[Bugfix] Fix Qwen2.5-Omni-7B accuarcy test #4556
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
👋 Hi! Thank you for contributing to the vLLM Ascend project. The following points will speed up your PR merge:
If CI fails, you can run linting and testing checks locally according Contributing and Testing. |
vllm-ascend-ci
added
accuracy-test
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Code Review
This pull request addresses a bug for the Qwen2.5-Omni-7B model by making attribute access more robust. The changes in vllm_ascend/ops/layernorm.py and vllm_ascend/ops/register_custom_ops.py use getattr with a default value to prevent potential AttributeError crashes. This is a good defensive programming practice that correctly fixes the issue. The changes are sound and I have no further suggestions.
Contributor
Author
|
@shen-shanshan |
Contributor
Author
fixed by : #4534 @Meihan-chen |
zhangxinyuehfad
force-pushed
the
zxy_fix_omini
branch
from
e047f15 to
b20e2ff
Compare
vllm-ascend-ci
removed
ready-for-test
zhangxinyuehfad
force-pushed
the
zxy_fix_omini
branch
from
b20e2ff to
c88edea
Compare
wangxiyuan
approved these changes
Dec 1, 2025
|
This pull request has conflicts, please resolve those before we can evaluate the pull request. |
Signed-off-by: hfadzxy <[email protected]>
zhangxinyuehfad
force-pushed
the
zxy_fix_omini
branch
from
c88edea to
e5f2fdc
Compare
wangxiyuan
added a commit
to wangxiyuan/vllm-ascend
that referenced
this pull request
Dec 2, 2025
This reverts commit 71e9b37.
wangxiyuan
added a commit
that referenced
this pull request
Dec 2, 2025
ChenCangtao
pushed a commit
to ChenCangtao/vllm-ascend
that referenced
this pull request
Dec 3, 2025
### What this PR does / why we need it? Fix Qwen2.5-Omni-7B accuarcy test issue：vllm-project#4480 Depends on : vllm-project#4534 - vLLM version: v0.11.2 - vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2 Signed-off-by: hfadzxy <[email protected]>
ChenCangtao
pushed a commit
to ChenCangtao/vllm-ascend
that referenced
this pull request
Dec 3, 2025
…" (vllm-project#4619) This reverts commit 71e9b37. It breaks vllm-ascend/Qwen3-30B-A3B-W8A8 test
Mercykid-bash
pushed a commit
to Mercykid-bash/vllm-ascend
that referenced
this pull request
Dec 4, 2025
### What this PR does / why we need it? Fix Qwen2.5-Omni-7B accuarcy test issue：vllm-project#4480 Depends on : vllm-project#4534 - vLLM version: v0.11.2 - vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2 Signed-off-by: hfadzxy <[email protected]> Signed-off-by: Che Ruan <[email protected]>
Mercykid-bash
pushed a commit
to Mercykid-bash/vllm-ascend
that referenced
this pull request
Dec 4, 2025
…" (vllm-project#4619) This reverts commit 71e9b37. It breaks vllm-ascend/Qwen3-30B-A3B-W8A8 test Signed-off-by: Che Ruan <[email protected]>
Mercykid-bash
pushed a commit
to Mercykid-bash/vllm-ascend
that referenced
this pull request
Dec 4, 2025
### What this PR does / why we need it? Fix Qwen2.5-Omni-7B accuarcy test issue：vllm-project#4480 Depends on : vllm-project#4534 - vLLM version: v0.11.2 - vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2 Signed-off-by: hfadzxy <[email protected]> Signed-off-by: Che Ruan <[email protected]>
Mercykid-bash
pushed a commit
to Mercykid-bash/vllm-ascend
that referenced
this pull request
Dec 4, 2025
…" (vllm-project#4619) This reverts commit 71e9b37. It breaks vllm-ascend/Qwen3-30B-A3B-W8A8 test Signed-off-by: Che Ruan <[email protected]>
Meihan-chen
pushed a commit
to Meihan-chen/vllm-ascend
that referenced
this pull request
Dec 5, 2025
### What this PR does / why we need it? Fix Qwen2.5-Omni-7B accuarcy test issue：vllm-project#4480 Depends on : vllm-project#4534 - vLLM version: v0.11.2 - vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2 Signed-off-by: hfadzxy <[email protected]>
Meihan-chen
pushed a commit
to Meihan-chen/vllm-ascend
that referenced
this pull request
Dec 5, 2025
…" (vllm-project#4619) This reverts commit 71e9b37. It breaks vllm-ascend/Qwen3-30B-A3B-W8A8 test
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What this PR does / why we need it?
Fix Qwen2.5-Omni-7B accuarcy test
issue：#4480
Depends on : #4534
Does this PR introduce any user-facing change?
How was this patch tested?
accuracy test:https://github.com/vllm-project/vllm-ascend/actions/runs/19808047476?pr=4556
