Inicio Explorar Axuda
Iniciar sesión
cturan
/
llama.cpp
réplica de https://github.com/cturan/llama.cpp
1
0
Fork 0
Ficheiros Incidencias 0 Wiki
Árbore: 92b8810ec7
Ramas Etiquetas
llama.cpp
/
ggml
Johannes Gäßler 92b8810ec7 CUDA: skip masked KV slices for all FA kernels (#14924) hai 5 meses
..
cmake 613c5095c3 cmake : Indent ggml-config.cmake (ggml/1310) hai 5 meses
include 21c021745d ggml: Add initial WebGPU backend (#14521) hai 6 meses
src 92b8810ec7 CUDA: skip masked KV slices for all FA kernels (#14924) hai 5 meses
.gitignore 17eb6aa8a9 vulkan : cmake integration (#8119) hai 1 ano
CMakeLists.txt b77d11179d HIP: add GGML_HIP_MMQ_MFMA option to allow disableing the MFMA path. (#14930) hai 5 meses