Kawrakow bc34573356 CPU: faster FA (#797) ... * Avoid computing FA chunks where the mask is -infinity * Avoid computing FA chunks where the mask is -infinity also for f16/bf16 --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>		2025-09-26 09:00:25 +02:00
..
cmake	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
include	Offload only activated experts to the GPU (#698)	2025-09-04 12:22:30 +02:00
src	CPU: faster FA (#797)	2025-09-26 09:00:25 +02:00
.gitignore	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
CMakeLists.txt	Set default value of GGML_SCHED_MAX_COPIES to 1 (#751)	2025-09-02 07:04:39 +02:00