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: 79bc429262
Ramas Etiquetas
llama.cpp
/
ggml
Johannes Gäßler 79bc429262 CUDA: faster tile FA (Pascal/AMD), headsize 256 (#15769) hai 4 meses
..
cmake 9a96389544 ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (#15094) hai 5 meses
include 186415d595 ggml-cpu: drop support for nnpa intrinsics (#15821) hai 4 meses
src 79bc429262 CUDA: faster tile FA (Pascal/AMD), headsize 256 (#15769) hai 4 meses
.gitignore 17eb6aa8a9 vulkan : cmake integration (#8119) hai 1 ano
CMakeLists.txt 186415d595 ggml-cpu: drop support for nnpa intrinsics (#15821) hai 4 meses