[vLLM][MoE] Avoid top-k boundary ties causing test failures#7580
Draft
sarah12121212 wants to merge 5 commits into
Draft
[vLLM][MoE] Avoid top-k boundary ties causing test failures#7580sarah12121212 wants to merge 5 commits into
sarah12121212 wants to merge 5 commits into
Conversation
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
test_fused_moegenerates random BF16 routing scores for top-k selection. Different routing implementations may resolve scores tied at the selection boundary using different expert IDs, causing numerical failures unrelated to the correctness of the MoE kernels.This PR:
Validation
Full vLLM MoE suite on B580 (Tested locally):
Full vLLM MoE suite on max 1100 (Tested locally):
Blocked by #7462 (it needs to be merged first)