saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-05-31 23:27:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Readme updates (#4448)

Browse source 
* Readme updates

* Update package repo table
This commit is contained in:
Faith Xu 2020-07-29 13:25:36 -07:00 committed by GitHub
parent db475c4f35
commit d8f3e46d45
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 10 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

15
README.md
View file

@ -69,7 +69,7 @@ ONNX Runtime is up to date and backwards compatible with all operators (both DNN
### Binaries
Official builds are available on PyPi (Python) and Nuget (C#/C/C++):
Official builds are available on PyPi (Python), Nuget (C#/C/C++), Maven Central (Java), and npm (node.js).
* Default CPU Provider (Eigen + MLAS)
* GPU Provider - NVIDIA CUDA
@ -78,9 +78,14 @@ Official builds are available on PyPi (Python) and Nuget (C#/C/C++):
Dev builds created from the master branch are available for testing newer changes between official releases. Please use these at your own risk. We strongly advise against deploying these to production workloads as support is limited for dev builds.
|Pypi (Python)|Nuget (C#/C/C++)|Other package repositories|
|---|---|---|
*If using pip, run `pip install --upgrade pip` prior to downloading.*<br><br>CPU: [**onnxruntime**](https://pypi.org/project/onnxruntime) / [ort-nightly (dev)](https://test.pypi.org/project/ort-nightly)<br><br>GPU: [**onnxruntime-gpu**](https://pypi.org/project/onnxruntime-gpu) / [ort-gpu-nightly (dev)](https://test.pypi.org/project/ort-gpu-nightly) | CPU: [**Microsoft.ML.OnnxRuntime**](https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime) / [ort-nightly (dev)](https://aiinfra.visualstudio.com/PublicPackages/_packaging?_a=feed&feed=ORT-Nightly) <br><br>GPU: [**Microsoft.ML.OnnxRuntime.Gpu**](https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime.gpu) / [ort-nightly (dev)](https://aiinfra.visualstudio.com/PublicPackages/_packaging?_a=feed&feed=ORT-Nightly)</li></ul>|[Contributed non-official packages](https://docs.microsoft.com/en-us/windows/ai/windows-ml/get-started-uwp) (including Homebrew, Linuxbrew, and nixpkgs)<br><br>*These are not maintained by the core ONNX Runtime team and may have limited support; use at your discretion.*|
|Repository|Details|
|---|---|
|Pypi (Python)|*If using pip, run `pip install --upgrade pip` prior to downloading.*<br>CPU: [**onnxruntime**](https://pypi.org/project/onnxruntime) / [ort-nightly (dev)](https://test.pypi.org/project/ort-nightly)<br>GPU: [**onnxruntime-gpu**](https://pypi.org/project/onnxruntime-gpu) / [ort-gpu-nightly (dev)](https://test.pypi.org/project/ort-gpu-nightly)|
|Nuget (C#/C/C++)|CPU: [**Microsoft.ML.OnnxRuntime**](https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime) / [ort-nightly (dev)](https://aiinfra.visualstudio.com/PublicPackages/_packaging?_a=feed&feed=ORT-Nightly) <br>GPU: [**Microsoft.ML.OnnxRuntime.Gpu**](https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime.gpu) / [ort-nightly (dev)](https://aiinfra.visualstudio.com/PublicPackages/_packaging?_a=feed&feed=ORT-Nightly)</li></ul>|
|Maven Central (Java)|CPU: [**com.microsoft.onnxruntime/onnxruntime**](https://search.maven.org/artifact/com.microsoft.onnxruntime/onnxruntime)<br>GPU: [**com.microsoft.onnxruntime/onnxruntime_gpu**](https://search.maven.org/artifact/com.microsoft.onnxruntime/onnxruntime_gpu)|
|npm (node.js)|CPU: [**onnxruntime**](https://www.npmjs.com/package/onnxruntime)|
|Other|[Contributed non-official packages](https://docs.microsoft.com/en-us/windows/ai/windows-ml/get-started-uwp) (including Homebrew, Linuxbrew, and nixpkgs)<br>*These are not maintained by the core ONNX Runtime team and may have limited support; use at your discretion.*|
#### System Requirements
@ -137,7 +142,7 @@ For production scenarios, it's strongly recommended to build only from an [offic
|CPU|GPU|IoT/Edge/Mobile|Other|
|---|---|---|---|
|<ul><li>Default CPU - *MLAS (Microsoft Linear Algebra Subprograms) + Eigen*</li><li>[Intel DNNL](./docs/execution_providers/DNNL-ExecutionProvider.md)</li><li>[Intel nGraph](./docs/execution_providers/nGraph-ExecutionProvider.md)</li><li>Intel MKL-ML *(build option)*</li></ul>|<ul><li>NVIDIA CUDA</li><li>[NVIDIA TensorRT](./docs/execution_providers/TensorRT-ExecutionProvider.md)</li><li>[DirectML](./docs/execution_providers/DirectML-ExecutionProvider.md)</li><li>[AMD MIGraphX](./docs/execution_providers/MIGraphX-ExecutionProvider.md)</li></ul>|<ul><li>[Intel OpenVINO](./docs/execution_providers/OpenVINO-ExecutionProvider.md)</li><li>[ARM Compute Library](./docs/execution_providers/ACL-ExecutionProvider.md) (*preview*)</li><li>[Android Neural Networks API](./docs/execution_providers/NNAPI-ExecutionProvider.md) (*preview*)</li></ul>|<ul><li>[Nuphar Model Compiler](./docs/execution_providers/Nuphar-ExecutionProvider.md) - (*preview*)</li><li>[Rockchip NPU](./docs/execution_providers/RKNPU-ExecutionProvider.md) (*preview*)</li><li>[Xilinx Vitis-AI](./docs/execution_providers/Vitis-AI-ExecutionProvider.md) (*preview*)</li></ul>|
|<ul><li>Default CPU - *MLAS (Microsoft Linear Algebra Subprograms) + Eigen*</li><li>[Intel DNNL](./docs/execution_providers/DNNL-ExecutionProvider.md)</li><li>[Intel nGraph](./docs/execution_providers/nGraph-ExecutionProvider.md)</li><li>Intel MKL-ML *(build option)*</li></ul>|<ul><li>NVIDIA CUDA</li><li>[NVIDIA TensorRT](./docs/execution_providers/TensorRT-ExecutionProvider.md)</li><li>[DirectML](./docs/execution_providers/DirectML-ExecutionProvider.md)</li><li>[AMD MIGraphX](./docs/execution_providers/MIGraphX-ExecutionProvider.md)</li></ul>|<ul><li>[Intel OpenVINO](./docs/execution_providers/OpenVINO-ExecutionProvider.md)</li><li>[ARM Compute Library](./docs/execution_providers/ACL-ExecutionProvider.md) (*preview*)</li><li>[Android Neural Networks API](./docs/execution_providers/NNAPI-ExecutionProvider.md) (*preview*)</li><li>[ARM-NN](./docs/execution_providers/ArmNN-ExecutionProvider.md) (*preview*)</li></ul>|<ul><li>[Nuphar Model Compiler](./docs/execution_providers/Nuphar-ExecutionProvider.md) - (*preview*)</li><li>[Rockchip NPU](./docs/execution_providers/RKNPU-ExecutionProvider.md) (*preview*)</li><li>[Xilinx Vitis-AI](./docs/execution_providers/Vitis-AI-ExecutionProvider.md) (*preview*)</li></ul>|
* [Roadmap: Upcoming accelerators](./docs/Roadmap.md#accelerators-and-execution-providers)
* [Extensibility: Add an execution provider](docs/AddingExecutionProvider.md)