Commit History

Author SHA1 Message Date
  PoTaTo 23a4beb069 Fix API server bugs. (#1019) 10 months ago
  Picus303 4fc8dbdfe0 Move inference code to library dir (#801) 1 year ago
  Lengyue dad516d86d update checkpoint path 1 year ago
  Lengyue 1d942c8b97 Update 1.2 sft checkpoints, inference.ipynb and READMEs 1 year ago
  spicysama f2c7eedf6f Add API usage (#345) 1 year ago
  spicysama ea53678446 Quantization Support (#316) 1 year ago
  Leng Yue 5e7914472f This PR brings V1.2 inference into main (#300) 1 year ago
  Lengyue 691b3bb937 Fix quanitzation & remove memory usage 1 year ago
  Lengyue ee7a1beb41 Better quantizer 2 years ago
  Lengyue afc854ad85 Clean unused code & reorganize 2 years ago