fix: move mPtrRoutingReplayOut to end of routing structs#4
Merged
TomerBN-Nvidia merged 1 commit intoupstream-routing-replayfrom Apr 14, 2026
Merged
Conversation
Inserting the field in the middle of DataBase and KernelParamsBase shifted memory offsets for all subsequent fields, causing GEMM crashes in FP8/FP4 autotuner tests (11/15 failures). Moving to end preserves the original layout for all existing fields. Also adds missing routing_replay_out arg to MXINT4 and FP4 paths in MoERunner._run(). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Move field from middle to end of DataBase and KernelParamsBase structs to preserve existing field offsets. Fixes FP8/FP4 autotuner GEMM crashes (11/15 failures). Also adds missing routing_replay_out arg to MXINT4/FP4 autotuner paths.