Files
ik_llama.cpp/github-data/pull_requests/251 - Try using fp32 for FlashMLA.md
2025-07-23 13:31:53 +02:00

423 B

🔀 #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.