Commit History

Autor SHA1 Mensaxe Data
  AlpinDale 60ca1e1e5e feat: add ngram prompt lookup decoding for speculative decoding (#438) hai 9 meses
  AlpinDale d8c4193704 feat: Speculative Decoding using a draft model (#432) hai 9 meses
  AlpinDale 8d26cf3876 simplify model_executor logic hai 9 meses
  AlpinDale 4d33ce60da feat: Triton flash attention backend for ROCm (#407) hai 10 meses
  AlpinDale 9aaeb5d349 add speculative config and arg for later hai 10 meses
  AlpinDale 753f6dc51b add v2 block manager hai 10 meses
  AlpinDale 7b9c08afae vision model support hai 10 meses
  AlpinDale d1786645a3 fix formatting hai 10 meses
  AlpinDale 2319b411ce refactor: neuron support hai 10 meses
  AlpinDale 0f6d56b07f feat: model executor refactor (#367) hai 10 meses
  AlpinDale f8dfac6372 chore: attention refactor and upstream sync apr01 (#365) hai 10 meses