Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Change gqa to use repeat instead of concatenate #443

Merged
merged 1 commit into from
Feb 15, 2024
Merged

Change gqa to use repeat instead of concatenate #443

merged 1 commit into from
Feb 15, 2024

Conversation

angeloskath
Copy link
Member

Simplify repeat and provide ~1.5 tps for quantized mistral 7B.

Copy link
Member

@awni awni left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Simpler and faster, very nice!

I aso see the perils here of having a different implementation file for each model

@awni awni merged commit f71e965 into main Feb 15, 2024
@awni awni deleted the repeat-gqa branch February 15, 2024 01:40
@mzbac mzbac mentioned this pull request Mar 3, 2024
Blaizzy pushed a commit to Blaizzy/mlx-examples that referenced this pull request Mar 13, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants