llama.cpp
7e960f40
- opencl: fold GQA head for f16 FA for better efficiency (#32631)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
4 hours ago
opencl: fold GQA head for f16 FA for better efficiency (#32631) Assisted-by: Codex Co-authored-by: Li He <lih@qti.qualcomm.com> Co-authored-by: Hongqiang Wang <wangh@qti.qualcomm.com>
References
#32631 - opencl: fold gqa heads for f16 decomposed FA
Author
shaofeiqi
Parents
8bf88ba9
Loading