Página inicial Explorar Ajuda
Entrar
cturan
/
llama.cpp
mirror de https://github.com/cturan/llama.cpp
1
0
Fork 0
Arquivos Issues 0 Wiki
Tree: ce734a8a2f
Branches Tags

Histórico de commits

Autor SHA1 Mensagem Data
  Alfred ce734a8a2f ggml-hexagon: Implement true Q8_0 quantization on Hexagon NPU for more accurate mixed-precision matmul operations (#17977) 4 semanas atrás
  Max Krasnyansky 63d2fc46e1 Add experimental ggml-hexagon backend for the Hexagon NPU (#16547) 2 meses atrás