Commits

Branch selector

 3dda7c2

User selector

All users

Datepicker

All time

Commit History

Commits on Sep 23, 2024

• [Bugfix] Avoid some bogus messages RE CUTLASS's revision when building (vllm-project#8702)

  tlrmchlsmth

  authored
  3dda7c2

  Copy full SHA for 3dda7c2

Commits on Sep 22, 2024

• [misc] upgrade mistral-common (vllm-project#8715)

  youkaichao

  authored
  92ba7e7

  Copy full SHA for 92ba7e7

• [build] enable existing pytorch (for GH200, aarch64, nightly) (vllm-project#8713)

  youkaichao

  authored
  d4a2ac8

  Copy full SHA for d4a2ac8

• [SpecDec][Misc] Cleanup, remove bonus token logic. (vllm-project#8701)

  LiuXiaoxuanPKU

  authored
  c6bd70d

  Copy full SHA for c6bd70d

• [Model][VLM] Add LLaVA-Onevision model support (vllm-project#8486)

  Show description for 5b59532
  

  4 peopleauthored
  5b59532

  Copy full SHA for 5b59532

• [MISC] rename CudaMemoryProfiler to DeviceMemoryProfiler (vllm-project#8703)

  ji-huazhong

  authored
  ca2b628

  Copy full SHA for ca2b628

• [Misc] Use NamedTuple in Multi-image example (vllm-project#8705)

  Show description for 8ca5051
  alex-jw-brooks

  authored
  8ca5051

  Copy full SHA for 8ca5051

• [Model] Refactor BLIP/BLIP-2 to support composite model loading (vllm-project#8407)

  DarkLight1337

  authored
  06ed281

  Copy full SHA for 06ed281

• [ci][build] fix vllm-flash-attn (vllm-project#8699)

  youkaichao

  authored
  0e40ac9

  Copy full SHA for 0e40ac9

• [Bugfix] Refactor composite weight loading logic (vllm-project#8656)

  Isotr0py

  authored
  13d88d4

  Copy full SHA for 13d88d4

Commits on Sep 21, 2024

• [Kernel][Bugfix] Delete some more useless code in marlin_moe_ops.cu (vllm-project#8643)

  tlrmchlsmth

  authored
  d66ac62

  Copy full SHA for d66ac62

• [dbrx] refactor dbrx experts to extend FusedMoe class (vllm-project#8518)

  divakar-amd

  authored
  9dc7c6c

  Copy full SHA for 9dc7c6c

• [Kernel][Triton][AMD] Remove tl.atomic_add from awq_gemm_kernel, 2-5x speedup MI300, minor improvement for MI250 (vllm-project#8646)

  rasmith

  authored
  ec4aaad

  Copy full SHA for ec4aaad

• [Doc] Fix typo in AMD installation guide (vllm-project#8689)

  Imss27

  authored
  4dfdf43

  Copy full SHA for 4dfdf43

• [VLM] Use SequenceData.from_token_counts to create dummy data (vllm-project#8687)

  DarkLight1337

  authored
  5e85f4f

  Copy full SHA for 5e85f4f

• [Kernel] Build flash-attn from source (vllm-project#8245)

  ProExpertProg

  authored
  71c6049

  Copy full SHA for 71c6049

• [beam search] add output for manually checking the correctness (vllm-project#8684)

  youkaichao

  authored
  0faab90

  Copy full SHA for 0faab90

• [Core] Factor out common code in SequenceData and Sequence (vllm-project#8675)

  DarkLight1337

  authored
  0455c46

  Copy full SHA for 0455c46

• [MISC] add support custom_op check (vllm-project#8557)

  Show description for d4bf085
  

  jikunshang

  and

  youkaichao

  authored
  d4bf085

  Copy full SHA for d4bf085

• [Core] Rename PromptInputs and inputs(vllm-project#8673)

  DarkLight1337

  authored
  0057894

  Copy full SHA for 0057894

Commits on Sep 20, 2024

• [Bugfix] Fix incorrect llava next feature size calculation (vllm-project#8496)

  zyddnys

  authored
  0f961b3

  Copy full SHA for 0f961b3

• [Hardware][AWS] update neuron to 2.20 (vllm-project#8676)

  Show description for 7f9c890
  omrishiv

  authored
  7f9c890

  Copy full SHA for 7f9c890

• [Doc] neuron documentation update (vllm-project#8671)

  Show description for 7c8566a
  omrishiv

  authored
  7c8566a

  Copy full SHA for 7c8566a

• [Bugfix][Core] Fix tekken edge case for mistral tokenizer (vllm-project#8640)

  patrickvonplaten

  authored
  b4e4eda

  Copy full SHA for b4e4eda

• [Bugfix] Config got an unexpected keyword argument 'engine' (vllm-project#8556)

  Juelianqvq

  authored
  2874bac

  Copy full SHA for 2874bac

• [Misc] Show AMD GPU topology in collect_env.py (vllm-project#8649)

  DarkLight1337

  authored
  035fa89

  Copy full SHA for 035fa89

• [Bugfix] Validate SamplingParam n is an int (vllm-project#8548)

  saumya-saran

  authored
  b28298f

  Copy full SHA for b28298f

• [CI/Build] Removing entrypoints/openai/test_embedding.py test from ROCm build (vllm-project#8670)

  alexeykondrat

  authored
  2940afa

  Copy full SHA for 2940afa

• [Model] Add OLMoE (vllm-project#7922)

  Muennighoff

  authored
  3b63de9

  Copy full SHA for 3b63de9

• [Core] Support Lora lineage and base model metadata management (vllm-project#6315)

  Jeffwan

  authored
  260d40b

  Copy full SHA for 260d40b

• [bugfix] [AMD] add multi-step advance_step to ROCmFlashAttentionMetadata (vllm-project#8474)

  SolitaryThinker

  authored
  9e5ec35

  Copy full SHA for 9e5ec35

• [Bugfix] Fix Phi3.5 mini and MoE LoRA inference (vllm-project#8571)

  garg-amit

  authored
  18ae428

  Copy full SHA for 18ae428

Commits on Sep 19, 2024

• [Misc] guard against change in cuda library name (vllm-project#8609)

  bnellnm

  authored
  de6f90a

  Copy full SHA for de6f90a

• [CI/Build] Re-enabling Entrypoints tests on ROCm, excluding ones that fail (vllm-project#8551)

  alexeykondrat

  authored
  6cb748e

  Copy full SHA for 6cb748e

• Create SECURITY.md (vllm-project#8642)

  simon-mo

  authored
  9e99407

  Copy full SHA for 9e99407

Pagination

Previous

Next