fix(CuTeDSL): correct FP4 tensor K dimension in grouped blockscaled GEMM#3102
Open
Hale423 wants to merge 1 commit intoNVIDIA:mainfrom
Open
fix(CuTeDSL): correct FP4 tensor K dimension in grouped blockscaled GEMM#3102Hale423 wants to merge 1 commit intoNVIDIA:mainfrom
Hale423 wants to merge 1 commit intoNVIDIA:mainfrom
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes #3057"
Float4E2M1FN packs 2 elements per byte, so the K storage dimension
must be halved (k // 2) when creating int8 device tensors for A and B.
This matches the existing correct handling in
dense_blockscaled_gemm_persistent.py (line 2493-2498).