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: c9a24fb932
Branches Tags
llama.cpp
/
ggml
Jeff Bolz c9a24fb932 vulkan: Support FA with any multiple of 8 head sizes (#15537) 5 months ago
..
cmake 9a96389544 ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (#15094) 5 months ago
include 92f7f0a53c ggml: add `conv3d` op (#15182) 5 months ago
src c9a24fb932 vulkan: Support FA with any multiple of 8 head sizes (#15537) 5 months ago
.gitignore 17eb6aa8a9 vulkan : cmake integration (#8119) 1 year ago
CMakeLists.txt 7a6e91ad26 CUDA: replace GGML_CUDA_F16 with CUDA arch checks (#15433) 5 months ago