Commit History

Autor SHA1 Mensaxe Data
  Michael Yang b599946b74 add format bytes hai 1 ano
  Bruce MacDonald d06bc0cb6e enable q8, q5, 5_1, and f32 for linux gpu (#699) 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
  Michael Yang 7dee25a07f fix falcon decode hai 1 ano
  Bruce MacDonald 09dd2aeff9 GGUF support (#441) hai 1 ano
  Bruce MacDonald 42998d797d subprocess llama.cpp server (#401) hai 1 ano
  Michael Yang b25dd1795d allow F16 to use metal hai 1 ano
  Michael Yang 304f2b6c96 add 34b to mem check hai 1 ano
  Michael Yang a894cc792d model and file type as strings hai 1 ano
  Michael Yang e26085b921 close open files hai 1 ano
  Michael Yang 6de5d032e1 implement loading ggml lora adapters through the modelfile hai 1 ano
  Michael Yang d791df75dd check memory requirements before loading hai 1 ano
  Michael Yang 020a3b3530 disable gpu for q5_0, q5_1, q8_0 quants hai 1 ano
  Michael Yang fccf8d179f partial decode ggml bin for more info hai 1 ano