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: 381da2d9f0
Ramas Etiquetas

Commit History

Autor SHA1 Mensaxe Data
  Georgi Gerganov 8030da7afe ggml : reuse quantum structs across backends (#5943) hai 1 ano
  Kawrakow 44ca159faf 1.5 bit: we can do even better (#5999) hai 1 ano
  Kawrakow be858f6205 Better 1.5 bit quantization (#5971) hai 1 ano
  Georgi Gerganov bf47a5eefc ggml : remove __constant__ specifier for CUDA tables (#5940) hai 1 ano
  Georgi Gerganov 8a3012a4ad ggml : add ggml-common.h to deduplicate shared code (#5940) hai 1 ano