Commit History

Autor SHA1 Mensaxe Data
  AlpinDale 2a349ca3e1 fix: specify device when loading lora and embedding tensors hai 6 meses
  AlpinDale 98f9dbd734 feat: Triton Kernels for Punica (#613) hai 6 meses
  AlpinDale f91991f584 fix: f-string fixes hai 7 meses
  AlpinDale 99680b2d23 feat: soft prompts (#589) hai 7 meses
  AlpinDale 0a6db357d8 fix: use safetensor keys instead of adapter_config.json to find unexpected modules hai 7 meses
  AlpinDale 85ef2fe8b1 chore: clean up placeholder symbols hai 7 meses
  AlpinDale 56e0b8223c chore: add base class for LoRA-supported models hai 7 meses
  AlpinDale 25feb1d592 chore: add support for pinning lora adapters in the lru cache hai 7 meses
  AlpinDale 9e73559eba make use of batched rotary embedding kernels to support long context lora hai 8 meses
  AlpinDale eaa06fdd14 fix some f-strings hai 8 meses
  AlpinDale b55381df0e speedup lora loading times by resuing the cpu dummy lora hai 8 meses
  AlpinDale e87c32bed3 feat: full tensor parallel for LoRA layers (#545) hai 8 meses
  AlpinDale 8be299e78b fix: lora load check hai 10 meses
  AlpinDale 9d81716bfd [v0.5.3] Release Candidate (#388) hai 10 meses
  AlpinDale e3252edd07 fix: remove event and stream, add typing (#382) hai 11 meses
  AlpinDale e42a78381a feat: switch from pylint to ruff (#322) hai 1 ano
  AlpinDale 657aec0cbd refactor: OpenAI endpoint (#261) hai 1 ano
  AlpinDale 697c06c4f5 fix: LoRA support for mixtral (#276) hai 1 ano
  AlpinDale c0aac15421 feat: S-LoRA support (#222) hai 1 ano