Histórico de commits

Autor SHA1 Mensagem Data
  AlpinDale d8a51d05a7 fix: seeded gens with pipeline parallel 5 meses atrás
  AlpinDale 2c653a2268 fix: make speculative decoding work with per-request seed 5 meses atrás
  AlpinDale af43576da0 feat: add MLPSpeculator speculative decoding support (#572) 5 meses atrás
  AlpinDale 4d1e613804 chore: minor simplifications 5 meses atrás
  AlpinDale e0886ee929 feat: add `ProposerWorkerBase` abstract class 6 meses atrás
  AlpinDale a94de94c44 refactor: combine the prefill and decode into a single API (#553) 6 meses atrás
  AlpinDale ef733aee43 implement ExecuteModelData to reduce executor complexity 6 meses atrás
  AlpinDale 79901b76de logprobs for target model (spec decoding) 6 meses atrás
  AlpinDale 723c6acb84 re-add ngram speculative decoding 6 meses atrás
  AlpinDale 9d81716bfd [v0.5.3] Release Candidate (#388) 8 meses atrás
  AlpinDale f8dfac6372 chore: attention refactor and upstream sync apr01 (#365) 10 meses atrás