Accueil Explorer Aide
Connexion
cturan
/
llama.cpp
miroir de https://github.com/cturan/llama.cpp
1
0
Fork 0
Fichiers Tickets 0 Wiki
Aborescence: 518a01480e
Branches Tags
llama.cpp
/
ggml
zhouwg 518a01480e sycl: remove redundant memcopy in function ggml_backend_sycl_buffer_set_tensor (#12734) il y a 10 mois
..
cmake 771d84371c scripts : update sync + fix cmake merge il y a 10 mois
include b4ae50810e metal : improve FA + improve MoE (#12612) il y a 10 mois
src 518a01480e sycl: remove redundant memcopy in function ggml_backend_sycl_buffer_set_tensor (#12734) il y a 10 mois
.gitignore 17eb6aa8a9 vulkan : cmake integration (#8119) il y a 1 an
CMakeLists.txt e408d4351a ggml : add logging for native build options/vars (whisper/2935) il y a 10 mois