cturan/llama.cpp @ 97669e40735d08db65ef094a8faae8e8411a97db

kopia lustrzana https://github.com/cturan/llama.cpp

rmatif 97669e4073 opencl: add attn sinks support for FA kernels (#15706)		5 miesięcy temu
..
cmake	9a96389544 ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (#15094)	6 miesięcy temu
include	9777032dcc llama : separate compute buffer reserve from fattn check (#15696)	5 miesięcy temu
src	97669e4073 opencl: add attn sinks support for FA kernels (#15706)	5 miesięcy temu
.gitignore	17eb6aa8a9 vulkan : cmake integration (#8119)	1 rok temu
CMakeLists.txt	4d74393bcc ggml: update kleidiai to v1.13.0 (#15663)	5 miesięcy temu