# Windows ML Overview

This section describes how to use **Windows ML on AMD Ryzen AI PCs** and complements the official [Microsoft Windows AI documentation](https://learn.microsoft.com/en-us/windows/ai/overview). It bridges Microsoft’s local AI platform with Ryzen AI hardware and software.

Microsoft provides a comprehensive AI platform for Windows spanning three pillars:

- **Windows AI APIs:** Built-in system APIs (OCR, image description, super resolution, object erase, etc.) for Copilot+ PCs. Use when your scenario is covered by these APIs.
- **Foundry Local:** On-device runtime for LLMs and generative AI; auto-detects hardware and downloads compatible models. Use for LLM scenarios with minimal setup.
- **Windows ML:** Runtime for custom ONNX models with automatic execution provider (EP) management across CPU, GPU, and NPU. Use when you need to run your own models.

On **Ryzen AI PCs**, Windows ML can leverage the NPU via the VitisAI EP (Execution Provider).

## When to Use Windows ML

Choose Windows ML when you:

- Need to run **custom ONNX models** (CNN, Transformer, or LLM) on Windows
- Want **automatic EP management** Windows downloads and registers compatible execution providers (VitisAI EP, MIGraphX EP, DirectML EP) on demand
- Prefer **C#, C++, or Python** with a shared Windows-wide ONNX Runtime (smaller app size)
- Need **hardware flexibility** select CPU, GPU, or NPU via execution policy

Use **Windows AI APIs** when built-in capabilities (OCR, image description, etc.) cover your scenario. Use **Foundry Local** when you want LLMs with minimal model preparation. Use the **Ryzen AI NPU-only flow** ([Model Compilation and Deployment](https://ryzenai.docs.amd.com/en/latest/modelrun.html)) when you need full control over ONNX Runtime without the Windows ML stack.

## Quick Links

| Topic                                                      | Page                                                                                                                               |
|------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------|
| Prerequisites and installation                             | [Installation](https://ryzenai.docs.amd.com/projects/WinML/en/latest/installation.html)                                            |
| VitisAI EP model support (CNN, Transformer, LLM)           | [VitisAI EP Model Support](https://ryzenai.docs.amd.com/projects/WinML/en/latest/model_support.html)                               |
| Model deployment                                           | [Model Deployment](https://ryzenai.docs.amd.com/projects/WinML/en/latest/model_deployment.html)                                    |
| Model conversion and quantization (AI Toolkit)             | [Model Conversion and Quantization (Foundry Toolkit)](https://ryzenai.docs.amd.com/projects/WinML/en/latest/model_conversion.html) |
| Execution providers (registration, EP policy, compilation) | [Execution Providers](https://ryzenai.docs.amd.com/projects/WinML/en/latest/winml_ep.html)                                         |
| Windows ML examples (CNN, Transformer, LLM)                | [Windows ML Example](https://ryzenai.docs.amd.com/projects/WinML/en/latest/winml_example.html)                                     |
| Frequently asked questions                                 | [Frequently Asked Questions](https://ryzenai.docs.amd.com/projects/WinML/en/latest/faq.html)                                       |
| Troubleshooting                                            | [Troubleshooting](https://ryzenai.docs.amd.com/projects/WinML/en/latest/troubleshooting.html)                                      |

## External Resources

- [Windows AI Developer Portal](https://developer.microsoft.com/en-us/windows/ai/)
- [Windows ML official documentation](https://learn.microsoft.com/en-us/windows/ai/new-windows-ml/overview)
- [AI on Windows samples (Microsoft Learn)](https://learn.microsoft.com/en-us/windows/ai/samples/)
- [WindowsAppSDK-Samples — WindowsML](https://github.com/microsoft/WindowsAppSDK-Samples/tree/main/Samples/WindowsML)
- [RyzenAI-SW Windows ML examples](https://github.com/amd/RyzenAI-SW/tree/main/WinML)

 <!-- ------------

 #####################################
 License
 #####################################

Ryzen AI is licensed under `MIT License <https://github.com/amd/ryzen-ai-documentation/blob/main/License>`_ . Refer to the `LICENSE File <https://github.com/amd/ryzen-ai-documentation/blob/main/License>`_ for the full license text and copyright notice. -->