Histórico de Commits

Autor SHA1 Mensagem Data
  AlpinDale cac8163f77 fix: request abort crashing pipeline parallel há 5 meses atrás
  AlpinDale 45a004874c chore: allow specifying custom Executor há 5 meses atrás
  AlpinDale a26f784240 chore: use the LoRA tokenizer in OpenAI API (#599) há 5 meses atrás
  AlpinDale c0c2b1ac20 fix: get_and_reset only when scheduler outputs are not empty há 5 meses atrás
  AlpinDale b9268be8e8 fix: engine timeout due to request abort há 5 meses atrás
  AlpinDale 99680b2d23 feat: soft prompts (#589) há 5 meses atrás
  AlpinDale 5240c0da23 fix: avoid unnecessary ray import warnings há 5 meses atrás
  AlpinDale 5be90c3859 Mamba infrastrucuture support (#586) há 5 meses atrás
  AlpinDale ae04f57ec1 feat: Pipeline Parallel support (#581) há 5 meses atrás
  AlpinDale 0886c361f4 feat: OpenVINO CPU backend (#576) há 5 meses atrás
  AlpinDale c0c336aaa3 refactor: registry for processing model inputs; quick_gelu; clip model support há 5 meses atrás
  AlpinDale 4ed1bb9958 chore: add fault tolerance for RayTokenizerGroupPool há 5 meses atrás
  AlpinDale 3c7444c89b fix: asyncio.run hangs in python < 3.12 há 5 meses atrás
  AlpinDale 6a57861fca feat: initial XPU support via intel_extension_for_pytorch (#571) há 6 meses atrás
  AlpinDale c482c09a3a fix: remove duplicated input processing in async engine há 6 meses atrás
  AlpinDale fe21123a1c feat: TPU support (#570) há 6 meses atrás
  AlpinDale d7ebffe2f0 chore: re-add the graceful engine shutdown há 6 meses atrás
  AlpinDale 90ceab32ff refactor: consolidate prompt args to LLM engines há 6 meses atrás
  AlpinDale de62ceb18c refactor: eliminate parallel worker per-step task scheduling overhead há 6 meses atrás
  AlpinDale c6a501f682 add multiprocessing executor; make ray optional há 6 meses atrás
  AlpinDale 50b7c13db0 refactor: attention selector (#552) há 6 meses atrás
  AlpinDale be8154a8a0 feat: proper embeddings API with e5-mistral-7b support há 6 meses atrás
  AlpinDale 3705050cd0 fix python 3.8 syntax há 6 meses atrás
  AlpinDale ef733aee43 implement ExecuteModelData to reduce executor complexity há 6 meses atrás
  AlpinDale 29c1b58255 minor logging fixes há 6 meses atrás
  AlpinDale c5fc4a4996 failsafe for later há 6 meses atrás
  AlpinDale aed64884c6 feat: prompt logprobs with chunked prefill (#539) há 6 meses atrás
  AlpinDale 199e776722 chore: move ray utils to executor dir há 7 meses atrás
  AlpinDale fca911ee0a vLLM Upstream Sync (#526) há 7 meses atrás
  AlpinDale 9d81716bfd [v0.5.3] Release Candidate (#388) há 8 meses atrás