Kawrakow 17d2db910f Use cuBLAS for large batches and quants with block size 16 (#559) ... Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>		2025-06-27 17:43:51 +02:00
..
cmake	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
include	Fix non rpc build error (#506)	2025-06-08 17:27:00 +03:00
src	Use cuBLAS for large batches and quants with block size 16 (#559)	2025-06-27 17:43:51 +02:00
.gitignore	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
CMakeLists.txt	Better strategy for GPU offload (#520)	2025-06-12 19:25:11 +03:00