microsoft / microsoft/winml-cli

bug: winml sys device shows device does not exist on current machine

Open
#739 2 comments 0 reactions 1 assignee View on GitHub

@timenick is already working on this.

Since May 26, 2026.

bug hardware P2 triaged
Dominant language
Python
Stars
40
Forks
11
Avg merge
1d 8h
Merged PRs (30d)
50

Description

the OpenVINOExecutionProvider GPU is not exist in my machine.

(winml-cli) PS C:\Dev\MKs\ModelKit> winml sys
╭──────────────────────────────╮
│ WinML CLI System Information │
╰──────────────────────────────╯

Environment
Python Version 3.11.14
Python Executable C:\Dev\MKs\ModelKit.venv\Scripts\python.exe
OS Windows 11
Machine AMD64

ML Libraries
Library Version Status
torch 2.12.0 OK
transformers 4.57.6 OK
onnx 1.18.0 OK
optimum 2.1.0 OK
numpy 2.2.6 OK
click 8.4.0 OK
rich 15.0.0 OK
onnxruntime 1.24.5.202604171637 (windowsml) OK

Available Devices (priority order)
#1 NPU Intel(R) AI Boost
Driver: 32.0.100.4724 | Manufacturer: Intel Corporation
#2 GPU NVIDIA GeForce RTX 5070
Driver: 32.0.15.9186 | Manufacturer: NVIDIA
#3 CPU Intel(R) Core(TM) Ultra 7 265K
Cores: 20 | Threads: 20 | Architecture: x64

Available Execution Providers
OpenVINOExecutionProvider -> NPU/GPU/CPU
Path: C:\Program
Files\WindowsApps\MicrosoftCorporationII.WinML.Intel.OpenVINO.EP.1.8_1.8.26.0_x64__8wekyb3d8bbwe\ExecutionProvider\onnxruntime_providers_openvino_plugin.dll
NvTensorRTRTXExecutionProvider -> GPU
Path: C:\Program
Files\WindowsApps\MicrosoftCorporationII.WinML.NVIDIA.TRT-RTX.EP.2_0.0.28.0_x64__8wekyb3d8bbwe\ExecutionProvider\onnxruntime_providers_nv_tensorrt_rtx.dll
DmlExecutionProvider -> GPU
(built-in)
CPUExecutionProvider -> CPU
(built-in)

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.