Commit History

Autor SHA1 Mensaxe Data
  sgsdxzy 214151b04c fix: max_num_batched_tokens for chunked_prefill (#412) hai 9 meses
  sgsdxzy 6a0a6360f1 fix: Allow setting config-path when converting ggufs. (#410) hai 9 meses
  sgsdxzy fcfb72af24 Support arbitrary model in GGUF. (#381) hai 10 meses
  AlpinDale e42a78381a feat: switch from pylint to ruff (#322) hai 11 meses
  sgsdxzy fe7844f2ef feat: sharding and safetensors support for gguf conversion (#256) hai 1 ano
  AlpinDale c3a221eb02 feat: GGUF, QuIP#, and Marlin support (#228) hai 1 ano