Commits

Branch selector

 711a000

User selector

All users

Datepicker

All time

Commit History

Commits on Apr 14, 2024

• [Frontend] [Core] feat: Add model loading using tensorizer (vllm-project#3476)

  sangstar

  authored
  711a000

Commits on Apr 13, 2024

• [Kernel] Add punica dimension for Baichuan-13B (vllm-project#4053)

  jeejeelee

  authored
  989ae25

• [Bugfix] fix_small_bug_in_neuron_executor (vllm-project#4051)

  zspo

  authored
  0a430b4

• [Bugfix] fix_log_time_in_metrics (vllm-project#4050)

  zspo

  authored
  ec8e3c6

• [Core][Distributed] improve logging for init dist (vllm-project#4042)

  youkaichao

  authored
  98afde1

• [Bugfix] More type hint fixes for py 3.8 (vllm-project#4039)

  dylanwhawk

  authored
  5c2e66e

• [CI/Test] expand ruff and yapf for all supported python version (vllm-project#4037)

  youkaichao

  authored
  546e721

Commits on Apr 12, 2024

• [Bugfix] Fix LoRA bug (vllm-project#4032)

  jeejeelee

  authored
  b8aacac

• Fix triton compilation issue (vllm-project#3984)

  Show description for d04973a
  

  Bellk17

  and

  WoosukKwon

  authored
  d04973a

• [Core] fix custom allreduce default value (vllm-project#4040)

  youkaichao

  authored
  fbb9d9e

• [mypy] Add mypy type annotation part 1 (vllm-project#4006)

  rkooo567

  authored
  09473ee

• [Misc] Fix typo in scheduler.py (vllm-project#4022)

  zhuohan123

  authored
  d4ec9ff

• [Bugfix] fix type hint for py 3.8 (vllm-project#4036)

  youkaichao

  authored
  96b6a6d

• [Test] Test multiple attn backend for chunked prefill. (vllm-project#4023)

  rkooo567

  authored
  36729ba

• [Frontend][Core] Move merge_async_iterators to utils (vllm-project#4026)

  DarkLight1337

  authored
  7fd3949

• [Core] Support LoRA on quantized models (vllm-project#4012)

  jeejeelee

  authored
  1096717

• [Doc] Add typing hints / mypy types cleanup (vllm-project#3816)

  Show description for c2b4a1b
  

  michaelfeil

  and

  ywang96

  authored
  c2b4a1b

Commits on Apr 11, 2024

• [BugFix] Fix handling of stop strings and stop token ids (vllm-project#3672)

  njhill

  authored
  e46a60a

• Add extra punica sizes to support bigger vocabs (vllm-project#4015)

  Yard1

  authored
  1e96c33

• Fix echo/logprob OpenAI completion bug (vllm-project#3441)

  Show description for 95e7d4a
  

  dylanwhawk

  and

  Dylan Hawk

  authored
  95e7d4a

• [Core] init_distributed_environment align with init_process_group(vllm-project#4014)

  Show description for 559eb85
  youkaichao

  authored
  559eb85

• [Core] Set linear_weights directly on the layer (vllm-project#3977)

  Yard1

  authored
  a10d305

• [Hardware][Intel] Isolate CPUModelRunner and ModelRunner for better maintenance (vllm-project#3824)

  bigPYJ1151

  authored
  8afca50

• punica fix-bgmv-kernel-640 (vllm-project#4007)

  kingljl

  authored
  08ccee1

• [Kernel] Fused MoE Config for Mixtral 8x22 (vllm-project#4002)

  ywang96

  authored
  c1dc547

• [Doc][Installation] delete python setup.py develop (vllm-project#3989)

  youkaichao

  authored
  f3d0bf7

• [Misc] Add indirection layer for custom ops (vllm-project#3913)

  jikunshang

  authored
  e9da5a4

• [Test] Add xformer and flash attn tests (vllm-project#3961)

  Show description for e42df72
  

  rkooo567

  and

  simon-mo

  authored
  e42df72

• [Core][Model] torch.compile for layernorm in commandr (vllm-project#3985)

  Show description for caada5e
  youkaichao

  authored
  caada5e

• [Core][5/N] Fully working chunked prefill e2e (vllm-project#3884)

  rkooo567

  authored
  67b4221

Commits on Apr 10, 2024

• [Core][Refactor] move parallel_utils into vllm/distributed (vllm-project#3950)

  Show description for 63e7176
  youkaichao

  authored
  63e7176

• [Bugfix] handle hf_config with architectures == None (vllm-project#3982)

  Show description for 934d366
  

  tjohnson31415

  and

  simon-mo

  authored
  934d366

• [Doc] Fix getting stared to use publicly available model (vllm-project#3963)

  fpaupier

  authored
  92cd2e2

• [Bugfix] Remove key sorting for guided_json parameter in OpenAi compatible Server (vllm-project#3945)

  dmarasco

  authored
  e4c4072

• [Doc] Add doc to state our model support policy (vllm-project#3948)

  Show description for e353974
  

  youkaichao

  and

  ywang96

  authored
  e353974

Pagination

PreviousNext