Commit History

Auteur SHA1 Bericht Datum
  AlpinDale c5d8028668 fix: no need to redefine supports_vision and supports_lora in model class 7 maanden geleden
  AlpinDale 56e0b8223c chore: add base class for LoRA-supported models 7 maanden geleden
  AlpinDale 690110a051 feat: bitsandbytes quantization 7 maanden geleden
  AlpinDale ac79d115b3 add guards for prefix caching, fp8, chunked, etc 7 maanden geleden
  AlpinDale f4ea11b982 feat: initial support for activation quantization 7 maanden geleden
  AlpinDale c1ed789835 fix: typo in llama.py 7 maanden geleden
  AlpinDale 656459fd84 make fp8_e4m3 work on nvidia 7 maanden geleden
  AlpinDale 9e73559eba make use of batched rotary embedding kernels to support long context lora 7 maanden geleden
  AlpinDale 2ecfa98da9 re-fix mistral nemo 7 maanden geleden
  AlpinDale 50b7c13db0 refactor: attention selector (#552) 7 maanden geleden
  AlpinDale 54a4cef647 add bias and tie word embedding support for llama 7 maanden geleden
  AlpinDale 639e48e47d fix: mistral nemo 7 maanden geleden
  AlpinDale b178ae4b4a chore: generalize linear_method to be quant_method (#540) 7 maanden geleden
  AlpinDale e7b1368156 feat: Phi3 support 8 maanden geleden
  AlpinDale fca911ee0a vLLM Upstream Sync (#526) 8 maanden geleden
  AlpinDale 9d81716bfd [v0.5.3] Release Candidate (#388) 10 maanden geleden
  AlpinDale f8dfac6372 chore: attention refactor and upstream sync apr01 (#365) 11 maanden geleden
  sgsdxzy 6ebac34dc1 chore: cleaner pre-llamafied Yi implementation (#352) 11 maanden geleden
  AlpinDale 681e94611f fix: restore backwards compatibility with old Yi models (#351) 11 maanden geleden
  AlpinDale da223153c6 feat&fix: cohere support and missing GPU blocks (#333) 1 jaar geleden
  AlpinDale e42a78381a feat: switch from pylint to ruff (#322) 1 jaar geleden
  AlpinDale 9810daa699 feat: INT8 KV Cache (#298) 1 jaar geleden
  AlpinDale e31c6f0b45 feat: refactor modeling logic and support more models (#274) 1 jaar geleden
  AlpinDale 842912d022 feat: on-the-fly gguf conversion (#250) 1 jaar geleden
  AlpinDale c3a221eb02 feat: GGUF, QuIP#, and Marlin support (#228) 1 jaar geleden
  AlpinDale c0aac15421 feat: S-LoRA support (#222) 1 jaar geleden
  AlpinDale 8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221) 1 jaar geleden
  AlpinDale f013d714c0 chore: merge dev branch into main (#177) 1 jaar geleden
  AlpinDale 2755a48d51 merge dev branch into main (#153) 1 jaar geleden
  AlpinDale 887e03669a feat: add exllamav2 for GPTQ (#99) 1 jaar geleden