microsoft / microsoft/onnxruntime-genai

DirectML inference Qwen2.5 contains messy code

Open
#1,638 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

ep:DML
Dominant language
C++
Stars
1.1k
Forks
354
Avg merge
2d 16h
Merged PRs (30d)
85

Description

When I try to use the model_qa.exe to inference Qwen2.5 7B ,contains lots of messy code on Intel Arrow lake iGPU (intel Ultra 7 255H igpu , driver version : 32.0.101.6913).

Image

It is ok on Intel Luna lake igpu, I dont know why this happend

Contributor guide

No contributing guide indexed for this repository

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 with model_qa.exe and reproduce Qwen2.5 7B inference on the Intel Arrow Lake iGPU using driver 32.0.101.6913. Compare the output with the reported working Intel Lunar Lake setup and inspect the inference path for the source of the messy output. Done means Qwen2.5 produces correct output on the affected hardware, with a regression test or documented reproduction if available.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.