cturan/llama.cpp @ fbb7fcffbcfc50009c275e75982b1603a6cb6b80

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

Eve e536426ded llamafile : disable sgemm for batch-size 1 (#9330)		1 年之前
..
cmake	f3f65429c4 llama : reorganize source code + improve CMake (#8006)	1 年之前
include	9bc6db28d0 ggml-quants : ternary packing for TriLMs and BitNet b1.58 (#8151)	1 年之前
src	e536426ded llamafile : disable sgemm for batch-size 1 (#9330)	1 年之前
.gitignore	17eb6aa8a9 vulkan : cmake integration (#8119)	1 年之前
CMakeLists.txt	8ebe8ddebd Improve Vulkan shader build system (#9239)	1 年之前