Modernize FP8 Blockwise GEMM#5002
Closed
jwfromm wants to merge 1 commit into
Closed
Conversation
Summary: FBGEMM (and MSLK) previously relied on a customized implementation of blockwise scaling that has bitrotted over the past few releases of CUTLASS. Now that CUTLASS has fully supported blockwise scaling natively, it is time to switch over to it. This diff updates our blockwise FP8 gemm to use the standard cutlass implementation. This improves performance a bit and resolves some correctness issues. Differential Revision: D84632911
✅ Deploy Preview for pytorch-fbgemm-docs ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
Contributor
jerryzh168
approved these changes
Oct 14, 2025
Contributor
|
This pull request has been merged in 2674b39. |
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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary: FBGEMM (and MSLK) previously relied on a customized implementation of blockwise scaling that has bitrotted over the past few releases of CUTLASS. Now that CUTLASS has fully supported blockwise scaling natively, it is time to switch over to it. This diff updates our blockwise FP8 gemm to use the standard cutlass implementation. This improves performance a bit and resolves some correctness issues.
Differential Revision: D84632911