the output "tiger_cat": 0.2425432652235031, "Egyptian_cat": 0.22137290239334106, "cougar": 0.0022544628009200096 -}% +}% ``` diff --git a/examples/image_classifier/vgg_16/README.md b/examples/image_classifier/vgg_16/README.md index aba5d1d37e..054862c9ca 100644 --- a/examples/image_classifier/vgg_16/README.md +++ b/examples/image_classifier/vgg_16/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + #### TorchServe inference with torch.compile of vgg-16 model This example shows how to take eager model of `vgg-16`, configure TorchServe to use `torch.compile` and run inference using `torch.compile` diff --git a/examples/image_segmenter/README.md b/examples/image_segmenter/README.md index e8f5674e3a..cbd3768cf0 100644 --- a/examples/image_segmenter/README.md +++ b/examples/image_segmenter/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Image Segmentation using TorchServe's default image_segmenter handler * [Image Segmentation using torchvision's pretrained fcn_resnet_101_coco model.](fcn) diff --git a/examples/image_segmenter/deeplabv3/README.md b/examples/image_segmenter/deeplabv3/README.md index 4e9ff8db38..a44363ca9b 100644 --- a/examples/image_segmenter/deeplabv3/README.md +++ b/examples/image_segmenter/deeplabv3/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Image Segmentation using torchvision's pretrained deeplabv3_resnet_101_coco model. * Download the pre-trained deeplabv3_resnet_101_coco image segmentation model's state_dict from the following URL: diff --git a/examples/image_segmenter/fcn/README.md b/examples/image_segmenter/fcn/README.md index 332483339f..20a39be0d3 100644 --- a/examples/image_segmenter/fcn/README.md +++ b/examples/image_segmenter/fcn/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Image Segmentation using torchvision's pretrained fcn_resnet_101_coco model. * Download the pre-trained fcn_resnet_101_coco image segmentation model's state_dict from the following URL: diff --git a/examples/instruction_embedding/README.md b/examples/instruction_embedding/README.md index efb2041aa0..7ad0b79caf 100644 --- a/examples/instruction_embedding/README.md +++ b/examples/instruction_embedding/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # A TorchServe handler for Instructor Embedding models A simple handler that you can use to serve [Instructor Embedding models](https://instructor-embedding.github.io/) with TorchServe, supporting both single inference and batch inference. diff --git a/examples/intel_extension_for_pytorch/README.md b/examples/intel_extension_for_pytorch/README.md index 5ff07b8563..bccaabd0ef 100644 --- a/examples/intel_extension_for_pytorch/README.md +++ b/examples/intel_extension_for_pytorch/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # TorchServe with Intel® Extension for PyTorch* TorchServe can be used with Intel® Extension for PyTorch* to give performance boost on Intel hardware.1 diff --git a/examples/large_models/Huggingface_accelerate/Readme.md b/examples/large_models/Huggingface_accelerate/Readme.md index f2afd96cc1..2e58ebe575 100644 --- a/examples/large_models/Huggingface_accelerate/Readme.md +++ b/examples/large_models/Huggingface_accelerate/Readme.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Loading large Huggingface models with constrained resources using accelerate This document briefs on serving large HG models with limited resource using accelerate. This option can be activated with `low_cpu_mem_usage=True`. The model is first created on the Meta device (with empty weights) and the state dict is then loaded inside it (shard by shard in the case of a sharded checkpoint). diff --git a/examples/large_models/Huggingface_accelerate/llama/Readme.md b/examples/large_models/Huggingface_accelerate/llama/Readme.md index 3b45640c82..e17ad38345 100644 --- a/examples/large_models/Huggingface_accelerate/llama/Readme.md +++ b/examples/large_models/Huggingface_accelerate/llama/Readme.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Loading meta-llama/Meta-Llama-3-70B-Instruct on AWS EC2 g5.24xlarge using accelerate This document briefs on serving large HF models with limited resource using accelerate. This option can be activated with `low_cpu_mem_usage=True`. The model is first created on the Meta device (with empty weights) and the state dict is then loaded inside it (shard by shard in the case of a sharded checkpoint). This examples uses Meta Llama-3 as an example but it works with Llama2 as well by replacing the model identifier. diff --git a/examples/large_models/Huggingface_pippy/Readme.md b/examples/large_models/Huggingface_pippy/Readme.md index 970d0315af..bab3ff96ec 100644 --- a/examples/large_models/Huggingface_pippy/Readme.md +++ b/examples/large_models/Huggingface_pippy/Readme.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Loading large Huggingface models with PiPPy (PyTorch Native Large inference solution) This document briefs on serving large HF model with PiPPy. diff --git a/examples/large_models/deepspeed/Readme.md b/examples/large_models/deepspeed/Readme.md index 8906e36a43..38c1b06d03 100644 --- a/examples/large_models/deepspeed/Readme.md +++ b/examples/large_models/deepspeed/Readme.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Loading large Huggingface models on Multiple GPUs This document briefs on serving large HuggingFace (HF) models on multiple GPUs using deepspeed. We are using facebook/opt-30b in this example diff --git a/examples/large_models/deepspeed_mii/LLM/Readme.md b/examples/large_models/deepspeed_mii/LLM/Readme.md index 2fc2d74bc7..a27df803da 100644 --- a/examples/large_models/deepspeed_mii/LLM/Readme.md +++ b/examples/large_models/deepspeed_mii/LLM/Readme.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Running LLM model using Microsoft DeepSpeed-MII in Torchserve This example demo serving HF LLM model with Microsoft DeepSpeed-MII in Torchserve. With DeepSpeed-MII there has been significant progress in system optimizations for DL model inference, drastically reducing both latency and cost. diff --git a/examples/large_models/deepspeed_mii/Readme.md b/examples/large_models/deepspeed_mii/Readme.md index 443f849fdb..4d1eadb246 100644 --- a/examples/large_models/deepspeed_mii/Readme.md +++ b/examples/large_models/deepspeed_mii/Readme.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Running Stable diffusion model using Microsoft DeepSpeed-MII in Torchserve. This document briefs on serving HG Stable diffusion model with Microsoft DeepSpeed-MII in Torchserve. With DeepSpeed-MII there has been significant progress in system optimizations for DL model inference, drastically reducing both latency and cost. diff --git a/examples/large_models/diffusion_fast/README.md b/examples/large_models/diffusion_fast/README.md index 222cf9a6d1..403a9ecc80 100644 --- a/examples/large_models/diffusion_fast/README.md +++ b/examples/large_models/diffusion_fast/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + ## Diffusion-Fast diff --git a/examples/large_models/gpt_fast/README.md b/examples/large_models/gpt_fast/README.md index 4a30e27040..ee6e34e9a4 100644 --- a/examples/large_models/gpt_fast/README.md +++ b/examples/large_models/gpt_fast/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + ## GPT-Fast diff --git a/examples/large_models/gpt_fast_mixtral_moe/README.md b/examples/large_models/gpt_fast_mixtral_moe/README.md index 155f862800..eac029d917 100644 --- a/examples/large_models/gpt_fast_mixtral_moe/README.md +++ b/examples/large_models/gpt_fast_mixtral_moe/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + ## Mixtral-MOE diff --git a/examples/large_models/inferentia2/llama/Readme.md b/examples/large_models/inferentia2/llama/Readme.md index 2bb856c5e8..506833d188 100644 --- a/examples/large_models/inferentia2/llama/Readme.md +++ b/examples/large_models/inferentia2/llama/Readme.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Large model inference on Inferentia2 This folder briefs on serving the [Llama 2 and Llama 3](https://huggingface.co/meta-llama) model on an [AWS Inferentia2](https://aws.amazon.com/ec2/instance-types/inf2/) for text completion with TorchServe's features: diff --git a/examples/large_models/inferentia2/llama/continuous_batching/Readme.md b/examples/large_models/inferentia2/llama/continuous_batching/Readme.md index 24852f6ff8..6a1052ec6a 100644 --- a/examples/large_models/inferentia2/llama/continuous_batching/Readme.md +++ b/examples/large_models/inferentia2/llama/continuous_batching/Readme.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Demo2: Llama-2 Using TorchServe continuous batching on inf2 This document briefs on serving the [Llama 2](https://huggingface.co/meta-llama) model on [AWS transformers-neuronx continuous batching](https://aws.amazon.com/ec2/instance-types/inf2/). diff --git a/examples/large_models/inferentia2/llama/streamer/Readme.md b/examples/large_models/inferentia2/llama/streamer/Readme.md index da931f68ce..3b17352c4c 100644 --- a/examples/large_models/inferentia2/llama/streamer/Readme.md +++ b/examples/large_models/inferentia2/llama/streamer/Readme.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Demo1: Llama-2 Using TorchServe micro-batching and Streamer on inf2 This document briefs on serving the [Llama 2](https://huggingface.co/meta-llama) model on [AWS Inferentia2](https://aws.amazon.com/ec2/instance-types/inf2/) for text completion with [micro batching](https://github.com/pytorch/serve/tree/96450b9d0ab2a7290221f0e07aea5fda8a83efaf/examples/micro_batching) and [streaming response](https://github.com/pytorch/serve/blob/96450b9d0ab2a7290221f0e07aea5fda8a83efaf/docs/inference_api.md#curl-example-1) support. diff --git a/examples/large_models/inferentia2/opt/Readme.md b/examples/large_models/inferentia2/opt/Readme.md index 85332650e4..de589125a1 100644 --- a/examples/large_models/inferentia2/opt/Readme.md +++ b/examples/large_models/inferentia2/opt/Readme.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Large model inference on Inferentia2 This document briefs on serving large HuggingFace (HF) models on [AWS Inferentia2](https://aws.amazon.com/ec2/instance-types/inf2/) instances. diff --git a/examples/large_models/ipex_llm_int8/README.md b/examples/large_models/ipex_llm_int8/README.md index bb9e4bc4c0..d5221f3f4f 100644 --- a/examples/large_models/ipex_llm_int8/README.md +++ b/examples/large_models/ipex_llm_int8/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Serving IPEX Optimized Models This example provides an example of serving IPEX-optimized LLMs e.g. ```meta-llama/llama2-7b-hf``` on huggingface. For setting up the Python environment for this example, please refer here: https://github.com/intel/intel-extension-for-pytorch/blob/main/examples/cpu/inference/python/llm/README.md#3-environment-setup @@ -38,7 +42,7 @@ There are 3 different example config files; ```model-config-llama2-7b-int8-sq.ya ### IPEX Weight Only Quantization
    -
  • weight_type: weight data type for weight only quantization. Options: INT8 or INT4. +
  • weight_type: weight data type for weight only quantization. Options: INT8 or INT4.
  • lowp_mode: low precision mode for weight only quantization. It indicates data type for computation.
diff --git a/examples/large_models/segment_anything_fast/README.md b/examples/large_models/segment_anything_fast/README.md index d7df0c2307..b3969beecf 100644 --- a/examples/large_models/segment_anything_fast/README.md +++ b/examples/large_models/segment_anything_fast/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + ## Segment Anything Fast diff --git a/examples/large_models/tp_llama/README.md b/examples/large_models/tp_llama/README.md index eb40b41b00..3c3972dc27 100644 --- a/examples/large_models/tp_llama/README.md +++ b/examples/large_models/tp_llama/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Serving Llama2 with PyTorch Native Tensor Parallelism This document briefs on serving the [Llama 2](https://huggingface.co/meta-llama) as presented in the original [Llama repo](https://github.com/facebookresearch/llama/tree/main) using PyTorch(PT) Tensor Parallel (TP) APIs, which under the hood make use of DTensors. It basically, takes a sharding plan for linear layers in MLP and Attention blocks of Llama2 model and make a TP model distributed over multiple GPUs. In the following, we show the steps how to use this and serve the Llama2 7-70B model with Torchserve. diff --git a/examples/large_models/trt_llm/llama/README.md b/examples/large_models/trt_llm/llama/README.md index 0b883ec74c..7bcdd1056d 100644 --- a/examples/large_models/trt_llm/llama/README.md +++ b/examples/large_models/trt_llm/llama/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Llama TensorRT-LLM Engine integration with TorchServe [TensorRT-LLM](https://github.com/NVIDIA/TensorRT-LLM) provides users with an option to build TensorRT engines for LLMs that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. diff --git a/examples/large_models/trt_llm/lora/README.md b/examples/large_models/trt_llm/lora/README.md index e969d9364d..d6e9adf697 100644 --- a/examples/large_models/trt_llm/lora/README.md +++ b/examples/large_models/trt_llm/lora/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Llama TensorRT-LLM Engine + LoRA model integration with TorchServe [TensorRT-LLM](https://github.com/NVIDIA/TensorRT-LLM) provides users with an option to build TensorRT engines for LLMs that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. diff --git a/examples/large_models/vllm/Readme.md b/examples/large_models/vllm/Readme.md index c734709338..f01b2c5da3 100644 --- a/examples/large_models/vllm/Readme.md +++ b/examples/large_models/vllm/Readme.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Example showing inference with vLLM This folder contains multiple demonstrations showcasing the integration of [vLLM Engine](https://github.com/vllm-project/vllm) with TorchServe, running inference with continuous batching. diff --git a/examples/large_models/vllm/llama3/Readme.md b/examples/large_models/vllm/llama3/Readme.md index ac8ea048d4..c67baa0d6d 100644 --- a/examples/large_models/vllm/llama3/Readme.md +++ b/examples/large_models/vllm/llama3/Readme.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Example showing inference with vLLM on LoRA model This is an example showing how to integrate [vLLM](https://github.com/vllm-project/vllm) with TorchServe and run inference on model `meta-llama/Meta-Llama-3.1-8B-Instruct` with continuous batching. diff --git a/examples/large_models/vllm/lora/Readme.md b/examples/large_models/vllm/lora/Readme.md index 0b855261e3..ab404dff43 100644 --- a/examples/large_models/vllm/lora/Readme.md +++ b/examples/large_models/vllm/lora/Readme.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Example showing inference with vLLM on LoRA model This is an example showing how to integrate [vLLM](https://github.com/vllm-project/vllm) with TorchServe and run inference on model `meta-llama/Meta-Llama-3.1-8B` + LoRA model `llama-duo/llama3.1-8b-summarize-gpt4o-128k` with continuous batching. diff --git a/examples/large_models/vllm/mistral/Readme.md b/examples/large_models/vllm/mistral/Readme.md index d7c504a54c..b6cee1b669 100644 --- a/examples/large_models/vllm/mistral/Readme.md +++ b/examples/large_models/vllm/mistral/Readme.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Example showing inference with vLLM on Mistral model This is an example showing how to integrate [vLLM](https://github.com/vllm-project/vllm) with TorchServe and run inference on model `mistralai/Mistral-7B-v0.1` with continuous batching. diff --git a/examples/micro_batching/README.md b/examples/micro_batching/README.md index 0f8a3d7fee..98de596721 100644 --- a/examples/micro_batching/README.md +++ b/examples/micro_batching/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Micro Batching Accelerators like GPUs can be used most cost efficiently for inference if they are steadily fed with incoming data. TorchServe currently allows a single batch to be processed per backend worker. diff --git a/examples/nmt_transformer/README.md b/examples/nmt_transformer/README.md index 6cd816c138..9b8350ba50 100644 --- a/examples/nmt_transformer/README.md +++ b/examples/nmt_transformer/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Transformer (NMT) models for English-French and English-German translation. The Transformer, introduced in the paper [Attention Is All You Need](https://arxiv.org/abs/1706.03762), is a powerful sequence-to-sequence modeling architecture capable of producing state-of-the-art neural machine translation (NMT) systems. diff --git a/examples/nvidia_dali/README.md b/examples/nvidia_dali/README.md index 0af11ee51b..7b6fb29c0a 100644 --- a/examples/nvidia_dali/README.md +++ b/examples/nvidia_dali/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # DALI Optimization integration with Torchserve models The NVIDIA Data Loading Library (DALI) is a library for data loading and pre-processing to accelerate deep learning applications. It provides a collection of highly optimized building blocks for loading and processing image, video and audio data. diff --git a/examples/object_detector/README.md b/examples/object_detector/README.md index d1a9e201dc..318f52fa35 100644 --- a/examples/object_detector/README.md +++ b/examples/object_detector/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Object Detection using TorchServe's default object_detector handler * [Object detection using torchvision's pretrained fast-rcnn model](fast-rcnn) diff --git a/examples/object_detector/fast-rcnn/README.md b/examples/object_detector/fast-rcnn/README.md index 2bc8f60ab1..d1f7c41e29 100644 --- a/examples/object_detector/fast-rcnn/README.md +++ b/examples/object_detector/fast-rcnn/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Object Detection using torchvision's pretrained fast-rcnn model. * Download the pre-trained fast-rcnn object detection model's state_dict from the following URL : diff --git a/examples/object_detector/maskrcnn/README.md b/examples/object_detector/maskrcnn/README.md index 62bb3a662d..ee29dac6dd 100644 --- a/examples/object_detector/maskrcnn/README.md +++ b/examples/object_detector/maskrcnn/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Object Detection using torchvision's pretrained maskrcnn model. * Download the pre-trained maskrcnn object detection model's state_dict from the following URL : diff --git a/examples/object_detector/yolo/yolov8/README.md b/examples/object_detector/yolo/yolov8/README.md index 6e0915b1ea..5f616738f8 100644 --- a/examples/object_detector/yolo/yolov8/README.md +++ b/examples/object_detector/yolo/yolov8/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Object Detection using Ultralytics's pretrained YOLOv8(yolov8n) model. diff --git a/examples/pt2/README.md b/examples/pt2/README.md index d5250d6b3c..6150c77b33 100644 --- a/examples/pt2/README.md +++ b/examples/pt2/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + ## PyTorch 2.x integration PyTorch 2.x brings more compiler options to PyTorch, for you that should mean better perf either in the form of lower latency or lower memory consumption. diff --git a/examples/pt2/torch_compile/README.md b/examples/pt2/torch_compile/README.md index 2cc1e3da80..7131650e26 100644 --- a/examples/pt2/torch_compile/README.md +++ b/examples/pt2/torch_compile/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # TorchServe inference with torch.compile of densenet161 model diff --git a/examples/pt2/torch_compile_hpu/README.md b/examples/pt2/torch_compile_hpu/README.md index 989177c7ac..29dfc4bb8d 100644 --- a/examples/pt2/torch_compile_hpu/README.md +++ b/examples/pt2/torch_compile_hpu/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # TorchServe Inference with torch.compile with HPU backend of Resnet50 model diff --git a/examples/pt2/torch_compile_openvino/README.md b/examples/pt2/torch_compile_openvino/README.md index 9d70a052ae..42f90f2218 100644 --- a/examples/pt2/torch_compile_openvino/README.md +++ b/examples/pt2/torch_compile_openvino/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # TorchServe Inference with torch.compile with OpenVINO backend of Resnet50 model diff --git a/examples/pt2/torch_compile_openvino/stable_diffusion/README.md b/examples/pt2/torch_compile_openvino/stable_diffusion/README.md index 29802e0d95..8412d15d30 100644 --- a/examples/pt2/torch_compile_openvino/stable_diffusion/README.md +++ b/examples/pt2/torch_compile_openvino/stable_diffusion/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Accelerating StableDiffusionXL model with torch.compile OpenVINO backend diff --git a/examples/pt2/torch_export_aot_compile/README.md b/examples/pt2/torch_export_aot_compile/README.md index 82a26624b2..2446fae225 100644 --- a/examples/pt2/torch_export_aot_compile/README.md +++ b/examples/pt2/torch_export_aot_compile/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # TorchServe inference with torch._export.aot_compile This example shows how to run TorchServe with Torch exported model with AOTInductor diff --git a/examples/pt2/torch_inductor_caching/README.md b/examples/pt2/torch_inductor_caching/README.md index eb28ac7e2e..12ec50674b 100644 --- a/examples/pt2/torch_inductor_caching/README.md +++ b/examples/pt2/torch_inductor_caching/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # TorchInductor Caching with TorchServe inference of densenet161 model diff --git a/examples/speech2text_wav2vec2/README.md b/examples/speech2text_wav2vec2/README.md index 75f7c73d29..5cd5e3cadc 100644 --- a/examples/speech2text_wav2vec2/README.md +++ b/examples/speech2text_wav2vec2/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + ## Speech2Text Wav2Vec2 example: In this example we will use a pretrained Wav2Vec2 model for Speech2Text using the `transformers` library: https://huggingface.co/docs/transformers/model_doc/wav2vec2 and serve it using torchserve. diff --git a/examples/stateful/sequence_batching/Readme.md b/examples/stateful/sequence_batching/Readme.md index 4d243d210e..297009826f 100644 --- a/examples/stateful/sequence_batching/Readme.md +++ b/examples/stateful/sequence_batching/Readme.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Stateful Inference A stateful model possesses the ability to leverage interdependencies between successive inference requests. This type of model maintains a persistent state across inference requests, thereby establishing a linkage between the outcomes of prior inquiries and those that follow. Notable illustrations of stateful models encompass online speech recognition systems, such as the Long Short-Term Memory (LSTM) model. Employing stateful inference mandates that the model server adheres to the sequential order of inference requests, ensuring predictions build upon the previous outcomes. diff --git a/examples/stateful/sequence_continuous_batching/Readme.md b/examples/stateful/sequence_continuous_batching/Readme.md index d3b839a8cd..6d4820fa6e 100644 --- a/examples/stateful/sequence_continuous_batching/Readme.md +++ b/examples/stateful/sequence_continuous_batching/Readme.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Stateful Inference A stateful model possesses the ability to leverage interdependencies between successive inference requests. This type of model maintains a persistent state across inference requests, thereby establishing a linkage between the outcomes of prior inquiries and those that follow. Notable illustrations of stateful models encompass online speech recognition systems, such as the Long Short-Term Memory (LSTM) model. Employing stateful inference mandates that the model server adheres to the sequential order of inference requests, ensuring predictions build upon the previous outcomes. diff --git a/examples/text_classification/README.md b/examples/text_classification/README.md index 2c3772c8a1..1ac059f179 100644 --- a/examples/text_classification/README.md +++ b/examples/text_classification/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Text Classification using TorchServe's default text_classifier handler ## !!!Deprecation Warning!!! diff --git a/examples/text_classification_with_scriptable_tokenizer/README.md b/examples/text_classification_with_scriptable_tokenizer/README.md index 63e1c3ecaa..bdfdf899ff 100644 --- a/examples/text_classification_with_scriptable_tokenizer/README.md +++ b/examples/text_classification_with_scriptable_tokenizer/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Text Classification using a Scriptable Tokenizer ## !!!Deprecation Warning!!! diff --git a/examples/text_to_speech_synthesizer/SpeechT5/README.md b/examples/text_to_speech_synthesizer/SpeechT5/README.md index 6536dbc3e3..23e6d5f3d5 100644 --- a/examples/text_to_speech_synthesizer/SpeechT5/README.md +++ b/examples/text_to_speech_synthesizer/SpeechT5/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Text to Speech synthesis with SpeechT5 This is an example showing text to speech synthesis using SpeechT5 model. This has been verified to work on (linux-aarch64) Graviton 3 instance diff --git a/examples/text_to_speech_synthesizer/WaveGlow/README.md b/examples/text_to_speech_synthesizer/WaveGlow/README.md index 8816495681..4d79c7f58e 100644 --- a/examples/text_to_speech_synthesizer/WaveGlow/README.md +++ b/examples/text_to_speech_synthesizer/WaveGlow/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Text to speech synthesis using WaveGlow & Tacotron2 model. **This example works only on NVIDIA CUDA device and not on CPU** diff --git a/examples/torch_tensorrt/torchcompile/T5/README.md b/examples/torch_tensorrt/torchcompile/T5/README.md index d4523fef11..6769227e1f 100644 --- a/examples/torch_tensorrt/torchcompile/T5/README.md +++ b/examples/torch_tensorrt/torchcompile/T5/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # TorchServe inference with torch.compile with tensorrt backend This example shows how to run TorchServe inference with T5 [Torch-TensorRT](https://github.com/pytorch/TensorRT) model diff --git a/examples/torch_tensorrt/torchcompile/resnet50/README.md b/examples/torch_tensorrt/torchcompile/resnet50/README.md index 6299d2b0f7..203065043a 100644 --- a/examples/torch_tensorrt/torchcompile/resnet50/README.md +++ b/examples/torch_tensorrt/torchcompile/resnet50/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # TorchServe inference with torch.compile with tensorrt backend This example shows how to run TorchServe inference with [Torch-TensorRT](https://github.com/pytorch/TensorRT) model diff --git a/examples/torch_tensorrt/torchscript/README.md b/examples/torch_tensorrt/torchscript/README.md index d73d023fca..c7c059e4b1 100644 --- a/examples/torch_tensorrt/torchscript/README.md +++ b/examples/torch_tensorrt/torchscript/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # TorchServe inference with torch tensorrt (using TorchScript) model This example shows how to run TorchServe inference with [Torch-TensorRT](https://github.com/pytorch/TensorRT) model using TorchScript. This is the legacy way of using TensorRT with PyTorch. We recommend using torch.compile for new deployments (see [../README.md](../README.md)). TorchScript is in maintenance mode. diff --git a/examples/torchrec_dlrm/README.md b/examples/torchrec_dlrm/README.md index ee5dbb710b..2d259933f9 100644 --- a/examples/torchrec_dlrm/README.md +++ b/examples/torchrec_dlrm/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # TorchRec DLRM Example diff --git a/examples/usecases/RAG_based_LLM_serving/Deploy.md b/examples/usecases/RAG_based_LLM_serving/Deploy.md index 7ee28cce1c..c66c691cea 100644 --- a/examples/usecases/RAG_based_LLM_serving/Deploy.md +++ b/examples/usecases/RAG_based_LLM_serving/Deploy.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Deploy Llama & RAG using TorchServe ## Contents diff --git a/examples/usecases/RAG_based_LLM_serving/README.md b/examples/usecases/RAG_based_LLM_serving/README.md index 258305849b..a0f45c8bab 100644 --- a/examples/usecases/RAG_based_LLM_serving/README.md +++ b/examples/usecases/RAG_based_LLM_serving/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Enhancing LLM Serving with Torch Compiled RAG on AWS Graviton Previously, it has been [demonstrated](https://pytorch.org/blog/high-performance-llama/) how to deploy Llama with TorchServe. Deploying just the LLM can have limitations such as lack of up-to-date information & limited domain specific knowledge. Retrieval Augmented Generation (RAG) is a technique that can be used to enhance the accuracy and reliability of an LLM by providing the context of up-to-date, relevant information. This blog post illustrates how to implement RAG alongside LLM in a microservices-based architecture, which enhances scalability and expedites development. Additionally, by utilizing CPU-based RAG with AWS Graviton, customers can efficiently use compute resources, ultimately leading to cost savings. diff --git a/examples/usecases/llm_diffusion_serving_app/README.md b/examples/usecases/llm_diffusion_serving_app/README.md index 98efeadeec..9862b4ed98 100644 --- a/examples/usecases/llm_diffusion_serving_app/README.md +++ b/examples/usecases/llm_diffusion_serving_app/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + ## Multi-Image Generation Streamlit App: Chaining Llama & Stable Diffusion using TorchServe, torch.compile & OpenVINO This Multi-Image Generation Streamlit app is designed to generate multiple images based on a provided text prompt. Instead of using Stable Diffusion directly, this app chains Llama and Stable Diffusion to enhance the image generation process. Here’s how it works: @@ -10,7 +14,7 @@ This Multi-Image Generation Streamlit app is designed to generate multiple image ## Quick Start Guide -**Prerequisites**: +**Prerequisites**: - Docker installed on your system - Hugging Face Token: Create a Hugging Face account and obtain a token with access to the [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) model. @@ -25,7 +29,7 @@ cd serve ./examples/usecases/llm_diffusion_serving_app/docker/build_image.sh # 3: Launch the streamlit app for server & client -# After the Docker build is successful, you will see a "docker run" command printed to the console. +# After the Docker build is successful, you will see a "docker run" command printed to the console. # Run that "docker run" command to launch the Streamlit app for both the server and client. ``` @@ -34,7 +38,7 @@ cd serve
```console -ubuntu@ip-10-0-0-137:~/serve$ ./examples/usecases/llm_diffusion_serving_app/docker/build_image.sh +ubuntu@ip-10-0-0-137:~/serve$ ./examples/usecases/llm_diffusion_serving_app/docker/build_image.sh EXAMPLE_DIR: .//examples/usecases/llm_diffusion_serving_app/docker ROOT_DIR: /home/ubuntu/serve DOCKER_BUILDKIT=1 docker buildx build --platform=linux/amd64 --file .//examples/usecases/llm_diffusion_serving_app/docker/Dockerfile --build-arg BASE_IMAGE="pytorch/torchserve:latest-cpu" --build-arg EXAMPLE_DIR=".//examples/usecases/llm_diffusion_serving_app/docker" --build-arg HUGGINGFACE_TOKEN=hf_ --build-arg HTTP_PROXY= --build-arg HTTPS_PROXY= --build-arg NO_PROXY= -t "pytorch/torchserve:llm_diffusion_serving_app" . @@ -45,7 +49,7 @@ DOCKER_BUILDKIT=1 docker buildx build --platform=linux/amd64 --file .//examples/ . => => naming to docker.io/pytorch/torchserve:llm_diffusion_serving_app 0.0s -Docker Build Successful ! +Docker Build Successful ! ............................ Next Steps ............................ -------------------------------------------------------------------- @@ -83,8 +87,8 @@ Note: You can replace the model identifiers (MODEL_NAME_LLM, MODEL_NAME_SD) as n ## What to expect After launching the Docker container using the `docker run ..` command displayed after a successful build, you can access two separate Streamlit applications: -1. TorchServe Server App (running at http://localhost:8084) to start/stop TorchServe, load/register models, scale up/down workers. -2. Client App (running at http://localhost:8085) where you can enter prompt for Image generation. +1. TorchServe Server App (running at http://localhost:8084) to start/stop TorchServe, load/register models, scale up/down workers. +2. Client App (running at http://localhost:8085) where you can enter prompt for Image generation. > Note: You could also run a quick benchmark comparing the performance of Stable Diffusion with Eager, torch.compile with inductor and openvino. > Review the `docker run ..` command displayed after a successful build for benchmarking @@ -262,7 +266,7 @@ Results saved at /home/model-server/model-store/ which is a Docker container mou ## Multi-Image Generation App UI -### App Workflow +### App Workflow ![Multi-Image Generation App Workflow Gif](https://raw.githubusercontent.com/pytorch/serve/master/examples/usecases/llm_diffusion_serving_app/docker/img/multi-image-gen-app.gif) ### App Screenshots diff --git a/examples/xgboost_classfication/README.md b/examples/xgboost_classfication/README.md index 153645611f..23230dbb72 100644 --- a/examples/xgboost_classfication/README.md +++ b/examples/xgboost_classfication/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # XGBoost Classifier for Iris dataset This example shows how to serve an XGBoost classifier model using TorchServe. diff --git a/frontend/README.md b/frontend/README.md index 8dfce7e6d2..6e13474ce5 100644 --- a/frontend/README.md +++ b/frontend/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + TorchServe REST API endpoint ============================== diff --git a/kubernetes/AKS/README.md b/kubernetes/AKS/README.md index 323f7df568..a97df20b40 100644 --- a/kubernetes/AKS/README.md +++ b/kubernetes/AKS/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + ## TorchServe on Azure Kubernetes Service (AKS) ### 1 Create an AKS cluster diff --git a/kubernetes/EKS/README.md b/kubernetes/EKS/README.md index c932f5e914..3d3a7a84b8 100644 --- a/kubernetes/EKS/README.md +++ b/kubernetes/EKS/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Torchserve on Elastic Kubernetes service (EKS) ## Overview diff --git a/kubernetes/GKE/README.md b/kubernetes/GKE/README.md index 9be81963f9..4f424fb7f9 100644 --- a/kubernetes/GKE/README.md +++ b/kubernetes/GKE/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + ## TorchServe on Google Kubernetes Engine (GKE) ### 1 Create an GKE cluster @@ -36,10 +40,10 @@ WARNING: Warning: basic authentication is deprecated, and will be removed in GKE WARNING: Currently VPC-native is not the default mode during cluster creation. In the future, this will become the default mode and can be disabled using `--no-enable-ip-alias` flag. Use `--[no-]enable-ip-alias` flag to suppress this warning. WARNING: Newly created clusters and node-pools will have node auto-upgrade enabled by default. This can be disabled using the `--no-enable-autoupgrade` flag. WARNING: Starting with version 1.18, clusters will have shielded GKE nodes by default. -WARNING: Your Pod address range (`--cluster-ipv4-cidr`) can accommodate at most 1008 node(s). +WARNING: Your Pod address range (`--cluster-ipv4-cidr`) can accommodate at most 1008 node(s). WARNING: Starting with version 1.19, newly created clusters and node-pools will have COS_CONTAINERD as the default node image when no image type is specified. Machines with GPUs have certain limitations which may affect your workflow. Learn more at https://cloud.google.com/kubernetes-engine/docs/how-to/gpus -Creating cluster ts in us-west1... Cluster is being health-checked (master is healthy)...done. +Creating cluster ts in us-west1... Cluster is being health-checked (master is healthy)...done. Created [https://container.googleapis.com/v1/projects/xxxxx-xxxx-35xx55/zones/us-west1/clusters/ts]. To inspect the contents of your cluster, go to: https://console.cloud.google.com/kubernetes/workload_/gcloud/us-west1/ts?project=xxxxx-xxxx-35xx55 kubeconfig entry generated for ts. @@ -100,7 +104,7 @@ cd serve/kubernetes/GKE * Change torchserve image in Helm/values.yaml to the CPU version * Set `n_gpu` to `0` in Helm/values.yaml * Skip NVIDIA plugin installation in section [2.3](#23-install-nvidia-device-plugin) - + #### 2.3 Install NVIDIA device plugin Before the GPUs in the nodes can be used, you must deploy a DaemonSet for the NVIDIA device plugin. This DaemonSet runs a pod on each node to provide the required drivers for the GPUs. @@ -292,7 +296,7 @@ Possible error in this step may be a result of one of the following. Your pod my * Check affinity zone in values.yaml to match the storage disk. * Wrong Server IP - + * Check the server IP mentioned in the pv_pvc.yaml * You can execute the following commands to inspect the pods / events to debug NFS Issues diff --git a/kubernetes/README.md b/kubernetes/README.md index 796ae4613d..995a5e6133 100644 --- a/kubernetes/README.md +++ b/kubernetes/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Torchserve on Kubernetes ## Security Changes diff --git a/kubernetes/autoscale.md b/kubernetes/autoscale.md index 2ad3a7da9e..d729e09a91 100644 --- a/kubernetes/autoscale.md +++ b/kubernetes/autoscale.md @@ -1,4 +1,8 @@ -# Autoscaler +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + +# Autoscaler Setup Kubernetes HPA(Horizontal Pod Autoscaler) for Torchserve, tuned for torchserve metrics. This uses Prometheus as metrics collector and Prometheus Adapter as metrics server, serving Torchserve metrics for HPA. diff --git a/kubernetes/examples/FasterTransformer_HuggingFace_Bert.md b/kubernetes/examples/FasterTransformer_HuggingFace_Bert.md index 7d1b696e0b..8233561b76 100644 --- a/kubernetes/examples/FasterTransformer_HuggingFace_Bert.md +++ b/kubernetes/examples/FasterTransformer_HuggingFace_Bert.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Faster Transformer HuggingFace Bert example in Kubernetes Torchserve. ## Overview diff --git a/kubernetes/examples/mnist/MNIST.md b/kubernetes/examples/mnist/MNIST.md index 0a55b9ca23..bd904294ab 100644 --- a/kubernetes/examples/mnist/MNIST.md +++ b/kubernetes/examples/mnist/MNIST.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Digit recognition model with MNIST dataset using a Kubernetes cluster In this example, we show how to use a pre-trained custom MNIST model to performing real time Digit recognition with TorchServe. diff --git a/kubernetes/kserve/README.md b/kubernetes/kserve/README.md index 166e9e6b1b..7edc40c74e 100644 --- a/kubernetes/kserve/README.md +++ b/kubernetes/kserve/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # End to End Documentation for Torchserve - KServe Model Serving The documentation covers the steps to run Torchserve inside the KServe environment for the mnist model. diff --git a/kubernetes/kserve/developer_guide.md b/kubernetes/kserve/developer_guide.md index 49ac2f244e..f4db034699 100644 --- a/kubernetes/kserve/developer_guide.md +++ b/kubernetes/kserve/developer_guide.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Developer Guide The documentation covers the steps to run Torchserve along with the KServe for the mnist model in a local machine without kubernetes. This serves the purpose of developing and debugging Kserve wrapper, service envelope for Torchserve. diff --git a/kubernetes/kserve/examples/gpt_fast/README.md b/kubernetes/kserve/examples/gpt_fast/README.md index 80626bec6f..c9bd7e4971 100644 --- a/kubernetes/kserve/examples/gpt_fast/README.md +++ b/kubernetes/kserve/examples/gpt_fast/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Text generation with GPT Fast using KServe [GPT Fast](https://github.com/pytorch-labs/gpt-fast) is a PyTorch native solution of optimized GPT models. We are using GPT Fast version of `llama2-7b-chat-hf`. diff --git a/kubernetes/kserve/examples/mnist/MNIST.md b/kubernetes/kserve/examples/mnist/MNIST.md index 24efd2a2bc..a66c24074a 100644 --- a/kubernetes/kserve/examples/mnist/MNIST.md +++ b/kubernetes/kserve/examples/mnist/MNIST.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Digit recognition model with MNIST dataset using a Kubernetes cluster In this example, we show how to use a pre-trained custom MNIST model to perform real time Digit recognition with TorchServe. diff --git a/kubernetes/kserve/image_transformer/README.md b/kubernetes/kserve/image_transformer/README.md index d9a94c394f..3daf36390b 100644 --- a/kubernetes/kserve/image_transformer/README.md +++ b/kubernetes/kserve/image_transformer/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Predict on a InferenceService using PyTorch Server and Transformer Most of the model servers expect tensors as input data, so a pre-processing step is needed before making the prediction call if the user is sending in raw input format. Transformer is a service for users to implement pre/post processing code before making the prediction call. In this example we add additional pre-processing step to allow the user send raw image data and convert it into json array. diff --git a/kubernetes/kserve/kf_request_json/v1/README.md b/kubernetes/kserve/kf_request_json/v1/README.md index 7cfc600e73..b9edb5f3c1 100644 --- a/kubernetes/kserve/kf_request_json/v1/README.md +++ b/kubernetes/kserve/kf_request_json/v1/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + ### Input generation For generating custom inputs, follow the readme instructions given below diff --git a/kubernetes/kserve/kf_request_json/v2/bert/README.md b/kubernetes/kserve/kf_request_json/v2/bert/README.md index c3e4c5f146..9e02a978df 100644 --- a/kubernetes/kserve/kf_request_json/v2/bert/README.md +++ b/kubernetes/kserve/kf_request_json/v2/bert/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # TorchServe example with Huggingface bert model In this example we will show how to serve [Huggingface Transformers with TorchServe](https://github.com/pytorch/serve/tree/master/examples/Huggingface_Transformers) diff --git a/kubernetes/kserve/kf_request_json/v2/mnist/README.md b/kubernetes/kserve/kf_request_json/v2/mnist/README.md index eef0435f4a..e63cda6f57 100644 --- a/kubernetes/kserve/kf_request_json/v2/mnist/README.md +++ b/kubernetes/kserve/kf_request_json/v2/mnist/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # TorchServe example with MNIST model In this example we will show how to serve [MNIST image classification](https://github.com/pytorch/serve/tree/master/examples/image_classifier/mnist) diff --git a/kubernetes/kserve/kserve_wrapper/README.md b/kubernetes/kserve/kserve_wrapper/README.md index 60284a0731..df72cc13c4 100644 --- a/kubernetes/kserve/kserve_wrapper/README.md +++ b/kubernetes/kserve/kserve_wrapper/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # KServe Wrapper The KServe wrapper folder contains three files : diff --git a/model-archiver/README.md b/model-archiver/README.md index 49685df9b3..8873c84c1f 100644 --- a/model-archiver/README.md +++ b/model-archiver/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Torch Model archiver for TorchServe ## Contents of this Document @@ -170,7 +174,7 @@ A model config yaml file. For example: ``` # TS frontend parameters -# See all supported parameters: https://github.com/pytorch/serve/blob/master/frontend/archive/src/main/java/org/pytorch/serve/archive/model/ModelConfig.java#L14 +# See all supported parameters: https://github.com/pytorch/serve/blob/2a0ce756b179677f905c3216b9c8427cd530a129/frontend/archive/src/main/java/org/pytorch/serve/archive/model/ModelConfig.java#L14 minWorkers: 1 # default: #CPU or #GPU maxWorkers: 1 # default: #CPU or #GPU batchSize: 1 # default: 1 diff --git a/plugins/docs/README.md b/plugins/docs/README.md index 5f921e25fa..4518352f40 100644 --- a/plugins/docs/README.md +++ b/plugins/docs/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + ## Torchserve plugins You can create following types of plugins for torchserve to customize the related behaviour. @@ -7,20 +11,20 @@ of following type using plugin. e.g. [endpoints plugin](../endpoints/) a. management api b. inference api c. metric api - + 2. Snapshot serializer - It is possible to override the default file based serializer of torchserve. For example, -here is [AWS DynamoDB snapshot serializer](../DDBEndPoint). This enables torchserve to serialize snapshots to DynamoDB. +here is [AWS DynamoDB snapshot serializer](../DDBEndPoint). This enables torchserve to serialize snapshots to DynamoDB. -### How to use plugins with torchserve. +### How to use plugins with torchserve. There are following two ways to include plugin jars to torchserve. -1. Using config. property - `plugins_path` +1. Using config. property - `plugins_path` e.g. Add following line to your torchserve config. properties file. `plugins_path= 2. Using command line option `--plugins-path` -e.g. -`torchserve --start --model-store --plugins-path=` +e.g. +`torchserve --start --model-store --plugins-path=` -e.g. --plugins-path=/Users/plugins/ \ No newline at end of file +e.g. --plugins-path=/Users/plugins/ diff --git a/plugins/docs/ddb_endpoint.md b/plugins/docs/ddb_endpoint.md index 8dac6bd62a..ce7ed766e8 100644 --- a/plugins/docs/ddb_endpoint.md +++ b/plugins/docs/ddb_endpoint.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + ## DynamoDB Endpoint plugin Using this plugin, you can serialize snapshots to DDB instead of files on your local file system. Refer [plugins](README.md) for details on how to use plugins with torchserve. @@ -8,15 +12,15 @@ You can change snapshot serializer by using a DDBEndPoint plugin as follow from - You have aws cli installed on your machine - Assuming you have AWS account and required privileged to create DDB tables/indexes -1. DDB serializer uses `DefaultCredentialsProvider` which supports following authorization mechanisms - - +1. DDB serializer uses `DefaultCredentialsProvider` which supports following authorization mechanisms - + - Environment Variables - AWS_ACCESS_KEY_ID and AWS_SECRET_ACCESS_KEY - Credential profiles file at the default location (~/.aws/credentials) shared by all AWS SDKs and the AWS CLI - Credentials delivered through the Amazon EC2 container service if AWS_CONTAINER_CREDENTIALS_RELATIVE_URI" environment variable is set and security manager has permission to access the variable, - Instance profile credentials delivered through the Amazon EC2 metadata service - + Please configure desired auth. mechanism from above list. - + 2. Create following two tables (using aws cli) `aws dynamodb create-table \ --table-name Snapshots2 \ diff --git a/test/README.md b/test/README.md index bd6731b881..bdcfa50ea7 100644 --- a/test/README.md +++ b/test/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # TorchServe Regression Tests This folder contains nightly regression tests executed against TorchServe master.These tests include @@ -45,10 +49,10 @@ docker run -it --gpus all --user root pytorch/torchserve:dev-gpu /bin/bash In the Docker CLI execute the following cmds. ``` -apt-get update +apt-get update apt-get install -y git wget sudo curl git clone https://github.com/pytorch/serve -cd serve +cd serve git checkout ``` Install dependencies (if not already installed) diff --git a/test/data_file_config.md b/test/data_file_config.md index b0ac3db31a..f5b621fcf0 100644 --- a/test/data_file_config.md +++ b/test/data_file_config.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + Use following properties to add inference test case in inference_data.json Mandatory properties diff --git a/ts/handler_utils/preprocess/built-in/Readme.md b/ts/handler_utils/preprocess/built-in/Readme.md index e4170bf1ad..1f31ed3595 100644 --- a/ts/handler_utils/preprocess/built-in/Readme.md +++ b/ts/handler_utils/preprocess/built-in/Readme.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # This readme covers how the default dali_image_classifier pipeline is built Torchserve comes with a built-in pre-processing pipeline for image classification example. diff --git a/ts/tests/README.md b/ts/tests/README.md index 2f51496955..1ac9b847a3 100644 --- a/ts/tests/README.md +++ b/ts/tests/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Testing TorchServe ## Pre-requisites diff --git a/workflow-archiver/README.md b/workflow-archiver/README.md index 20096b1f52..f095f1ee99 100644 --- a/workflow-archiver/README.md +++ b/workflow-archiver/README.md @@ -1,3 +1,7 @@ +# ⚠️ Notice: Limited Maintenance + +This project is no longer actively maintained. While existing releases remain available, there are no planned updates, bug fixes, new features, or security patches. Users should be aware that vulnerabilities may not be addressed. + # Torch Workflow archiver for TorchServe ## Contents of this Document @@ -13,7 +17,7 @@ ## Overview A key feature of TorchServe is the ability to package workflow specification (.yaml) and other workflow dependency files into a single workflow archive file (.war). This file can then be redistributed and served by anyone using TorchServe. - + The CLI creates a `.war` file that TorchServe CLI uses to serve the workflows. The following information is required to create a standalone workflow archive: @@ -94,4 +98,4 @@ A .yaml file specifying workflow DAG specification ### Handler -Handler is path to a py file to handle workflow's pre-process and post-process functions. +Handler is path to a py file to handle workflow's pre-process and post-process functions.