Repository navigation
metal-flash-attention support #22
Description
Can this project help for you? https://github.com/philipturner/metal-flash-attention
So far, metal-flash-attention can indeed provide the fastest generation speed for stable diffusion on MacOS.
Reacted by lin72h
Activity
leejet commentedon Aug 21, 2023
Thank you for the feedback. I'm currently focusing on making it run faster, and I'll make time to take a look at this project and see if I can offer any assistance.
sroussey commentedon Aug 21, 2023
I came here to suggest the same thing.
Green-Sky commentedon Aug 21, 2023
linking this here for reference ggml-org/ggml#293
GaidamakUA commentedon Oct 3, 2023
What needs to be done to make this happen? I'm not very good with cpp, but I want to help.
Green-Sky commentedon Sep 12, 2024
#386
I am in the dark on metal flash attention support, or metal support in general.
So would be nice if someone with the hardware could test the pr. :)
github-actions commentedon Jul 9, 2026
This issue has had no activity for one year. The latest version of the code may already have fixed the problem.
If the issue still exists in the latest version, you can reopen this issue at any time with updated reproduction details.