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: 24dc769f1b
Branches Tags
llama.cpp
/
ggml
Jeff Bolz 24dc769f1b vulkan: Fuse mul_mat_id+add_id+mul and mul_mat+add+add. (#17287) 2 months ago
..
cmake 9a96389544 ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (#15094) 5 months ago
include 389ac78b26 ggml : add ops SOFTPLUS, EXPM1, TRI, SOLVE_TRI, CUMSUM (#17063) 2 months ago
src 24dc769f1b vulkan: Fuse mul_mat_id+add_id+mul and mul_mat+add+add. (#17287) 2 months ago
.gitignore 17eb6aa8a9 vulkan : cmake integration (#8119) 1 year ago
CMakeLists.txt 08416ebe7f ggml: disable vxe for cross-compilation by default (#16966) 2 months ago