Commits

Branch selector

 main

User selector

All users

Datepicker

All time

Commit History

Commits on Nov 27, 2024

• [Kernel] Remove if-else with identical branches in marlin 2:4 (vllm-project#10687)

  Show description for e225110
  tlrmchlsmth

  authored
  e225110

  Copy full SHA for e225110

• [Misc]Further reduce BNB static variable (vllm-project#10597)

  Show description for 15cc2a9
  jeejeelee

  authored
  15cc2a9

  Copy full SHA for 15cc2a9

• [Hardware][Gaudi]add get_name method for HPUAttentionBackend (vllm-project#10667)

  Show description for e85250b
  jikunshang

  authored
  e85250b

  Copy full SHA for e85250b

• [bugfix] fix the default value of llm_int8_threshold in BitsAndBytesConfig (vllm-project#10657)

  yansh97

  authored
  cfb3bf2

  Copy full SHA for cfb3bf2

• [Bugfix][SpecDecode] apply sampling parameters to target probabilities for consistency in rejection sampling. (vllm-project#10198)

  Show description for 1bf905d
  jeongin601

  authored
  1bf905d

  Copy full SHA for 1bf905d

• [V1] Update interface for idefics3 (vllm-project#10680)

  Show description for 0a4d968
  ywang96

  authored
  0a4d968

  Copy full SHA for 0a4d968

• Remove hard-dependencies of Speculative decode to CUDA workers (vllm-project#10587)

  Show description for 0a71900
  xuechendi

  authored
  0a71900

  Copy full SHA for 0a71900

Commits on Nov 26, 2024

• [V1] Refactor model executable interface for multimodal models (vllm-project#10570)

  Show description for 2f0a0a1
  ywang96

  authored
  2f0a0a1

  Copy full SHA for 2f0a0a1

• [Bugfix] Check bnb_4bit_quant_storage for bitsandbytes (vllm-project#10642)

  mgoin

  authored
  7576cd3

  Copy full SHA for 7576cd3

• [Bugfix] Fix using -O[0,3] with LLM entrypoint (vllm-project#10677)

  Show description for 9a99273
  mgoin

  authored
  9a99273

  Copy full SHA for 9a99273

• [Hardware][NVIDIA] Add non-NVML CUDA mode for Jetson (vllm-project#9735)

  Show description for f5792c7
  conroy-cheers

  authored
  f5792c7

  Copy full SHA for f5792c7

• [Bugfix] Fix for Spec model TP + Chunked Prefill (vllm-project#10232)

  Show description for db66e01
  

  andoorve

  and

  sroy745

  authored
  db66e01

  Copy full SHA for db66e01

• [V1] Enable profile for LLMEngine (vllm-project#10665)

  jikunshang

  authored
  1f6584e

  Copy full SHA for 1f6584e

• [ci] add vllm_test_utils (vllm-project#10659)

  Show description for 334d64d
  youkaichao

  authored
  334d64d

  Copy full SHA for 334d64d

• [Misc] Remove outdated init protocols (vllm-project#10655)

  Show description for 9406353
  DarkLight1337

  authored
  9406353

  Copy full SHA for 9406353

• custom allreduce + torch.compile (vllm-project#10121)

  Show description for 9a88f89
  

  SageMoore

  and

  youkaichao

  authored
  9a88f89

  Copy full SHA for 9a88f89

• [v1] EngineArgs for better config handling for v1 (vllm-project#10382)

  Show description for 519e8e4
  rickyyx

  authored
  519e8e4

  Copy full SHA for 519e8e4

• [Feature] vLLM ARM Enablement for AARCH64 CPUs (vllm-project#9228)

  Show description for a6760f6
  

  3 peopleauthored
  a6760f6

  Copy full SHA for a6760f6

• [bugfix] fix aria model and add torch.compile (vllm-project#10645)

  Show description for 45ac4ff
  youkaichao

  authored
  45ac4ff

  Copy full SHA for 45ac4ff

• [misc] do not read HOST_IP (vllm-project#10644)

  Show description for 6e9ff05
  youkaichao

  authored
  6e9ff05

  Copy full SHA for 6e9ff05

Commits on Nov 25, 2024

• [Model] Add OLMo November 2024 model (vllm-project#10503)

  2015aroras

  authored
  9db713a

  Copy full SHA for 9db713a

• [Doc] Fix typos in docs (vllm-project#10636)

  Show description for 1b583cf
  DarkLight1337

  authored
  1b583cf

  Copy full SHA for 1b583cf

• [Model] Enable optional prefix when loading embedding models (vllm-project#10639)

  Show description for cf73f0c
  DarkLight1337

  authored
  cf73f0c

  Copy full SHA for cf73f0c

• [Model]: Add support for Aria model (vllm-project#10514)

  Show description for b1d9205
  

  xffxff

  and

  Isotr0py

  authored
  b1d9205

  Copy full SHA for b1d9205

• [Docs] Add Snowflake Slides (vllm-project#10641)

  Show description for 452a4e8
  simon-mo

  authored
  452a4e8

  Copy full SHA for 452a4e8

• [Bugfix] Fix chunked prefill with model dtype float32 on Turing Devices (vllm-project#9850)

  Show description for c27df94
  

  wallashss

  and

  mgoin

  authored
  c27df94

  Copy full SHA for c27df94

• [Bug]: Authorization ignored when root_path is set (vllm-project#10606)

  Show description for d04b13a
  chaunceyjiang

  authored
  d04b13a

  Copy full SHA for d04b13a

• Super tiny little typo fix (vllm-project#10633)

  fzyzcjy

  authored
  2b0879b

  Copy full SHA for 2b0879b

• [Model] Support is_causal HF config field for Qwen2 model (vllm-project#10621)

  Show description for ed46f14
  DarkLight1337

  authored
  ed46f14

  Copy full SHA for ed46f14

• [misc] move functions to config.py (vllm-project#10624)

  Show description for 05d1f8c
  youkaichao

  authored
  05d1f8c

  Copy full SHA for 05d1f8c

• [misc] add torch.compile compatibility check (vllm-project#10618)

  Show description for 25d806e
  youkaichao

  authored
  25d806e

  Copy full SHA for 25d806e

• [torch.compile] add warning for unsupported models (vllm-project#10622)

  Show description for 6581378
  youkaichao

  authored
  6581378

  Copy full SHA for 6581378

• [torch.compile] force inductor threads (vllm-project#10620)

  Show description for 7c2134b
  jeejeelee

  authored
  7c2134b

  Copy full SHA for 7c2134b

• [Doc] Add encoder-based models to Supported Models page (vllm-project#10616)

  Show description for a30a605
  DarkLight1337

  authored
  a30a605

  Copy full SHA for a30a605

• [torch.compile] support encoder based models (vllm-project#10613)

  Show description for 571841b
  youkaichao

  authored
  571841b

  Copy full SHA for 571841b

Pagination

Previous

Next