Commits

Branch selector

 58ca663

User selector

All users

Datepicker

All time

Commit History

Commits on Jul 18, 2024

• [ Misc ] Improve Min Capability Checking in compressed-tensors (vllm-project#6522)

  robertgshaw2-redhat

  authored
  58ca663

  Copy full SHA for 58ca663

• [TPU] Refactor TPU worker & model runner (vllm-project#6506)

  WoosukKwon

  authored
  4634c87

  Copy full SHA for 4634c87

• [Bugfix] Update flashinfer.py with PagedAttention forwards - Fixes Gemma2 OpenAI Server Crash (vllm-project#6501)

  noamgat

  authored
  c8a7d51

  Copy full SHA for c8a7d51

• [BugFix][Frontend] Use LoRA tokenizer in OpenAI APIs (vllm-project#6227)

  Show description for e2fbaee
  

  njhill

  and

  DarkLight1337

  authored
  e2fbaee

  Copy full SHA for e2fbaee

• [Misc] Minor patch for draft model runner (vllm-project#6523)

  comaniac

  authored
  8a74c68

  Copy full SHA for 8a74c68

• [Core] Introduce SPMD worker execution using Ray accelerated DAG (vllm-project#6032)

  Show description for 61e5927
  

  ruisearch42

  and

  stephanie-wang

  authored
  61e5927

  Copy full SHA for 61e5927

• [BugFix] Avoid secondary error in ShmRingBuffer destructor (vllm-project#6530)

  njhill

  authored
  d25877d

  Copy full SHA for d25877d

• [core][model] yet another cpu offload implementation (vllm-project#6496)

  Show description for 1c27d25
  

  youkaichao

  and

  mgoin

  authored
  1c27d25

  Copy full SHA for 1c27d25

• [ Kernel ] Fp8 Channelwise Weight Support (vllm-project#6487)

  robertgshaw2-redhat

  authored
  18fecc3

  Copy full SHA for 18fecc3

• [Model] Pipeline parallel support for Mixtral (vllm-project#6516)

  comaniac

  authored
  b5af8c2

  Copy full SHA for b5af8c2

• [ Kernel ] FP8 Dynamic-Per-Token Quant Kernel (vllm-project#6511)

  Show description for b5241e4
  

  varun-sundar-rabindranath

  and

  Varun Sundar Rabindranath

  authored
  b5241e4

  Copy full SHA for b5241e4

Commits on Jul 17, 2024

• [Core] draft_model_runner: Implement prepare_inputs on GPU for advance_step (vllm-project#6338)

  alexm-redhat

  authored
  e76466d

  Copy full SHA for e76466d

• [Bugfix] Fix Ray Metrics API usage (vllm-project#6354)

  Yard1

  authored
  5f0b993

  Copy full SHA for 5f0b993

• [DOC] - Add docker image to Cerebrium Integration (vllm-project#6510)

  milo157

  authored
  a38524f

  Copy full SHA for a38524f

• [Core] Refactor _prepare_model_input_tensors - take 2 (vllm-project#6164)

  comaniac

  authored
  2fa4623

  Copy full SHA for 2fa4623

• [Misc] Use torch.Tensor for type annotation (vllm-project#6505)

  WoosukKwon

  authored
  a9a2e74

  Copy full SHA for a9a2e74

• [TPU] Remove multi-modal args in TPU backend (vllm-project#6504)

  WoosukKwon

  authored
  e09ce75

  Copy full SHA for e09ce75

• [Bugfix] Fix for multinode crash on 4 PP (vllm-project#6495)

  Show description for 5fa6e98
  andoorve

  authored
  5fa6e98

  Copy full SHA for 5fa6e98

• [Doc][CI/Build] Update docs and tests to use vllm serve (vllm-project#6431)

  DarkLight1337

  authored
  5bf35a9

  Copy full SHA for 5bf35a9

• [Misc][Speculative decoding] Typos and typing fixes (vllm-project#6467)

  Show description for a19e8d3
  ShangmingCai

  authored
  a19e8d3

  Copy full SHA for a19e8d3

• [ROCm] Cleanup Dockerfile and remove outdated patch (vllm-project#6482)

  hongxiayang

  authored
  1038388

  Copy full SHA for 1038388

• [Distributed][PP] only create embedding & lm head when necessary (vllm-project#6455)

  Show description for 1d094fd
  wushidonguc

  authored
  1d094fd

  Copy full SHA for 1d094fd

• [misc][distributed] add seed to dummy weights (vllm-project#6491)

  youkaichao

  authored
  ce37be7

  Copy full SHA for ce37be7

• [misc][distributed] improve tests (vllm-project#6488)

  youkaichao

  authored
  7f62077

  Copy full SHA for 7f62077

Commits on Jul 16, 2024

• [ci][distributed] add pipeline parallel correctness test (vllm-project#6410)

  youkaichao

  authored
  09c2eb8

  Copy full SHA for 09c2eb8

• [Kernel][Attention] Separate Attention.kv_scale into k_scale and v_scale (vllm-project#6081)

  mgoin

  authored
  978aed5

  Copy full SHA for 978aed5

• [Misc] Log spec decode metrics (vllm-project#6454)

  comaniac

  authored
  160e1d8

  Copy full SHA for 160e1d8

• [Doc] Fix the lora adapter path in server startup script (vllm-project#6230)

  Jeffwan

  authored
  94162be

  Copy full SHA for 94162be

• [Hardware][TPU] Support MoE with Pallas GMM kernel (vllm-project#6457)

  WoosukKwon

  authored
  c467dff

  Copy full SHA for c467dff

• [doc][misc] remind to cancel debugging environment variables (vllm-project#6481)

  Show description for 9f4ccec
  youkaichao

  authored
  9f4ccec

  Copy full SHA for 9f4ccec

• [CI/Build] Remove "boardwalk" image asset (vllm-project#6460)

  DarkLight1337

  authored
  38ef948

  Copy full SHA for 38ef948

• [Core] Use numpy to speed up padded token processing (vllm-project#6442)

  peng1999

  authored
  2bb0489

  Copy full SHA for 2bb0489

• [Misc] Fix typos in spec. decode metrics logging. (vllm-project#6470)

  Show description for 7508a3d
  tdoublep

  authored
  7508a3d

  Copy full SHA for 7508a3d

• [Frontend] Support for chat completions input in the tokenize endpoint (vllm-project#5923)

  sasha0552

  authored
  7a3d2a5

  Copy full SHA for 7a3d2a5

• [CI/Build] vLLM cache directory for images (vllm-project#6444)

  DarkLight1337

  authored
  d970115

  Copy full SHA for d970115

Pagination

Previous

Next