BF16I4 Preshuffled Batched GEMM #4399
Closed
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: Some integrations of fbgemm kernels and oss systems like VLLM would be made simpler by the ability to slice preshuffled tensors. Prior to this diff, there were two blockers to doing that: - Scales were required to be contiguous. This is easily addressed by more carefully setting the stride argument. - Shuffled tensors have a non-trivial layout. We add a python helper function for slicing int4 shuffled tensors. Notably, it involves some data copying that I believe is unavoidable. Hopefully it only needs to be done during model setup. Differential Revision: D77239566
Summary: The preshuffled BF16I4 batched gemm is much faster than BF16I4 batched gemm, especially in memory-bound shapes, which will be used in fbgemm + other oss system integration Add BF16I4 preshuffled batched gemm to unblock the integration as requested Differential Revision: D77311295
✅ 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: D77311295 |
|
This pull request has been merged in b56c580. |
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Outdated suggestions cannot be applied.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:
The preshuffled BF16I4 batched gemm is much faster than BF16I4 batched gemm, especially in memory-bound shapes, which will be used in fbgemm + other oss system integration
Add BF16I4 preshuffled batched gemm to unblock the integration as requested
Differential Revision: D77311295