Better CPU prompt processing performance for SWA models#696
Merged
Conversation
Owner
Author
|
Just for fun, here a CPU-only comparison with mainline 
|
ikawrakow
pushed a commit
that referenced
this pull request
Aug 17, 2025
This reverts commit 93a4f60.
ikawrakow
added a commit
that referenced
this pull request
Aug 17, 2025
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR is a follow up of #692 and uses the same technique to improve prompt processing performance for models utilizing SWA. As #682 it is implemented only on the CPU and requires FA.
Here some performance comparisons on a Ryzen-7950X CPU
Gemma3-270M-it, Q8_0
GPT-OSS-20B, MXFP4