nicolas
/
ik_llama_opt
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
ik_llama_opt/github-data/pull_requests/421 - Fix standard attentio...

421 B
Raw Permalink Blame History

🐛 #421 - Fix standard attention on the CPU

Author ikawrakow
State ❌ Closed
Created 2025-05-15
Updated 2025-05-15

Description

I have focusing on FA, MLA, FlashMLA lately, and at some point I have broken the standard self attention CPU implementation. This PR fixes it and closes #420.