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: e562eece7c
Branches Tags
llama.cpp
/
ggml
Johannes Gäßler e562eece7c CUDA: fix typo in FlashAttention code (#13926) 7 months ago
..
cmake 21fcc21ad5 cmake: Factor out CPU architecture detection (#13883) 7 months ago
include a8ea03d8ad ggml : add ggml_repeat_4d (#13824) 7 months ago
src e562eece7c CUDA: fix typo in FlashAttention code (#13926) 7 months ago
.gitignore 17eb6aa8a9 vulkan : cmake integration (#8119) 1 year ago
CMakeLists.txt bef8176387 vulkan: use timestamp queries for GGML_VULKAN_PERF (#13817) 7 months ago