saymrwulf/onnxruntime: ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-05-22 22:01:08 +00:00

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

Find a file

glen-amd 281ed8c12d VitisAI EP Context Model (#20926 ) # Why so many commits - Runtime debugging - which is necessary - Three different approaches to EP context model - as a result testing back and forth - Windows compatibility issues - this development has been done on Linux for convenience # "Open" (?) questions - Full offloading to a specific EP - Dumping EP context models by EPs vs [by ONNXRT](`e2abba18ea/onnxruntime/core/framework/graph_partitioner.cc (L725)`) - [Node name to pick nodes](`e2abba18ea/onnxruntime/core/framework/graph_partitioner.cc (L654)`) # VitisAI EP made three variant implementations that have respective pros and cons (and of course we can combine them) ## Serialize and cache the list of compute capabilities and the original ONNX model itself ## In `ComputeCapability()`, serialize and cache the backend compilation cache and the related necessary cache info such as cache dir and cache key ## In `Compile()`, serialize and cache the backend compilation cache and the related necessary cache info such as cache dir and cache key # EP context model creation - Precondition Session option configuration `kOrtSessionOptionEpContextEnable` (aka "ep.context_enable") is enabled. - Approach 1 - Steps 1. EP creates an ONNX model whose main graph has EP context nodes (i.e., node type is "EPContext"). 2. EP implements/overrides `IExecutionProvider::GetEpContextNodes()` method. 3. ONNXRT core creates an EP context model and saves/dumps it. - `CreateEpContextModel()` in the file "graph_partitioner.cc" - In `get_ep_context_node()`, `Node::Name()` is used to check whether a node is an EP context node. This limits that EP model creation can only happen in `IExecutionProvider::Compile()`. - The workaround is (1) not implementing `IExecutionProvider::GetEpContextNodes()` and (2) dumping the EP context model by EP itself. 4. Optionally, EP can also dump the EP context model it created by iteself. - Examples - `QNNExecutionProvider` - `VitisAIExecutionProvider` - Approach 2 - Steps 1. EP creates an ONNX model whose main graph has EP context nodes (i.e., node type is "EPContext"). 2. EP does NOT implement `IExecutionProvider::GetEpContextNodes()` at all. 3. EP dumps the EP context model it created. - Examples - `TensorrtExecutionProvider` - UPDATES - TRT EP is switching to leveraging `IExecutionProvider::GetEpContextNodes()` - `OpenVINOExecutionProvider` (?) # What to cache in EP context nodes - Non Compilation based EPs - Examples - `VitisAIExecutionProvider` - Characteristics - Heavy lifting work happens in `IExecutionProvider::GetCapability()`. - Preconditions - `IExecutionProvider::GetCapability()` is only called once by ONNXRT. - Cache content - Serialization of a list of `ComputeCapability` - Not EP-specific - Serialized using `onnx::FunctionProto` - EP-specific cache - Compilation based EPs - Examples - `QNNExecutionProvider` - `TensorrtExecutionProvider` - `MIGraphXExecutionProvider` - `OpenVINOExecutionProvider` - Cache content - EP-specific cache # Requirements - Offline / AOT compilation of ONNX models with EP context cache - Compile somewhere, run everywhere - Pseudo code with brief explanation ``` GenerateCache(original_onnx_file, cache_onnx_file) model_buffer = load(original_onnx_file) --> Load the original ONNX model file model_buffer = decrypt(model_buffer) session_options = { kOrtSessionOptionEpContextEnable: true, kOrtSessionOptionEpContextFilePath: temp_file } --> Set necessary configs Ort::CreateSessionFromArray(model_buffer, session_options) --> The new ONNX model with EP context is created and dumped into the user specified file "temp_file" temp_buffer = encrypt(temp_file) write(temp_buffer, cache_onnx_file) --> Write the encypted context of "temp_file" into the "cache_onnx_file" file InitializeInferenceSession(cache_onnx_file) model_buffer = load(cache_onnx_file) --> Load the ONNX model with EP context from the file generated in the previous step model_buffer = decrypt(model_buffer) session_options = { } Ort::CreateSessionFromArray(model_buffer, session_options) --> Create and initalize an session with the EP context model ``` - Python code with comments - EP context model creation ```python import onnxruntime as onnxrt # Session options for creating an ONNX model with EP context cache. sess_opts = onnxrt.SessionOptions() # Verbose. sess_opts.log_severity_level = 0 # This is REQUIRED. sess_opts.add_session_config_entry("ep.context_enable", "1") # This is OPTIONAL. # Either an absolute path (preferred for now) or a relative path (WIP) is okay. # sess_opts.add_session_config_entry("ep.context_file_path", "/some/path/to/original_model_ctx.onnx") # This is OPTIONAL. sess_opts.add_session_config_entry("ep.context_embed_mode", "1") orig_model_location = "/some/path/to/original_model.onnx" sess = onnxrt.InferenceSession(orig_model_location, sess_opts, providers=["VitisAIExecutionProvider"], provider_options=[]) ``` - Inference run with an EP context model ```python import onnxruntime as onnxrt # Session options for creating an ONNX model with EP context cache. sess_opts = onnxrt.SessionOptions() # Default EP context model path. # ep_ctx_model_location = "/some/path/to/origina_model.onnx_ctx.onnx" # User configured EP context model path. ep_ctx_model_location = "/some/path/to/origina_model_ctx.onnx" sess = onnxrt.InferenceSession(ep_ctx_model_location, sess_opts, providers=["VitisAIExecutionProvider"], provider_options=[]) model_inputs = {} run_opts = onnxrt.RunOptions() # Verbose. run_opts.log_severity_level = 1 sess.run(None, model_inputs, run_opts) ``` --------- Co-authored-by: Glen Cao <glen@Glens-MacBook-Air.local>		2024-07-12 21:22:58 -07:00
.config	Update tsaoptions.json: update the email alias (#13448 )	2022-10-26 15:56:16 -07:00
.devcontainer	Remove two lines in the Dockerfile for Github Codespace (#12278 )	2022-07-21 20:52:17 -07:00
.gdn	Update win-ci-pipeline.yml: enable xnnpack tests (#16244 )	2023-06-14 19:12:42 -07:00
.github	Fix lint C++ actions (#21303 )	2024-07-11 09:46:41 +08:00
.pipelines	Fix onebranch exception in code signing (#21088 )	2024-06-19 12:07:17 +08:00
.vscode	disable gemm f16 on CPU (#19744 )	2024-03-01 13:44:29 -08:00
cgmanifests	Update absl (#21300 )	2024-07-10 11:14:15 -07:00
cmake	Migraphx ep windows build (#21284 )	2024-07-11 21:21:38 -07:00
csharp	Fix typos - 1st Wave (#21278 )	2024-07-11 13:35:08 +08:00
dockerfiles	Update Dockerfile.cuda (#21042 )	2024-06-13 23:50:03 -07:00
docs	[CPU] SparseAttention op (#21110 )	2024-07-03 21:51:57 -07:00
include/onnxruntime/core	VitisAI EP Context Model (#20926 )	2024-07-12 21:22:58 -07:00
java	Remove warning suppression from Java Packaging pipeline. (#21010 )	2024-06-24 16:46:21 -07:00
js	[js/webgpu] Remove unnecessary initialization of var (#21312 )	2024-07-12 12:34:34 -07:00
objectivec	Fix Objective-C static analysis warnings. (#20417 )	2024-04-24 11:48:29 -07:00
onnxruntime	VitisAI EP Context Model (#20926 )	2024-07-12 21:22:58 -07:00
orttraining	Fix typos - 1st Wave (#21278 )	2024-07-11 13:35:08 +08:00
rust	Fix rust compile issues and add GH action to run build validations and tests (#18346 )	2023-11-09 04:26:02 -08:00
samples	Removed all the deprecated python training code and related tests and utils (#18333 )	2023-11-17 18:19:21 -08:00
tools	[Fix] Exception in iosDynamicFramework Post-Merge workflow (#21262 )	2024-07-12 09:24:12 -07:00
winml	Remove core/common/gsl.h (#20894 )	2024-07-08 18:09:39 -07:00
.clang-format	Prevent GSL_SUPPRESS arguments from being modified by clang-format (#17242 )	2023-08-22 18:26:53 -07:00
.clang-tidy	Create clang-tidy CI (#12653 )	2022-09-30 08:05:38 -07:00
.dockerignore
.gitattributes
.gitignore	Build onnxruntime.dll as arm64x (#18633 )	2023-12-06 16:49:00 -08:00
.gitmodules	[js/web] optimize module export and deployment (#20165 )	2024-05-20 09:51:16 -07:00
.lintrunner.toml	Make Flash Attention work on Windows (#21015 )	2024-06-24 09:43:49 -07:00
build.bat	try to find patch.exe in git default installation folder (#17106 )	2023-08-10 21:48:13 -07:00
build.sh	Upgrade old Python version in packaging pipeline (#16667 )	2023-07-17 08:24:47 -07:00
build_arm64x.bat	remove unnecessary environment variable (#19166 )	2024-01-16 16:24:37 -08:00
CITATION.cff	Fix citation author name issue (#19597 )	2024-02-22 17:03:56 -08:00
CODEOWNERS	Add owners for public facing API files (#15288 )	2023-03-30 17:16:15 -07:00
CONTRIBUTING.md	Fix link to High Level Design (#11786 )	2023-02-28 11:05:54 -08:00
lgtm.yml	Fix lgtm C++ error (#13613 )	2022-11-10 10:06:22 -08:00
LICENSE
NuGet.config
ort.wprp	Fully dynamic ETW controlled logging for ORT and QNN logs (#20537 )	2024-06-06 21:11:14 -07:00
ORT_icon_for_light_bg.png	Update nuget icon (#10672 )	2022-03-01 09:11:03 -08:00
packages.config	Update DML to 1.14.1 (#20380 )	2024-04-18 22:43:41 -07:00
pyproject.toml	[CUDA] Add SparseAttention operator for Phi-3-small (#20216 )	2024-04-30 09:06:29 -07:00
README.md	Update README.md (#18963 )	2024-01-03 17:26:25 -08:00
requirements-dev.txt	ONNX 1.15 integration (#17125 )	2023-09-26 14:44:48 -07:00
requirements-doc.txt
requirements-lintrunner.txt	Bump ruff to 0.3.2 and black to 24 (#19878 )	2024-03-13 10:00:32 -07:00
requirements-training.txt	ONNX 1.15 integration (#17125 )	2023-09-26 14:44:48 -07:00
requirements.txt	Add compatibility for NumPy 2.0 (#21085 )	2024-06-27 13:50:53 -07:00
SECURITY.md	Microsoft mandatory file (#11619 )	2022-05-25 13:56:10 -07:00
setup.py	Migraphx ep windows build (#21284 )	2024-07-11 21:21:38 -07:00
ThirdPartyNotices.txt	Fix HalideIR title in third party notices reference (#20190 )	2024-04-05 11:12:43 -07:00
VERSION_NUMBER	Bump up version in main from 1.18.0 to 1.19.0 (#20489 )	2024-04-29 20:21:41 -07:00

README.md

ONNX Runtime is a cross-platform inference and training machine-learning accelerator.

ONNX Runtime inference can enable faster customer experiences and lower costs, supporting models from deep learning frameworks such as PyTorch and TensorFlow/Keras as well as classical machine learning libraries such as scikit-learn, LightGBM, XGBoost, etc. ONNX Runtime is compatible with different hardware, drivers, and operating systems, and provides optimal performance by leveraging hardware accelerators where applicable alongside graph optimizations and transforms. Learn more →

ONNX Runtime training can accelerate the model training time on multi-node NVIDIA GPUs for transformer models with a one-line addition for existing PyTorch training scripts. Learn more →

Get Started & Resources

General Information: onnxruntime.ai
Usage documentation and tutorials: onnxruntime.ai/docs
YouTube video tutorials: youtube.com/@ONNXRuntime
Upcoming Release Roadmap
Companion sample repositories:
- ONNX Runtime Inferencing: microsoft/onnxruntime-inference-examples
- ONNX Runtime Training: microsoft/onnxruntime-training-examples

Builtin Pipeline Status

System	Inference	Training
Windows
Linux
Mac
Android
iOS
Web
Other

Third-party Pipeline Status

System	Inference	Training
Linux

Data/Telemetry

Windows distributions of this project may collect usage data and send it to Microsoft to help improve our products and services. See the privacy statement for more details.

Contributions and Feedback

We welcome contributions! Please see the contribution guidelines.

For feature requests or bug reports, please file a GitHub Issue.

For general discussion or questions, please use GitHub Discussions.

Code of Conduct

This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact opencode@microsoft.com with any additional questions or comments.

License

This project is licensed under the MIT License.