[Bugfix]Fix eplb enable when using mtp float weights. #4571
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
Signed-off-by: offline0806 <[email protected]>
![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 fixes an issue where expert load balancing (EPLB) could not be enabled with float weights. The change introduces a temporary flag, init_eplb_enable, to conditionally bypass a quantization check that was incorrectly triggered for float weights, specifically for dynamic EPLB. The logic seems correct. I've added one comment to improve the clarity of the TODO comment associated with this temporary flag, which will enhance code maintainability.
|
👋 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. |
Signed-off-by: offline0806 <[email protected]>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> Signed-off-by: offline893 <[email protected]>
Collaborator
|
plz rebase to the latest main to run ci correctly |
MengqingCao
added
ready
MengqingCao
approved these changes
Dec 2, 2025
Collaborator
MengqingCao
left a comment
MengqingCao
left a comment
There was a problem hiding this comment.
LGTM, thanks for this fix!
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 eplb enable when using mtp float weights. It will be remove when eplb supporting mtp and float weights. ### How was this patch tested? Deepseek-V3 + MTP + EPLB in A3. - vLLM version: v0.11.2 - vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2 --------- Signed-off-by: offline0806 <[email protected]> Signed-off-by: offline893 <[email protected]> Co-authored-by: offline0806 <[email protected]> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
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 eplb enable when using mtp float weights. It will be remove when eplb supporting mtp and float weights. ### How was this patch tested? Deepseek-V3 + MTP + EPLB in A3. - vLLM version: v0.11.2 - vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2 --------- Signed-off-by: offline0806 <[email protected]> Signed-off-by: offline893 <[email protected]> Co-authored-by: offline0806 <[email protected]> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> 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 eplb enable when using mtp float weights. It will be remove when eplb supporting mtp and float weights. ### How was this patch tested? Deepseek-V3 + MTP + EPLB in A3. - vLLM version: v0.11.2 - vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2 --------- Signed-off-by: offline0806 <[email protected]> Signed-off-by: offline893 <[email protected]> Co-authored-by: offline0806 <[email protected]> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> Signed-off-by: Che Ruan <[email protected]>
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 eplb enable when using mtp float weights. It will be remove when eplb supporting mtp and float weights.
Does this PR introduce any user-facing change?
How was this patch tested?
Deepseek-V3 + MTP + EPLB in A3.
![Uploading image.png…]()