Skip to content

Conversation

weireweire
Copy link
Contributor

@weireweire weireweire commented Aug 21, 2025

Purpose

New flahsinfer have changed the enum name.

Besides, to update flashinfer, flashinfer-ai/flashinfer#1475 require we make the scale of moe 2d for autotune. But it's not handle in this PR.

Test Plan

Test Result

(Optional) Documentation Update


Essential Elements of an Effective PR Description Checklist
  • The purpose of the PR, such as "Fix some issue (link existing issues this PR will resolve)".
  • The test plan, such as providing test command.
  • The test results, such as pasting the results comparison before and after, or e2e results
  • (Optional) The necessary documentation update, such as updating supported_models.md and examples for a new model.

Copy link

👋 Hi! Thank you for contributing to the vLLM project.

💬 Join our developer Slack at https://slack.vllm.ai to discuss your PR in #pr-reviews, coordinate on features in #feat- channels, or join special interest groups in #sig- channels.

Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run fastcheck CI which starts running only a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of those by going to your fastcheck build on Buildkite UI (linked in the PR checks section) and unblock them. If you do not have permission to unblock, ping simon-mo or khluu to add you in our Buildkite org.

Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging.

To run CI, PR reviewers can either: Add ready label to the PR or enable auto-merge.

🚀

Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

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

Code Review

This pull request updates an enum name in vllm/compilation/collective_fusion.py to reflect a change in the flashinfer library. Specifically, flashinfer_comm.FP4QuantizationSFLayout.SWIZZLED is renamed to flashinfer_comm.QuantizationSFLayout.SWIZZLED. This change is correct and necessary for compatibility with the updated dependency. The pull request is a draft, and the author has noted that additional changes related to the flashinfer update will be handled separately.

@@ -465,7 +465,7 @@ def call_trtllm_fused_allreduce_norm(
quant_out=quant_out,
scale_out=scale_out,
# in vllm we only support swizzled layout
layout_code=flashinfer_comm.FP4QuantizationSFLayout.SWIZZLED,
layout_code=flashinfer_comm.QuantizationSFLayout.SWIZZLED,
Copy link
Contributor

Choose a reason for hiding this comment

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

SWIZZLED needs to be changed to SWIZZLED_128x4

(caused by flashinfer-ai/flashinfer@669ff33 )

@weireweire
Copy link
Contributor Author

merged in #23537

@weireweire weireweire closed this Aug 26, 2025
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