Histórico de Commits

Autor SHA1 Mensagem Data
  AlpinDale 2c653a2268 fix: make speculative decoding work with per-request seed há 5 meses atrás
  AlpinDale af43576da0 feat: add MLPSpeculator speculative decoding support (#572) há 5 meses atrás
  AlpinDale 4d1e613804 chore: minor simplifications há 5 meses atrás
  AlpinDale e0886ee929 feat: add `ProposerWorkerBase` abstract class há 6 meses atrás
  AlpinDale a94de94c44 refactor: combine the prefill and decode into a single API (#553) há 6 meses atrás
  AlpinDale ef733aee43 implement ExecuteModelData to reduce executor complexity há 6 meses atrás
  AlpinDale 79901b76de logprobs for target model (spec decoding) há 6 meses atrás
  AlpinDale 723c6acb84 re-add ngram speculative decoding há 6 meses atrás
  AlpinDale 9d81716bfd [v0.5.3] Release Candidate (#388) há 8 meses atrás
  AlpinDale f8dfac6372 chore: attention refactor and upstream sync apr01 (#365) há 10 meses atrás