jdelony/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-06-28 04:30:15 -05:00
Code Issues Packages Projects Releases Wiki Activity
ik_llama.cpp/github-data/pull_requests/251 - Try using fp32 for FlashMLA.md

423 B
Raw Permalink Blame History

🔀 #251 - Try using fp32 for FlashMLA

Author ikawrakow
State ❌ Closed
Created 2025-03-10
Updated 2025-03-12

💬 Conversation

👤 ikawrakow commented the 2025-03-12 at 07:51:20:

Closing this as the numerical issues were caused by fp16 experts matrix multiplications.