Skip to content

[EP] LL kernel buffer tokens #542

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.

Sign up for GitHub

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

Jump to bottom
Open
MaoZiming wants to merge 4 commits into
base: main
Choose a base branch
from
Open

[EP] LL kernel buffer tokens #542

MaoZiming wants to merge 4 commits into from
+269 −56

Conversation

@MaoZiming
Copy link
Member

@MaoZiming MaoZiming commented Nov 12, 2025

Description

Please include a summary of the changes and the related issue.

Fixes # (issue)

Type of Change

  • Bug fix
  • New feature
  • Documentation update

How Has This Been Tested?

Include any tests here.

  • Unit tests
  • Integration tests
  • Manual testing

Checklist

  • My code follows the style guidelines, e.g. format.sh.
  • I have run build_and_install.sh to verify compilation.
  • I have removed redundant variables and comments.
  • I have updated the documentation.
  • I have added tests.

@MaoZiming
Copy link
Member Author

MaoZiming commented Nov 13, 2025 •
edited
Loading

@YangZhou1997
EP=32 dispatch is around 350us, Combine is around 580us.
I think there is not much room for combine, the recv_rdma_buffer has token_slot from different sender experts on different ranks. The combine latency seems a bit better.

@MaoZiming
Copy link
Member Author

MaoZiming commented Nov 13, 2025 •
edited
Loading

EP=32
image

@MaoZiming
Copy link
Member Author

MaoZiming commented Nov 13, 2025

EP=16:
image

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@MaoZiming