Commits

Branch selector

 main

User selector

All users

Datepicker

All time

Commit History

Commits on Feb 21, 2025

• Missing comment explaining VDR variable in GGUF kernels (vllm-project#13290)

  SzymonOzog

  authored
  1cdc886

  Copy full SHA for 1cdc886

• [V1][Sampler] Avoid an operation during temperature application (vllm-project#13587)

  njhill

  authored
  31aa045

  Copy full SHA for 31aa045

• [Bugfix] Add mm_processor_kwargs to chat-related protocols (vllm-project#13644)

  ywang96

  authored
  a30c093

  Copy full SHA for a30c093

• Use pre-commit to update requirements-test.txt (vllm-project#13617)

  hmellor

  authored
  c7b07a9

  Copy full SHA for c7b07a9

• [NVIDIA] Fix an issue to use current stream for the nvfp4 quant (vllm-project#13632)

  kaixih

  authored
  27a09dc

  Copy full SHA for 27a09dc

• [Misc] Adding script to setup ray for multi-node vllm deployments (vllm-project#12913)

  Edwinhr716

  authored
  981f3c8

  Copy full SHA for 981f3c8

• Add llmaz as another integration (vllm-project#13643)

  Show description for 44c33f0
  kerthcet

  authored
  44c33f0

  Copy full SHA for 44c33f0

• [Neuron][Kernel] Vectorize KV cache load in FlashPagedAttention to maximize DMA bandwidth (vllm-project#13245)

  Show description for 3317008
  lingfanyu

  authored
  3317008

  Copy full SHA for 3317008

• [Bugfix] Fix max_num_batched_tokens for MLA (vllm-project#13620)

  Show description for 71face8
  mgoin

  authored
  71face8

  Copy full SHA for 71face8

Commits on Feb 20, 2025

• [Frontend] Add backend-specific options for guided decoding (vllm-project#13505)

  Show description for bfbc0b3
  joerunde

  authored
  bfbc0b3

  Copy full SHA for bfbc0b3

• fix neuron performance issue (vllm-project#13589)

  ajayvohra2005

  authored
  6a417b8

  Copy full SHA for 6a417b8

• [V1][Minor] Print KV cache size in token counts (vllm-project#13596)

  Show description for d3ea501
  WoosukKwon

  authored
  d3ea501

  Copy full SHA for d3ea501

• Update pre-commit's isort version to remove warnings (vllm-project#13614)

  hmellor

  authored
  34aad51

  Copy full SHA for 34aad51

• [Bugfix] Fix deepseekv3 grouped topk error (vllm-project#13474)

  Show description for ed6e907
  Chen-XiaoBing

  authored
  ed6e907

  Copy full SHA for ed6e907

• Merge similar examples in offline_inference into single basic example (vllm-project#12737)

  hmellor

  authored
  992e5c3

  Copy full SHA for 992e5c3

• [Kernel] LoRA - Refactor sgmv kernels (vllm-project#13110)

  varun-sundar-rabindranath

  authored
  b69692a

  Copy full SHA for b69692a

• [2/n][ci] S3: Use full model path (vllm-project#13564)

  Show description for a64a844
  khluu

  authored
  a64a844

  Copy full SHA for a64a844

• [ci] Fix spec decode test (vllm-project#13600)

  khluu

  authored
  aa1e62d

  Copy full SHA for aa1e62d

• [CI/Build] Use uv in the Dockerfile (vllm-project#13566)

  mgoin

  authored
  497bc83

  Copy full SHA for 497bc83

• [API Server] Add port number range validation (vllm-project#13506)

  Show description for 3738e6f
  terrytangyuan

  authored
  3738e6f

  Copy full SHA for 3738e6f

• [ROCm] MI300A compile targets deprecation (vllm-project#13560)

  gshtras

  authored
  0023cd2

  Copy full SHA for 0023cd2

• [Misc] add mm_processor_kwargs to extra_body for Qwen2.5-VL (vllm-project#13533)

  wulipc

  authored
  041e294

  Copy full SHA for 041e294

• [Misc] Warn if the vLLM version can't be retrieved (vllm-project#13501)

  Show description for 9621667
  alex-jw-brooks

  authored
  9621667

  Copy full SHA for 9621667

• [bugfix] spec decode worker get tp group only when initialized (vllm-project#13578)

  simon-mo

  authored
  8c755c3

  Copy full SHA for 8c755c3

• [core] add sleep and wake up endpoint and v1 support (vllm-project#12987)

  Show description for ba81163
  

  youkaichao

  and

  cennn

  authored
  ba81163

  Copy full SHA for ba81163

• [ROCm][MoE] mi300 mixtral8x7B perf for specific BS (vllm-project#13577)

  Show description for 0d243f2
  divakar-amd

  authored
  0d243f2

  Copy full SHA for 0d243f2

• [ci] Add AWS creds for AMD (vllm-project#13572)

  khluu

  authored
  88f6ba3

  Copy full SHA for 88f6ba3

• [Misc] Qwen2.5 VL support LoRA (vllm-project#13261)

  jeejeelee

  authored
  512368e

  Copy full SHA for 512368e

• [3/n][CI] Load Quantization test models with S3 (vllm-project#13570)

  Show description for 473f51c
  

  khluu

  and

  EC2 Default User

  authored
  473f51c

  Copy full SHA for 473f51c

• [BugFix] Avoid error traceback in logs when V1 LLM terminates (vllm-project#13565)

  Show description for a4c402a
  njhill

  authored
  a4c402a

  Copy full SHA for a4c402a

Commits on Feb 19, 2025

• [Misc] Avoid calling unnecessary hf_list_repo_files for local model path (vllm-project#13348)

  Show description for 550d97e
  Isotr0py

  authored
  550d97e

  Copy full SHA for 550d97e

• [MISC] Logging the message about Ray teardown (vllm-project#13502)

  Show description for fbbe1fb
  

  comaniac

  and

  ruisearch42

  authored
  fbbe1fb

  Copy full SHA for fbbe1fb

• Fix copyright year to auto get current year (vllm-project#13561)

  wilsonwu

  authored
  01c184b

  Copy full SHA for 01c184b

• [doc] clarify multi-node serving doc (vllm-project#13558)

  Show description for ad5a35c
  youkaichao

  authored
  ad5a35c

  Copy full SHA for ad5a35c

• [Bugfix] Fix device ordinal for multi-node spec decode (vllm-project#13269)

  Show description for 5ae9f26
  ShangmingCai

  authored
  5ae9f26

  Copy full SHA for 5ae9f26

Pagination

Previous

Next