Skip to content

[Bugfix] graph batch size round up to tp size, when enable expert par… #1610

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged

Conversation

liziyu179
Copy link
Contributor

@liziyu179 liziyu179 commented Jul 3, 2025

What this PR does / why we need it?

graph batch size round up to tp size, when enable expert parallel

Does this PR introduce any user-facing change?

How was this patch tested?

…allel

Signed-off-by: liziyu <liziyu16@huawei.com>
@liziyu179 liziyu179 force-pushed the fix_graph_batch_size branch from 4a614a1 to bbf0ce6 Compare July 3, 2025 07:42
@ganyi1996ppo
Copy link
Collaborator

@zzzzwwjj This PR also fix the padding problem, merge this PR for emergency test, please close the #1607

@ganyi1996ppo ganyi1996ppo merged commit e878d56 into vllm-project:v0.9.1-dev Jul 3, 2025
19 of 22 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants