Historique des commits

Auteur SHA1 Message Date
  AlpinDale ae04f57ec1 feat: Pipeline Parallel support (#581) il y a 6 mois
  AlpinDale fad45609b8 chore: remove logical token blocks (turns out they are not needed) il y a 6 mois
  AlpinDale 237fa59aea feat: support CPU/GPU swapping in BlockManagerV2 il y a 6 mois
  AlpinDale 9099040472 feat: cross-attention kv caching support il y a 6 mois
  AlpinDale 8b56dc4347 dict -> torch.Tensor for blocks_to_swap il y a 6 mois
  AlpinDale 148aca8ff1 cow => dict[int, list] -> list il y a 6 mois
  AlpinDale 25c2b6feca ignore infeasible swap requests il y a 6 mois
  AlpinDale 6f6bf568e5 enable prefix caching with v2 block manager for spec decoding il y a 6 mois
  AlpinDale fca911ee0a vLLM Upstream Sync (#526) il y a 7 mois
  AlpinDale 9d81716bfd [v0.5.3] Release Candidate (#388) il y a 9 mois