Commits

Branch selector

main

User selector

All users

All time

Commit history

Commits on Jun 20, 2023

• Use slow tokenizer for open llama models (#168)

  WoosukKwon

  authored
  67d96c2View commit details

  Copy full SHA for 67d96c2

  Browse repository at this point

• Remove e.g. in README (#167)

  zhuohan123

  authored
  033f5c7View commit details

  Copy full SHA for 033f5c7

  Browse repository at this point

• [Minor] Fix URLs (#166)

  WoosukKwon

  authored
  794e578View commit details

  Copy full SHA for 794e578

  Browse repository at this point

• [Minor] Fix icons in doc (#165)

  WoosukKwon

  authored
  caddfc1View commit details

  Copy full SHA for caddfc1

  Browse repository at this point

• Change image urls (#164)

  zhuohan123

  authored
  fc72e39View commit details

  Copy full SHA for fc72e39

  Browse repository at this point

• Fix repo & documentation URLs (#163)

  WoosukKwon

  authored
  b7e62d3View commit details

  Copy full SHA for b7e62d3

  Browse repository at this point

• [Docs] Minor fix (#162)

  WoosukKwon

  authored
  364536aView commit details

  Copy full SHA for 364536a

  Browse repository at this point

• Add and list supported models in README (#161)

  zhuohan123

  authored
  0b32a98View commit details

  Copy full SHA for 0b32a98

  Browse repository at this point

• [PyPI] Fix package info in setup.py (#158)

  WoosukKwon

  authored
  570fb2eView commit details

  Copy full SHA for 570fb2e

  Browse repository at this point

Commits on Jun 19, 2023

• Add logo and polish readme (#156)

  zhuohan123

  authored
  a255885View commit details

  Copy full SHA for a255885

  Browse repository at this point

• Add performance figures for dark mode (#160)

  WoosukKwon

  authored
  5822edeView commit details

  Copy full SHA for 5822ede

  Browse repository at this point

• Remove benchmark_async_llm_server.py (#155)

  zhuohan123

  authored
  0370afaView commit details

  Copy full SHA for 0370afa

  Browse repository at this point

• [Minor] Fix CompletionOutput.__repr__ (#157)

  WoosukKwon

  authored
  7e2a913View commit details

  Copy full SHA for 7e2a913

  Browse repository at this point

Commits on Jun 18, 2023

• Add comments on swap space (#154)

  WoosukKwon

  authored
  3f92038View commit details

  Copy full SHA for 3f92038

  Browse repository at this point

• Write README and front page of doc (#147)

  WoosukKwon

  authored
  dcda03bView commit details

  Copy full SHA for dcda03b

  Browse repository at this point

• Reduce GPU memory utilization to make sure OOM doesn't happen (#153)

  zhuohan123

  authored
  bf5f121View commit details

  Copy full SHA for bf5f121

  Browse repository at this point

Commits on Jun 17, 2023

• Add quickstart guide (#148)

  zhuohan123

  authored
  bec7b2dView commit details

  Copy full SHA for bec7b2d

  Browse repository at this point

• Change the name to vLLM (#150)

  WoosukKwon

  authored
  0b98ba1View commit details

  Copy full SHA for 0b98ba1

  Browse repository at this point

• Rename servers to engines (#152)

  zhuohan123

  authored
  e5464eeView commit details

  Copy full SHA for e5464ee

  Browse repository at this point

• [Minor] Fix benchmark_throughput.py (#151)

  WoosukKwon

  authored
  bab8f3dView commit details

  Copy full SHA for bab8f3d

  Browse repository at this point

Commits on Jun 16, 2023

• Rename servers and change port numbers to reduce confusion (#149)

  zhuohan123

  authored
  eedb46bView commit details

  Copy full SHA for eedb46b

  Browse repository at this point

Commits on Jun 15, 2023

• Add script for benchmarking serving throughput (#145)

  WoosukKwon

  authored
  311490aView commit details

  Copy full SHA for 311490a

  Browse repository at this point

Commits on Jun 11, 2023

• Remove redundant code in ColumnParallelLinear (#146)

  WoosukKwon

  authored
  da5ddcdView commit details

  Copy full SHA for da5ddcd

  Browse repository at this point

Commits on Jun 10, 2023

• Non-streaming simple fastapi server (#144)

  zhuohan123

  authored
  5020e1eView commit details

  Copy full SHA for 5020e1e

  Browse repository at this point

Commits on Jun 7, 2023

• Add docstrings for LLMServer and related classes and examples (#142)

  zhuohan123

  authored
  4298374View commit details

  Copy full SHA for 4298374

  Browse repository at this point

• Support FP32 (#141)

  WoosukKwon

  authored
  e38074bView commit details

  Copy full SHA for e38074b

  Browse repository at this point

Commits on Jun 6, 2023

• [PyPI] Packaging for PyPI distribution (#140)

  WoosukKwon

  authored
  376725cView commit details

  Copy full SHA for 376725c

  Browse repository at this point

• [Docs] Write the `Adding a New Model` section (#138)

  WoosukKwon

  authored
  456941cView commit details

  Copy full SHA for 456941c

  Browse repository at this point

Commits on Jun 5, 2023

• Fix various issues of async servers (#135)

  zhuohan123

  authored
  1a956e1View commit details

  Copy full SHA for 1a956e1

  Browse repository at this point

Commits on Jun 4, 2023

• Add docstrings for LLM (#137)

  WoosukKwon

  authored
  8274ca2View commit details

  Copy full SHA for 8274ca2

  Browse repository at this point

Commits on Jun 3, 2023

• Document supported models (#127)

  WoosukKwon

  authored
  62ec38eView commit details

  Copy full SHA for 62ec38e

  Browse repository at this point

• Add .readthedocs.yaml (#136)

  WoosukKwon

  authored
  0eda2e0View commit details

  Copy full SHA for 0eda2e0

  Browse repository at this point

Commits on May 28, 2023

• Add throughput benchmarking script (#133)

  WoosukKwon

  authored
  211318dView commit details

  Copy full SHA for 211318d

  Browse repository at this point

• Enable LLaMA fast tokenizer (#132)

  WoosukKwon

  authored
  337871cView commit details

  Copy full SHA for 337871c

  Browse repository at this point

Commits on May 27, 2023

• Add a doc for installation (#128)

  WoosukKwon

  authored
  56b7f0eView commit details

  Copy full SHA for 56b7f0e

  Browse repository at this point