cturan/llama.cpp @ c39665f589091903396a442a6ee56613303e0350

镜像来自 https://github.com/cturan/llama.cpp

Johannes Gäßler c39665f589 CUDA: fix MMQ for non-contiguous src0, add tests (#10021)		1 年之前
..
cmake	f3f65429c4 llama : reorganize source code + improve CMake (#8006)	1 年之前
include	6b8447352d [CANN] Adapt to dynamically loadable backends mechanism (#9970)	1 年之前
src	c39665f589 CUDA: fix MMQ for non-contiguous src0, add tests (#10021)	1 年之前
.gitignore	17eb6aa8a9 vulkan : cmake integration (#8119)	1 年之前
CMakeLists.txt	60ce97c9d8 add amx kernel for gemm (#8998)	1 年之前