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: 72c6bc3f3d
Ramas Etiquetas
llama.cpp
/
ggml
Johannes Gäßler defe2158dd CUDA: mul_mat_v support for batch sizes > 1 (#14262) hai 7 meses
..
cmake 3555b3004b ggml-cpu : rework weak alias on apple targets (#14146) hai 7 meses
include b7147673f2 Add `ggml_roll` (ggml/1274) hai 7 meses
src defe2158dd CUDA: mul_mat_v support for batch sizes > 1 (#14262) hai 7 meses
.gitignore 17eb6aa8a9 vulkan : cmake integration (#8119) hai 1 ano
CMakeLists.txt dd8e59f443 ggml : disable warnings for tests when using MSVC (ggml/1273) hai 7 meses