Faster Q4_K_R4 and Q5_K_R4 on AVX2/Zen4 #182
Merged
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
We now arrive at PP-512 = 328 t/s for LLaMA-3.1-8B on a Ryzen-5975WX CPU, up from 291 t/s when I last measured on 3c5f872. With FA and Q8_0 K-cache we get to 339.5 t/s.
We arrive at 302 t/s for LLaMA-3.1-8B on a Ryzen-5975WX CPU, up from 273 t/s.
After the changes I made to AVX2, it ends up being slightly faster compared to what I had for Zen4.
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Outdated suggestions cannot be applied.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.
TG is about the same. PP-512 comparison between main and this PR for LLaMA-3.1-8B on a Ryzen-5975WX (
AVX2) and a Ryzen-7950X (Zen4)The improvement on
Zen4is very minor. The benefit there is bloat reduction as I'm now reusing the same implementation asAVX2.