Commit History

Autor SHA1 Mensaxe Data
  Michael Yang 199941cd15 fix: gguf int type hai 1 ano
  Michael Yang c5e1bbabda instead of static number of parameters for each model family, get the real number from the tensors (#1022) hai 1 ano
  Michael Yang 125d0a013a ggufv3 hai 1 ano
  Michael Yang c02c0cd483 starcoder hai 1 ano
  Bruce MacDonald 86279f4ae3 unbound max num gpu layers (#591) hai 1 ano
  Bruce MacDonald 4cba75efc5 remove tmp directories created by previous servers (#559) hai 1 ano
  Bruce MacDonald 66003e1d05 subprocess improvements (#524) hai 1 ano
  Bruce MacDonald 2540c9181c support for packaging in multiple cuda runners (#509) hai 1 ano
  Michael Yang 0c5a454361 fix model type for 70b hai 1 ano
  Michael Yang 7dee25a07f fix falcon decode hai 1 ano
  Bruce MacDonald 09dd2aeff9 GGUF support (#441) hai 1 ano