Skip to content

Conversation

@momo609
Copy link
Collaborator

@momo609 momo609 commented Aug 1, 2025

What this PR does / why we need it?

Does this PR introduce any user-facing change?

How was this patch tested?

@github-actions
Copy link

github-actions bot commented Aug 1, 2025

👋 Hi! Thank you for contributing to the vLLM Ascend project. The following points will speed up your PR merge:‌‌

  • A PR should do only one thing, smaller PRs enable faster reviews.
  • Every PR should include unit tests and end-to-end tests ‌to ensure it works and is not broken by other future PRs.
  • Write the commit message by fulfilling the PR description to help reviewer and future developers understand.

If CI fails, you can run linting and testing checks locally according Contributing and Testing.

hidden_states = torch.cat(hidden_states, dim=0)
return hidden_states

w1 = w1.transpose(1, 2)
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Duplicate code?

wangxiaoxin-sherie added 2 commits August 8, 2025 15:05
@github-actions
Copy link

This pull request has conflicts, please resolve those before we can evaluate the pull request.


return final_hidden_states

class QuantizedTokenDispatcherWithAllGather(MoETokenDispatcher):
Copy link
Contributor

@realliujiaxu realliujiaxu Aug 26, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

fused_experts_with_allgather is not transferred here. when expert_map is not None, this is really slow

@momo609 momo609 closed this Sep 1, 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.

3 participants