Awesome
<p align="center"><img width="50%" src="docs/images/ONNX_Runtime_logo_dark.png" /></p>ONNX Runtime is a cross-platform inference and training machine-learning accelerator.
Systolic Quickstart
This is a fork of upstream onnxruntime modified to work on riscv platforms and particularly focused on supporting the Gemmini accelerator. Gemmini is not necessarily required though, so this should also be suitable for those wanting to perform cpu-only inference on a riscv platform -- although this is less thoroughly tested so may not be as performant (the main blocker I can think of is that the sgemm
kernel is implemented via naive matmul; ideally this should be linked with a proper BLAS implementation, but since floating point inference was not the main goal with this fork – rather, running quantized networks was – that is still a todo).
Read BUILD.md in systolic_runner
(along with other documentation) for information on cross-compiling and usage instructions.
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
Build Pipeline Status
System | CPU | GPU | EPs |
---|---|---|---|
Windows | |||
Linux | <br><br><br><br> | <br><br><br> | <br> |
Mac | <br> | ||
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.