Fuse expert SilU heads (MoE) into batched GEMM via fuse_horizontal#5087
Open
TedThemistokleous wants to merge 1 commit into
Open
Fuse expert SilU heads (MoE) into batched GEMM via fuse_horizontal#5087TedThemistokleous wants to merge 1 commit into
TedThemistokleous wants to merge 1 commit into
Conversation
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
| if(pw->module_inputs().empty()) | ||
| return false; | ||
|
|
||
| bool found = false; |
Contributor
There was a problem hiding this comment.
[format.py] reported by reviewdog 🐶
Suggested change
| bool found = false; | |
| bool found = false; |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Motivation
Batch SilU heads that come from Mixture of experts (MoE)
Adds the match_expert_head fusion pass to fuse this pattern into a single batched GEMM
Running with this setup gave me boost across all the batches 1-11%
Technical Details
Adds a single fusion pass that should happen before dot_horizontal_fusion
Changelog Category
Add a
CHANGELOG.mdentry for any option other thanNot ApplicableFollow the LLVM AI Tool Use Policy for contributions using AI.