868c8af9ac
* Adding pipeline file for eager mode * adding the build eager mode flag * adding torch wheel files for installation * Changing pytorch version for change in wheel files * updating requirements file path * Removing Java and NodeJS from the build * removing import torch for testing build of eager mode * changing the build command * import torch * building eager mode separately * removing Java tests * python path issues * changing python path location * changing the build path file loc * installing torch before build * setting environment for building eager mode * Copying the build file and getting rid of flags * changing python path * adding missing packages * moving build eager mode code * changing python path to python3 * adding amd_hipify * adding logger file * install torch before build * change requirements file location * install torch before build eager * modifying eager mode build * modifying build location * adding new docker image * handling gradle move issue * Typo fix * changing deps file * adding java and nodejs * changing repo name for docker image * removing pybind * building only eager mode * changing the image name * removing install wheel package * build complete onnxruntime with eager mode * building wheel * enabling pybind * adding build eager mode flag in unit tests * removing build java nodejs * adding build command * removing java tests * moving Debug tests before Release * building Debug only case * changing debug test code * running the build eager mode with tests * adding build dir * adding build dir path * changing build dir path * changing build command for eager mode * building eager mode and running tests simultaneously * adding more flags to the pipeline * chaning flag * adding Debug and Release * changing torch to nightly build * changing torch version for nightly build * chaning torch version * move to Ubuntu image * adding pool * adding dockerfile for eager mode * adding python deps file for eager * modifying python deps file for eager * changing deps file * changing deps file statements * changing python path * REMOVING ECHO line * going to original docker file * changing docker file * changing to eager requirements file * changing python deps file * changing paths * changing cmake path * changing build script * changing python installation * running debug mode only * changing pipeline file * test name * test name * test name2 * changing requirements file * final flags for eager mode * previous pipeline * moving to ubuntu image and including some deps * adding cmake path * returning to manylinux image * removing unncecessary files for pipeline |
||
|---|---|---|
| .gdn | ||
| .github | ||
| cgmanifests | ||
| cmake | ||
| csharp | ||
| dockerfiles | ||
| docs | ||
| include/onnxruntime/core | ||
| java | ||
| js | ||
| objectivec | ||
| onnxruntime | ||
| orttraining | ||
| package/rpm | ||
| samples | ||
| server | ||
| tools | ||
| winml | ||
| .clang-format | ||
| .clang-tidy | ||
| .dockerignore | ||
| .flake8 | ||
| .gitattributes | ||
| .gitignore | ||
| .gitmodules | ||
| build.amd64.1411.bat | ||
| build.bat | ||
| build.sh | ||
| CODEOWNERS | ||
| CONTRIBUTING.md | ||
| LICENSE | ||
| NuGet.config | ||
| ort.wprp | ||
| packages.config | ||
| README.md | ||
| requirements-dev.txt | ||
| requirements-doc.txt | ||
| requirements-training.txt | ||
| requirements.txt.in | ||
| setup.py | ||
| ThirdPartyNotices.txt | ||
| VERSION_NUMBER | ||
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
General Information: onnxruntime.ai
Usage documention and tutorials: onnxruntime.ai/docs
Companion sample repositories:
- ONNX Runtime Inferencing: microsoft/onnxruntime-inference-examples
- ONNX Runtime Training: microsoft/onnxruntime-training-examples
Build Pipeline Status
| System | CPU | GPU | EPs |
|---|---|---|---|
| Windows | |||
| Linux | |||
| Mac | |||
| Android | |||
| iOS | |||
| WebAssembly |
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.