cturan/llama.cpp @ aede2074f608d7bf6614cdd047bce687a2b3d908

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

ag2s20150909 9660ffef58 ggml : fix kleidiai build (#12159)		10 months ago
..
cmake	b95c8af37c cmake: Fix ggml backend dependencies and installation (#11818)	10 months ago
include	70680c48e5 ggml : upgrade init_tensor API to return a ggml_status (#11854)	10 months ago
src	9660ffef58 ggml : fix kleidiai build (#12159)	10 months ago
.gitignore	17eb6aa8a9 vulkan : cmake integration (#8119)	1 year ago
CMakeLists.txt	80c41ddd8f CUDA: compress mode option and default to size (#12029)	10 months ago