Conversation
tianleiwu
reviewed
Apr 14, 2025
tianleiwu
reviewed
Apr 14, 2025
tianleiwu
reviewed
Apr 14, 2025
tianleiwu
reviewed
Apr 14, 2025
tianleiwu
reviewed
Apr 14, 2025
tianleiwu
reviewed
Apr 14, 2025
tianleiwu
reviewed
Apr 14, 2025
tianleiwu
reviewed
Apr 14, 2025
tianleiwu
reviewed
Apr 14, 2025
tianleiwu
reviewed
Apr 14, 2025
tianleiwu
approved these changes
Apr 16, 2025
Contributor
tianleiwu
left a comment
tianleiwu
left a comment
There was a problem hiding this comment.
It would be nice to support 8 bits later.
ashrit-ms
pushed a commit
that referenced
this pull request
Apr 24, 2025
### Description <!-- Describe your changes. --> Most models can benefit from fusing the pre-GQA nodes into a single MatMul or MatMulNBits. This change will detect the patterns possible to fuse and execute the fusion on CUDA EPs. ### Motivation and Context This will enable publishing of a single GPU model going forward. --------- Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
Most models can benefit from fusing the pre-GQA nodes into a single MatMul or MatMulNBits. This change will detect the patterns possible to fuse and execute the fusion on CUDA EPs.
Motivation and Context
This will enable publishing of a single GPU model going forward.