Skip to content

Conversation

wenscarl
Copy link
Collaborator

@wenscarl wenscarl commented Oct 6, 2025

📌 Description

co-authored by @ChristinaZ(major contribution)
After this change, for deepseek mode, now logits is always fp32, bias can be bfloat16 and fp32 now.

🔍 Related Issues

🚀 Pull Request Checklist

Thank you for contributing to FlashInfer! Before we review your pull request, please make sure the following items are complete.

✅ Pre-commit Checks

  • I have installed pre-commit by running pip install pre-commit (or used your preferred method).
  • I have installed the hooks with pre-commit install.
  • I have run the hooks manually with pre-commit run --all-files and fixed any reported issues.

If you are unsure about how to set up pre-commit, see the pre-commit documentation.

🧪 Tests

  • Tests have been added or updated as needed.
  • All tests are passing (unittest, etc.).

Reviewer Notes

wenscarl and others added 2 commits October 7, 2025 11:23
…ode.

Signed-off-by: Christina Zhang <83400082+ChristinaZ@users.noreply.github.com>
@pavanimajety
Copy link
Contributor

@ChristinaZ Thanks for making changes across all MOE runners!

@wenscarl wenscarl marked this pull request as ready for review October 10, 2025 03:39
@wenscarl wenscarl requested a review from pavanimajety October 10, 2025 03:39
Copy link
Contributor

@pavanimajety pavanimajety left a comment

Choose a reason for hiding this comment

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

LGTM, thanks @wenscarl and @ChristinaZ for making the required changes!

@wenscarl wenscarl requested a review from pavanimajety October 14, 2025 03:46
@wenscarl
Copy link
Collaborator Author

@yzh119 could you take a look and merge it? Thanks!

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.

3 participants