Faster small batch qmv #1861
Merged
Faster small batch qmv #1861
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
|
Nice!! 🚀 |
|
Helps with ml-explore/mlx-examples#1281 |
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Outdated suggestions cannot be applied.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.
Speeds up small batch qvm and qmv by swapping batch and block dimensions in the kernel:
Speculative generation benchmark on M2 Ultra:
Pre: Generation: 390 tokens, 31.786 tokens-per-sec
Post: Generation: 390 tokens, 37.843 tokens-per-sec
No draft model: Generation: 390 tokens, 31.765 tokens-per-sec