ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Find a file
xkszltl 3a9f30df46
Compatibility patch for nlohmann/json < 3.9.0. (#12394)
This is required on CentOS 7 if using distro-provided json-devel 3.6.1.

Regression introduced in:
- https://github.com/microsoft/onnxruntime/pull/11775

Related upstream commit:
-
74520d8bb0

Fixed https://github.com/microsoft/onnxruntime/issues/12393
2023-01-17 10:59:20 +10:00
.config Update tsaoptions.json: update the email alias (#13448) 2022-10-26 15:56:16 -07:00
.devcontainer
.gdn
.github Delete add-issues-to-project (#14147) 2023-01-11 14:33:37 -08:00
.pipelines [DML EP] Upgrade DML to 1.10.0 (#13796) 2022-11-30 21:32:14 -08:00
.vscode
cgmanifests [CPU] Resize of Opset 18 (#13890) 2023-01-14 08:57:23 +10:00
cmake Fix build error on Windows if Python debug libraries are installed (#14308) 2023-01-17 09:48:26 +10:00
csharp [CPU] Resize of Opset 18 (#13890) 2023-01-14 08:57:23 +10:00
dockerfiles Openvino ep 2022.3 v4.3 (#14210) 2023-01-11 16:31:26 -08:00
docs Add present_past_share_buff to QAttention Defs to enable QAttention related tests. (#14297) 2023-01-14 09:19:06 -08:00
include/onnxruntime/core Add ability to register custom ops by specifying a function name (#14177) 2023-01-12 15:11:34 +10:00
java Add Java and Objective-C bindings for RegisterCustomOpsUsingFunction. (#14256) 2023-01-13 09:04:26 -08:00
js [web] utility functions for tensor<->image conversion in ORT web (#13603) 2023-01-12 09:05:18 -08:00
objectivec Add Java and Objective-C bindings for RegisterCustomOpsUsingFunction. (#14256) 2023-01-13 09:04:26 -08:00
onnxruntime Compatibility patch for nlohmann/json < 3.9.0. (#12394) 2023-01-17 10:59:20 +10:00
orttraining Improved test cases by using paramerters (#14246) 2023-01-13 12:54:23 -08:00
package/rpm Bumping up version number to 1.14.0 on main branch (#13401) 2022-10-21 19:16:44 -04:00
samples
test Multi-stream execution support (#13495) 2022-12-15 07:39:29 -08:00
tools install shared deps script (#14234) 2023-01-16 18:27:29 +08:00
winml Enabling thread pool to be numa-aware (#13778) 2022-12-12 10:33:55 -08:00
.clang-format
.clang-tidy Create clang-tidy CI (#12653) 2022-09-30 08:05:38 -07:00
.dockerignore
.flake8 Remove miscellaneous nuphar configs (#13070) 2022-09-26 13:41:28 -07:00
.gitattributes
.gitignore Ignore more build directories and clangd files (#14154) 2023-01-07 06:58:57 +08:00
.gitmodules Remove unused git submodules (#13830) 2022-12-07 21:59:16 -08:00
build.amd64.1411.bat
build.bat
build.sh
CITATION.cff
CODEOWNERS Add cgmanifest file in codeowner list (#13042) 2022-09-22 18:58:01 -07:00
CONTRIBUTING.md
lgtm.yml Fix lgtm C++ error (#13613) 2022-11-10 10:06:22 -08:00
LICENSE
NuGet.config
ort.wprp
ORT_icon_for_light_bg.png
packages.config [DML EP] Upgrade DML to 1.10.0 (#13796) 2022-11-30 21:32:14 -08:00
pyproject.toml Update pylint config to include valid short names (#13631) 2022-11-14 10:00:25 -08:00
README.md Update resource section in readme (#13724) 2022-11-28 09:42:31 -08:00
requirements-dev.txt
requirements-doc.txt
requirements-training.txt Remove protobuf pin from training requirements (#13695) 2022-11-22 12:27:18 -08:00
requirements.txt.in
SECURITY.md
setup.py Openvino ep 2022.3 v4.3 (#14210) 2023-01-11 16:31:26 -08:00
ThirdPartyNotices.txt [CPU] Resize of Opset 18 (#13890) 2023-01-14 08:57:23 +10:00
VERSION_NUMBER Bumping up version number to 1.14.0 on main branch (#13401) 2022-10-21 19:16:44 -04:00

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

Build Pipeline Status

System CPU GPU EPs
Windows Build Status Build Status Build Status
Linux Build Status
Build Status
Build Status
Build Status
Build Status
Build Status
Build Status
Build Status
Build Status
Build Status
Mac Build Status
Build Status
Android Build Status
iOS Build Status
WebAssembly Build Status

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.