Refactor Triton-kernel MoE runner integration #11795
Merged
ch-wan merged 28 commits intosgl-project:mainfrom Oct 24, 2025
Merged
Refactor Triton-kernel MoE runner integration #11795ch-wan merged 28 commits intosgl-project:mainfrom
ch-wan merged 28 commits intosgl-project:mainfrom
Conversation
ch-wan
reviewed
Oct 18, 2025
…sed/non-fused paths for both no_combine settings; register pre-permute from standard to Triton-kernel
ch-wan
requested changes
Oct 21, 2025
Collaborator
ch-wan
left a comment
There was a problem hiding this comment.
Thank you for your contribution. Overall, the code structure and logic look good to me. I left some comments. Also, could you check the errors in CI tests? Thanks.
…n kernel moe bias path
ch-wan
reviewed
Oct 23, 2025
ch-wan
approved these changes
Oct 24, 2025
Collaborator
|
This PR breaks #12059 |
4 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Motivation
Refactor Triton-kernel MoE runner integration into
triton_kernels.pyper #8715Modifications
Plan.md
Accuracy Tests
test/srt/test_triton_fused_moe.pypasses on Nvidia B200.Benchmarking and Profiling
Not relevant as no kernels were modified.
Checklist