2018-12-07 06:21:04 +00:00
< p align = "center" > < img width = "50%" src = "docs/images/ONNX_Runtime_logo_dark.png" / > < / p >
2021-02-12 00:50:32 +00:00
**ONNX Runtime** is a cross-platform **inference and training machine-learning accelerator** compatible with deep learning frameworks, PyTorch and TensorFlow/Keras, as well as classical machine learning libraries such as scikit-learn, and more.
2018-11-20 00:48:22 +00:00
2021-02-06 02:09:27 +00:00
ONNX Runtime uses the portable [ONNX ](https://onnx.ai ) computation graph format, backed by execution providers optimized for operating systems, drivers and hardware.
2019-03-06 06:38:40 +00:00
2021-02-12 00:50:32 +00:00
Common use cases for ONNX Runtime:
2021-02-06 02:09:27 +00:00
2020-05-19 03:08:36 +00:00
* Improve inference performance for a wide variety of ML models
* Reduce time and cost of training large models
* Train in Python but deploy into a C#/C++/Java app
2021-02-12 00:50:32 +00:00
* Run with optimized performance on different hardware and operating systems
2020-05-19 03:08:36 +00:00
* Support models created in several different frameworks
2018-12-01 06:10:26 +00:00
2021-02-12 00:50:32 +00:00
[ONNX Runtime inference ](https://www.onnxruntime.ai/docs/get-started/inference.html ) APIs are stable and production-ready since the [1.0 release ](https://github.com/microsoft/onnxruntime/releases/tag/v1.0.0 ) in October 2019 and can enable faster customer experiences and lower costs.
2020-05-19 03:08:36 +00:00
2021-02-12 00:50:32 +00:00
[ONNX Runtime training ](https://www.onnxruntime.ai/docs/get-started/training.html ) feature was introduced in May 2020 in preview. This feature supports acceleration of PyTorch training on multi-node NVIDIA GPUs for transformer models. Additional updates for this feature are coming soon.
2020-05-19 03:08:36 +00:00
2021-02-12 00:50:32 +00:00
## Get Started
2020-05-19 03:08:36 +00:00
2021-02-12 00:50:32 +00:00
**http://onnxruntime.ai/**
* [Install ](https://www.onnxruntime.ai/docs/get-started/install.html )
* [Inference ](https://www.onnxruntime.ai/docs/get-started/inference.html )
* [Training ](https://www.onnxruntime.ai/docs/get-started/training.html )
* [Documentation ](https://www.onnxruntime.ai/docs/ )
* [Samples and Tutorials ](https://www.onnxruntime.ai/docs/tutorials/ )
* [Frequently Asked Questions ](./docs/FAQ.md )
2020-05-19 03:08:36 +00:00
2021-02-12 00:50:32 +00:00
## Build Pipeline Status
|System|CPU|GPU|EPs|
2020-05-19 03:08:36 +00:00
|---|---|---|---|
2021-02-12 00:50:32 +00:00
|Windows|[](https://dev.azure.com/onnxruntime/onnxruntime/_build/latest?definitionId=9)|[](https://dev.azure.com/onnxruntime/onnxruntime/_build/latest?definitionId=10)|[](https://dev.azure.com/onnxruntime/onnxruntime/_build/latest?definitionId=47)|
|Linux|[](https://dev.azure.com/onnxruntime/onnxruntime/_build/latest?definitionId=11)< br > [](https://dev.azure.com/onnxruntime/onnxruntime/_build/latest?definitionId=64)< br > [](https://dev.azure.com/onnxruntime/onnxruntime/_build/latest?definitionId=110)< br > [](https://dev.azure.com/onnxruntime/onnxruntime/_build/latest?definitionId=78)< br > [](https://dev.azure.com/onnxruntime/onnxruntime/_build/latest?definitionId=86)|[](https://dev.azure.com/onnxruntime/onnxruntime/_build/latest?definitionId=12)< br > [](https://dev.azure.com/onnxruntime/onnxruntime/_build/latest?definitionId=45)< br > [](https://dev.azure.com/onnxruntime/onnxruntime/_build/latest?definitionId=140)< br > [](https://dev.azure.com/onnxruntime/onnxruntime/_build/latest?definitionId=84)|[](https://dev.azure.com/onnxruntime/onnxruntime/_build/latest?definitionId=110)< br > [](https://dev.azure.com/onnxruntime/onnxruntime/_build/latest?definitionId=108)|
|Mac|[](https://dev.azure.com/onnxruntime/onnxruntime/_build/latest?definitionId=13)< br > [](https://dev.azure.com/onnxruntime/onnxruntime/_build/latest?definitionId=65)|||
|Android|||[](https://dev.azure.com/onnxruntime/onnxruntime/_build/latest?definitionId=53)|
|iOS|||[](https://dev.azure.com/onnxruntime/onnxruntime/_build/latest?definitionId=134)|
2020-05-06 22:43:32 +00:00
2019-08-28 04:31:19 +00:00
2021-02-12 00:50:32 +00:00
## Data/Telemetry
2019-10-15 22:58:02 +00:00
2019-10-20 01:25:57 +00:00
This project may collect usage data and send it to Microsoft to help improve our products and services. See the [privacy statement ](docs/Privacy.md ) for more details.
2020-05-19 03:08:36 +00:00
2021-02-12 00:50:32 +00:00
## Contributions and Feedback
2020-05-19 03:08:36 +00:00
2019-07-02 00:11:50 +00:00
We welcome contributions! Please see the [contribution guidelines ](CONTRIBUTING.md ).
2018-11-20 00:48:22 +00:00
2021-02-12 00:50:32 +00:00
For feature requests or bug reports, please file a [GitHub Issue ](https://github.com/Microsoft/onnxruntime/issues ).
For general discussion or questions, please use [Github Discussions ](https://github.com/microsoft/onnxruntime/discussions ).
2018-11-20 00:48:22 +00:00
2018-11-27 10:28:55 +00:00
## Code of Conduct
2020-05-19 03:08:36 +00:00
2018-11-20 00:48:22 +00:00
This project has adopted the [Microsoft Open Source Code of Conduct ](https://opensource.microsoft.com/codeofconduct/ ).
For more information see the [Code of Conduct FAQ ](https://opensource.microsoft.com/codeofconduct/faq/ )
or contact [opencode@microsoft.com ](mailto:opencode@microsoft.com ) with any additional questions or comments.
2019-10-20 01:25:57 +00:00
2021-02-12 00:50:32 +00:00
## License
2020-05-19 03:08:36 +00:00
This project is licensed under the [MIT License ](LICENSE ).
