ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Find a file
Sheil Kumar 85fa168dc1
Add optional dft_length input to the DFT and IDFT operators. (#11427)
* Add optional dft_length input.

* CR Feedback

Co-authored-by: Sheil Kumar <sheilk@microsoft.com>
2022-05-03 16:17:43 -07:00
.config A new pipeline to replace the existing WindowsAI packaging pipeline (#10646) 2022-03-03 08:56:49 -08:00
.gdn Update compliance tasks in python packaging pipeline and fix some compile warnings (#8471) 2021-07-30 17:16:37 -07:00
.github Github action: Inline lint python / js / cpp (#11328) 2022-04-26 14:17:28 -07:00
.pipelines A new pipeline to replace the existing WindowsAI packaging pipeline (#10646) 2022-03-03 08:56:49 -08:00
.vscode Add python docstring linting in vscode settings (#11316) 2022-04-23 06:23:04 -07:00
cgmanifests Update SafeInt version. (#11379) 2022-04-28 10:51:59 -07:00
cmake Re-implment the function support in onnxruntime (#11167) 2022-04-29 10:15:58 -07:00
csharp Format all python files under onnxruntime with black and isort (#11324) 2022-04-26 09:35:16 -07:00
dockerfiles Create Checkout Submodules Script (#11344) 2022-04-29 13:04:26 -07:00
docs Format all python files under onnxruntime with black and isort (#11324) 2022-04-26 09:35:16 -07:00
include/onnxruntime/core APIs for custom op to invoke ort operator directly (#10713) 2022-05-03 14:16:30 -07:00
java Specify list/map capacity when initializing where possible (#11110) 2022-04-27 20:59:18 -07:00
js [js] upgrade async@3.2.3 /js/web/ (#11426) 2022-05-03 14:04:22 -07:00
objectivec Format all python files under onnxruntime with black and isort (#11324) 2022-04-26 09:35:16 -07:00
onnxruntime Add optional dft_length input to the DFT and IDFT operators. (#11427) 2022-05-03 16:17:43 -07:00
orttraining Support ort device tensor in ortmodule's inference (#11112) 2022-05-03 14:28:30 -07:00
package/rpm Bump master version to 1.12 (#10797) 2022-03-28 12:30:11 -07:00
samples Format all python files under onnxruntime with black and isort (#11324) 2022-04-26 09:35:16 -07:00
server Format all python files under onnxruntime with black and isort (#11324) 2022-04-26 09:35:16 -07:00
tools [wasm] increase timeout for Web Assembly static lib CI (#11306) 2022-05-03 11:29:40 -07:00
winml Add optional dft_length input to the DFT and IDFT operators. (#11427) 2022-05-03 16:17:43 -07:00
.clang-format
.clang-tidy
.dockerignore
.flake8 Format all python files under onnxruntime with black and isort (#11324) 2022-04-26 09:35:16 -07:00
.gitattributes
.gitignore Add python docstring linting in vscode settings (#11316) 2022-04-23 06:23:04 -07:00
.gitmodules Upgrade emsdk to 3.1.3 (#10577) 2022-02-28 23:52:41 -08:00
build.amd64.1411.bat
build.bat
build.sh
CITATION.cff Fix CITATION.cff and add automatic validation of your citation metadata (#10478) 2022-04-13 10:03:52 -07:00
CODEOWNERS Update to use teams instead of individual GH handles (#11163) 2022-04-12 12:06:12 -07:00
CONTRIBUTING.md minor improvements to CONTRIBUTING doc (#11080) 2022-04-12 15:22:34 -07:00
lgtm.yml Add LGTM config for c++ and c# (#11365) 2022-04-27 10:51:40 -07:00
LICENSE
NuGet.config
ort.wprp
ORT_icon_for_light_bg.png Update nuget icon (#10672) 2022-03-01 09:11:03 -08:00
packages.config Bump winrt version (#10243) 2022-01-12 10:52:27 -08:00
pyproject.toml Set black's target version (#11370) 2022-04-27 14:52:19 -07:00
README.md Add OpenVINO Pipeline Status to README (#11299) 2022-04-21 15:59:50 -07:00
requirements-dev.txt Introduce parameterized as a dev dependency (#11364) 2022-04-26 17:24:39 -07:00
requirements-doc.txt
requirements-training.txt
requirements.txt.in
setup.py Update setup.py to include config files used by model analysis in wheel. (#11381) 2022-04-28 16:13:26 +10:00
ThirdPartyNotices.txt add copyright (#9943) (#9970) 2021-12-08 14:34:53 -08:00
VERSION_NUMBER Bump master version to 1.12 (#10797) 2022-03-28 12:30:11 -07:00

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

General Information: onnxruntime.ai

Usage documention and tutorials: onnxruntime.ai/docs

Companion sample repositories:

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
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.