Note
Access to this page requires authorization. You can try signing in or changing directories.
Access to this page requires authorization. You can try changing directories.
Windows ML supports the following execution providers. To learn more about execution providers, see the ONNX Runtime docs.
Included execution providers
The following execution providers are included with the ONNX Runtime that ships with Windows ML:
- CPU
- DirectML
Available execution providers
The execution providers listed below are available (depending on device and driver compatibility) for dynamic download and registration via the Windows ML ExecutionProviderCatalog APIs (see Initialize execution providers). Before you download an execution provider, please be sure to read the licenses corresponding to the execution provider.
| Name (Vendor) | Requirements | License Terms |
|---|---|---|
"NvTensorRtRtxExecutionProvider"(Nvidia) |
NVIDIA GeForce RTX 30XX and above with minimum recommended driver version 32.0.15.5585 + Cuda version 12.5 | eula-12Aug2025.pdf License Agreement for NVIDIA Software Development Kits — EULA |
"OpenVINOExecutionProvider"(Intel) |
CPU: Intel TigerLake (11th Gen) and above with min recommended driver 32.0.100.9565 GPU: Intel AlderLake (12th Gen) and above with min recommended driver 32.0.101.1029 NPU: Intel ArrowLake (15th Gen) and above with min recommended driver 32.0.100.4239 |
Intel OBL Distribution Commercial Use License Agreement v2025.02.12 |
"QNNExecutionProvider"(Qualcomm) |
Snapdragon(R) X Elite - X1Exxxxx - Qualcomm(R) Hexagon(TM) NPU with minimum driver version 30.0.140.0 and above Snapdragon(R) X Plus - X1Pxxxxx - Qualcomm(R) Hexagon(TM) NPU with minimum driver version 30.0.140.0 and above |
To view the QNN License, download the Qualcomm® Neural Processing SDK, extract the ZIP, and open the LICENSE.pdf file. |
"VitisAIExecutionProvider"(AMD) |
Min: Adrenalin Edition 25.6.3 with NPU driver 32.00.0203.280 Max: Adrenalin Edition 25.9.1 with NPU driver 32.00.0203.297 |
No additional license required |