cturan/llama.cpp @ 05697f670b1ea28b80c39854832ea53527f75c55

mirror of https://github.com/cturan/llama.cpp

Georgi Gerganov 05697f670b metal : simplify f16 and f32 dequant kernels (#0)		1 year ago
..
cmake	f3f65429c4 llama : reorganize source code + improve CMake (#8006)	1 year ago
include	9f40989351 ggml : move CPU backend to a separate file (#10144)	1 year ago
src	05697f670b metal : simplify f16 and f32 dequant kernels (#0)	1 year ago
.gitignore	17eb6aa8a9 vulkan : cmake integration (#8119)	1 year ago
CMakeLists.txt	60ce97c9d8 add amx kernel for gemm (#8998)	1 year ago