Histórico de commits

Autor SHA1 Mensagem Data
  AlpinDale 5240c0da23 fix: avoid unnecessary ray import warnings 6 meses atrás
  AlpinDale 5be90c3859 Mamba infrastrucuture support (#586) 6 meses atrás
  AlpinDale ae04f57ec1 feat: Pipeline Parallel support (#581) 7 meses atrás
  AlpinDale 0886c361f4 feat: OpenVINO CPU backend (#576) 7 meses atrás
  AlpinDale c0c336aaa3 refactor: registry for processing model inputs; quick_gelu; clip model support 7 meses atrás
  AlpinDale 4ed1bb9958 chore: add fault tolerance for RayTokenizerGroupPool 7 meses atrás
  AlpinDale 3c7444c89b fix: asyncio.run hangs in python < 3.12 7 meses atrás
  AlpinDale 6a57861fca feat: initial XPU support via intel_extension_for_pytorch (#571) 7 meses atrás
  AlpinDale c482c09a3a fix: remove duplicated input processing in async engine 7 meses atrás
  AlpinDale fe21123a1c feat: TPU support (#570) 7 meses atrás
  AlpinDale d7ebffe2f0 chore: re-add the graceful engine shutdown 7 meses atrás
  AlpinDale 90ceab32ff refactor: consolidate prompt args to LLM engines 7 meses atrás
  AlpinDale de62ceb18c refactor: eliminate parallel worker per-step task scheduling overhead 7 meses atrás
  AlpinDale c6a501f682 add multiprocessing executor; make ray optional 7 meses atrás
  AlpinDale 50b7c13db0 refactor: attention selector (#552) 7 meses atrás
  AlpinDale be8154a8a0 feat: proper embeddings API with e5-mistral-7b support 7 meses atrás
  AlpinDale 3705050cd0 fix python 3.8 syntax 7 meses atrás
  AlpinDale ef733aee43 implement ExecuteModelData to reduce executor complexity 7 meses atrás
  AlpinDale 29c1b58255 minor logging fixes 7 meses atrás
  AlpinDale c5fc4a4996 failsafe for later 7 meses atrás
  AlpinDale aed64884c6 feat: prompt logprobs with chunked prefill (#539) 7 meses atrás
  AlpinDale 199e776722 chore: move ray utils to executor dir 8 meses atrás
  AlpinDale fca911ee0a vLLM Upstream Sync (#526) 8 meses atrás
  AlpinDale 9d81716bfd [v0.5.3] Release Candidate (#388) 10 meses atrás
  AlpinDale 0f6d56b07f feat: model executor refactor (#367) 11 meses atrás
  AlpinDale b361096463 fix: tokenizer when using ray (#366) 11 meses atrás
  AlpinDale f8dfac6372 chore: attention refactor and upstream sync apr01 (#365) 11 meses atrás
  AlpinDale c2d77b1822 chore: logging refactor (#302) 1 ano atrás
  AlpinDale 2d3d44b3e9 chore: add health check for ray workers (#290) 1 ano atrás
  AlpinDale ac82b67f75 feat: naive context shift and various QoL changes (#289) 1 ano atrás