Enable CUTLASS grouped GEMM for llama4x pretraining grad on GB200 and H100 #4856
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
Summary: X-link: facebookresearch/FBGEMM#1868 Optimize BF16 CUTLASS GMM to bring 1.1x - 1.3x speedup for llama4x pretraining fprop shapes. More results can be found in this [spreadsheet](https://docs.google.com/spreadsheets/d/172Nm0F9K6XJenNFoNFqC5Sp1Ll2KhLtfOJpIfkuHDzc/edit?usp=sharing) Differential Revision: D81704026
… H100 Summary: X-link: facebookresearch/FBGEMM#1869 Enable CUTLASS grouped GEMM for llama4x pretraining grad on GB200 and H100 Next steps: 1. Currently enabled dgrad. Will build a new kernel for wgrad as followup 2. Will further optimize perf on GB200 Reviewed By: jwfromm Differential Revision: D81997154
✅ Deploy Preview for pytorch-fbgemm-docs ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
|
This pull request was exported from Phabricator. Differential Revision: D81997154 |
|
This pull request has been merged in dc0ab6d. |
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Outdated suggestions cannot be applied.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:
X-link: https://github.com/facebookresearch/FBGEMM/pull/1869
Enable CUTLASS grouped GEMM for llama4x pretraining grad on GB200 and H100
Next steps:
Reviewed By: jwfromm
Differential Revision: D81997154