fix deepep tokens_per_expert - #2053
Open
PengchengShi00 wants to merge 1 commit into
Open
Conversation
jayhenry
self-requested a review
August 28, 2026 12:12
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Fix DeepEP expert assignment counting by deriving
num_out_tokensandtokens_per_expertdirectly from the received topk_ids, instead of relying onnum_recv_tokens_per_expert_list.This ensures that permute and grouped GEMM use the same expert assignment layout, preventing tokens from being processed by incorrectly aligned local experts. Additional assertions validate local expert IDs and assignment counts.
After this fix, the train-inference discrepancy with DeepEP decreased from 0.004449 to 0.000364.