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: c262beddf2
Ramas Etiquetas
llama.cpp
/
ggml
Gaurav Garg c262beddf2 CUDA: Prefer vector flash decoding kernel for Gemma models (#12738) hai 9 meses
..
cmake 771d84371c scripts : update sync + fix cmake merge hai 9 meses
include b4ae50810e metal : improve FA + improve MoE (#12612) hai 9 meses
src c262beddf2 CUDA: Prefer vector flash decoding kernel for Gemma models (#12738) hai 9 meses
.gitignore 17eb6aa8a9 vulkan : cmake integration (#8119) hai 1 ano
CMakeLists.txt e408d4351a ggml : add logging for native build options/vars (whisper/2935) hai 9 meses