microsoft / microsoft/winml-cli

feature tracking: qnn cpu is supported but unusable yet

Open
#860 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

For Microsoft.WinML.Qualcomm.QNN.EP.2_2.2450.47.0_arm64__8wekyb3d8bbwe, qnn will report cpu as supported device, but could not be used on ort 1.24, so we explicitly declare only gpu, npu are supported

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.

Research direction

Start by investigating the Microsoft.WinML.Qualcomm.QNN.EP.2_2.2450.47.0_arm64__8wekyb3d8bbwe behavior with ONNX Runtime 1.24. Determine why CPU is reported as supported but cannot be used. Done means CPU support is usable or the explicit device declaration is updated based on the confirmed limitation.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.