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: 55a1c5a5fd
Branches Tags
llama.cpp
/
ggml
Aman Gupta 55a1c5a5fd CUDA: add softmax broadcast (#14475) 6 months ago
..
cmake 3555b3004b ggml-cpu : rework weak alias on apple targets (#14146) 7 months ago
include ec68e84c32 ggml : support bcast ggml_soft_max_ext, ggml_flash_attn_ext (#14435) 6 months ago
src 55a1c5a5fd CUDA: add softmax broadcast (#14475) 6 months ago
.gitignore 17eb6aa8a9 vulkan : cmake integration (#8119) 1 year ago
CMakeLists.txt 60ef23d6c1 ggml-cpu: enable IBM NNPA Vector Intrinsics (#14317) 7 months ago