Home Explore Help
Sign In
cturan
/
llama.cpp
mirror of https://github.com/cturan/llama.cpp
1
0
Fork 0
Files Issues 0 Wiki
Tree: 4807e8f96a
Branches Tags
llama.cpp
/
ggml
Aman Gupta c0bfc57af4 CUDA: mul_mat_id for mmf for bs <= 64 for f16 and bs <= 32 for f32 (#16277) 3 months ago
..
cmake 9a96389544 ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (#15094) 5 months ago
include e789095502 llama: print memory breakdown on exit (#15860) 4 months ago
src c0bfc57af4 CUDA: mul_mat_id for mmf for bs <= 64 for f16 and bs <= 32 for f32 (#16277) 3 months ago
.gitignore 17eb6aa8a9 vulkan : cmake integration (#8119) 1 year ago
CMakeLists.txt b995a10760 common : use cpp-httplib as a cURL alternative for downloads (#16185) 4 months ago