removed lens calculation for qwen2_5#906
Closed
slokesha wants to merge 3 commits into
Closed
Conversation
Signed-off-by: slokesha <slokeshappa@habana.ai>
slokesha
requested review from
mgawarkiewicz-intel,
piotrbocian and
wpyszka
as code owners
Signed-off-by: slokesha <slokeshappa@habana.ai>
✅ CI PassedAll checks passed successfully against the following vllm commit: |
Signed-off-by: slokesha <slokeshappa@habana.ai>
✅ CI PassedAll checks passed successfully against the following vllm commit: |
michalkuligowski
approved these changes
Feb 3, 2026
| lens = (cu_seqlens[1:] - cu_seqlens[:-1]).tolist() | ||
| if mask is not None or len(lens) == 1: | ||
| if not qwen2_5_vl or (qwen2_5_vl and q_len < 65536): | ||
| if qwen2_5_vl: |
Collaborator
There was a problem hiding this comment.
Is this needed on main?
Collaborator
|
@slokesha - is this PR needed? Similiar changes were already merged to 0.14.1 |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Remove the lens = (cu_seqlens[1:] - cu_seqlens[:-1]).tolist() computation from the Qwen2.5 path.
This calculation is not required for Qwen2.5 and was causing a performance regression after PR #884. Removing it restores the previous performance without changing model behavior.