# onnx-runtime-unity **Repository Path**: Guoyonghui666/onnx-runtime-unity ## Basic Information - **Project Name**: onnx-runtime-unity - **Description**: onnx-runtime - **Primary Language**: C# - **License**: MIT - **Default Branch**: master - **Homepage**: https://gitee.com/Guoyonghui666/ - **GVP Project**: No ## Statistics - **Stars**: 0 - **Forks**: 0 - **Created**: 2025-12-23 - **Last Updated**: 2026-04-02 ## Categories & Tags **Categories**: Uncategorized **Tags**: None ## README # ONNX Runtime Plugin for Unity [![upm](https://img.shields.io/npm/v/com.github.asus4.onnxruntime?label=upm)](https://www.npmjs.com/package/com.github.asus4.onnxruntime) Pre-built ONNX Runtime libraries for Unity. ## [See Examples](https://github.com/asus4/onnxruntime-unity-examples) [https://github.com/asus4/onnxruntime-unity-examples](https://github.com/asus4/onnxruntime-unity-examples) Yolox NanoSAM ## Tested environment - Unity: 2022.3.20f1 (LTS) - ONNX Runtime: [1.19.2](https://github.com/microsoft/onnxruntime/releases/tag/v1.19.2) - ONNX Runtime Extensions: [0.12.0](https://github.com/microsoft/onnxruntime-extensions/releases/tag/v0.12.0) ### Execution Providers & Extensions #### [Execution Providers](https://onnxruntime.ai/docs/execution-providers/) Execution Providers are hardware acceleration libraries for each platform. See [official docs](https://onnxruntime.ai/docs/execution-providers/) for more details. | Platform | CPU | CoreML | NNAPI | CUDA | TensorRT | DirectML | XNNPACK | | --- | --- | --- | --- | --- | --- | --- | --- | | macOS | :white_check_mark: | :white_check_mark: | | | | | | | iOS | :white_check_mark: | :white_check_mark: | | | | | :construction: | | Android | :white_check_mark: | | :white_check_mark: | | | | :construction: | | Windows | :white_check_mark: | | | :construction: | :construction: | :white_check_mark: | | | Linux | :white_check_mark: | | | :construction: | :construction: | | | #### [ONNX Runtime Extensions](https://github.com/microsoft/onnxruntime-extensions) ONNX Runtime Extensions are a set of pre/post-processing. | Platform | Extensions | | --- | --- | | macOS | :construction: | | iOS | :construction: | | Android | :construction: | | Windows | :construction: | | Linux | :construction: | :white_check_mark: : Supported in Unity Core library :construction: : Experimental Preview ## How to Install Pre-built libraries are available on [NPM](https://www.npmjs.com/package/com.github.asus4.onnxruntime). Add the following `scopedRegistries` and `dependencies` in `Packages/manifest.json`. ```json "scopedRegistries": [ { "name": "NPM", "url": "https://registry.npmjs.com", "scopes": [ "com.github.asus4" ] } ] "dependencies": { "com.github.asus4.onnxruntime": "0.2.0", "com.github.asus4.onnxruntime.unity": "0.2.0", "com.github.asus4.onnxruntime.win-x64-gpu": "0.2.0", "com.github.asus4.onnxruntime.linux-x64-gpu": "0.2.0", "com.github.asus4.onnxruntime-extensions": "0.2.0", ... other dependencies } ``` ### What is included in each package - `com.github.asus4.onnxruntime` : Core library - CPU provider for all platforms - GPU provider for iOS, Android, macOS and Windows(only DirectML) - `com.github.asus4.onnxruntime.unity` : (Optional) Utilities for Unity - `com.github.asus4.onnxruntime.win-x64-gpu` : (Optional) GPU provider for Windows - `com.github.asus4.onnxruntime.linux-x64-gpu` : (Optional) GPU provider for Linux - `com.github.asus4.onnxruntime-extensions` : (Optional) ONNX Runtime Extensions