Skip to content

Conversation

@zhoux77899
Copy link
Contributor

@zhoux77899 zhoux77899 commented Jun 25, 2025

What this PR does / why we need it?

Fixes qwen3 w4a8 test case failed due to sampling_params not fixed and torch_npu updated.

Does this PR introduce any user-facing change?

None.

How was this patch tested?

Signed-off-by: ZhouXiang <zhouxiang100@huawei.com>
Signed-off-by: ZhouXiang <zhouxiang100@huawei.com>
Signed-off-by: ZhouXiang <zhouxiang100@huawei.com>
@MengqingCao
Copy link
Collaborator

LGTM, thanks for the fixing!

@yiz-liu
Copy link
Collaborator

yiz-liu commented Jun 26, 2025

@ganyi1996ppo @wangxiyuan Please review and merge this pull request at your earliest convenience, as it is currently blocking several other PRs.

@zhoux77899 Should also merge this to main? Thanks.

@wangxiyuan wangxiyuan merged commit 43591c3 into vllm-project:v0.9.1-dev Jun 26, 2025
7 checks passed
@wangxiyuan
Copy link
Collaborator

Quick merge to unblock the CI

@zhoux77899
Copy link
Contributor Author

@zhoux77899 Should also merge this to main? Thanks.

main has not this test case currently.

@Yikun Yikun added the no-main label Jul 14, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

5 participants