llama.cpp
ggml-cuda: fix divergent barrier in f16 flash attention
#27870
Merged
Go
Login via GitHub
Home
FAQ
Install
Login
via GitHub
Overview
Commits
2
Changes
View On
GitHub
Commits
ggml-cuda: fix divergent barrier in f16 flash attention
siavashnorouzi
committed
78 days ago
ggml-cuda: avoid duplicate metadata pointer setup
siavashnorouzi
committed
78 days ago
Loading