cturan/llama.cpp @ 87e397d00bdcedd5cbf6dfda06a7b0f302462728

slaren 87e397d00b ggml : fix quant dot product with odd number of blocks (#8549)		1 год назад
..
cmake	f3f65429c4 llama : reorganize source code + improve CMake (#8006)	1 год назад
include	a15ef8f8a0 CUDA: fix partial offloading for ne0 % 256 != 0 (#8572)	1 год назад
src	87e397d00b ggml : fix quant dot product with odd number of blocks (#8549)	1 год назад
.gitignore	17eb6aa8a9 vulkan : cmake integration (#8119)	1 год назад
CMakeLists.txt	705b7ecf60 cmake : install all ggml public headers (#8480)	1 год назад