Commits

Branch selector

 main

User selector

All users

Datepicker

All time

Commit History

Commits on Aug 17, 2024

• [Bugfix] Fix custom_ar support check (vllm-project#7617)

  bnellnm

  authored
  e680349

  Copy full SHA for e680349

Commits on Aug 16, 2024

• [Model] Align nemotron config with final HF state and fix lm-eval-small (vllm-project#7611)

  mgoin

  authored
  44f26a9

  Copy full SHA for 44f26a9

• [Kernel] fix types used in aqlm and ggml kernels to support dynamo (vllm-project#7596)

  bnellnm

  authored
  37fd47e

  Copy full SHA for 37fd47e

• [Kernel][Misc] dynamo support for ScalarType (vllm-project#7594)

  bnellnm

  authored
  7759ae9

  Copy full SHA for 7759ae9

• [Kernel] register punica functions as torch ops (vllm-project#7591)

  bnellnm

  authored
  9f69856

  Copy full SHA for 9f69856

• [Doc] Update quantization supported hardware table (vllm-project#7595)

  mgoin

  authored
  d4f0f17

  Copy full SHA for d4f0f17

• [Doc] Add docs for llmcompressor INT8 and FP8 checkpoints (vllm-project#7444)

  mgoin

  authored
  b3f4e17

  Copy full SHA for b3f4e17

• [Core] Fix tracking of model forward time in case of PP>1 (vllm-project#7440)

  Show description for 93478b6
  sfc-gh-mkeralapura

  authored
  93478b6

  Copy full SHA for 93478b6

• [spec decode] [4/N] Move update_flash_attn_metadata to attn backend (vllm-project#7571)

  Show description for f366f63
  

  SolitaryThinker

  and

  comaniac

  authored
  f366f63

  Copy full SHA for f366f63

• [Kernel] Add tuned triton configs for ExpertsInt8 (vllm-project#7601)

  mgoin

  authored
  855866c

  Copy full SHA for 855866c

• [Kernel] W8A16 Int8 inside FusedMoE (vllm-project#7415)

  mzusman

  authored
  7fc23be

  Copy full SHA for 7fc23be

• [Feature][Hardware][Amd] Add fp8 Linear Layer for Rocm (vllm-project#7210)

  charlifu

  authored
  e837b62

  Copy full SHA for e837b62

• support tqdm in notebooks (vllm-project#7510)

  fzyzcjy

  authored
  ec724a7

  Copy full SHA for ec724a7

• [Bugfix][Hardware][AMD][Frontend] add quantization param to embedding checking method (vllm-project#7513)

  gongdao123

  authored
  0e39a33

  Copy full SHA for 0e39a33

• [CI] Fix crashes of performance benchmark (vllm-project#7500)

  KuntaiDu

  authored
  6fc5b0f

  Copy full SHA for 6fc5b0f

• [Core] Use uvloop with zmq-decoupled front-end (vllm-project#7570)

  njhill

  authored
  9587b05

  Copy full SHA for 9587b05

• register custom op for flash attn and use from torch.ops (vllm-project#7536)

  youkaichao

  authored
  54bd9a0

  Copy full SHA for 54bd9a0

• [Misc/Testing] Use torch.testing.assert_close (vllm-project#7324)

  jon-chuang

  authored
  50b8d08

  Copy full SHA for 50b8d08

• [CI] Move quantization cpu offload tests out of fastcheck (vllm-project#7574)

  mgoin

  authored
  e165528

  Copy full SHA for e165528

• Chat method for offline llm (vllm-project#5049)

  Show description for 3b19e39
  

  5 peopleauthored
  3b19e39

  Copy full SHA for 3b19e39

• [ci/test] rearrange tests and make adag test soft fail (vllm-project#7572)

  youkaichao

  authored
  4cd7d47

  Copy full SHA for 4cd7d47

• [Feature]: Add OpenAI server prompt_logprobs support vllm-project#6508 (vllm-project#7453)

  gnpinkert

  authored
  f878c8f

  Copy full SHA for f878c8f

• [Misc] Add quantization config support for speculative model. (vllm-project#7343)

  ShangmingCai

  authored
  b67ae00

  Copy full SHA for b67ae00

• [Bugfix][Harmless] Fix float16 dtype for model_is_embedding (vllm-project#7566)

  mgoin

  authored
  9c8e2d1

  Copy full SHA for 9c8e2d1

Commits on Aug 15, 2024

• [Bugfix] Fix default weight loading for scalars (vllm-project#7534)

  mgoin

  authored
  21313e0

  Copy full SHA for 21313e0

• [Misc] Update dockerfile for CPU to cover protobuf installation (vllm-project#7182)

  PHILO-HE

  authored
  f4da5f7

  Copy full SHA for f4da5f7

• [Bugfix] update neuron for version > 0.5.0 (vllm-project#7175)

  Show description for 9c1f78d
  

  omrishiv

  and

  DarkLight1337

  authored
  9c1f78d

  Copy full SHA for 9c1f78d

• [Bugfix][TPU] Correct env variable for XLA cache path (vllm-project#7544)

  WoosukKwon

  authored
  fc93e56

  Copy full SHA for fc93e56

Commits on Aug 14, 2024

• llama_index serving integration documentation (vllm-project#6973)

  Show description for 22b39e1
  

  pavanjava

  and

  pavanmantha

  authored
  22b39e1

  Copy full SHA for 22b39e1

• [Misc] Revert compressed-tensors code reuse (vllm-project#7521)

  kylesayrs

  authored
  f55a9ae

  Copy full SHA for f55a9ae

• [TPU] Set per-rank XLA cache (vllm-project#7533)

  WoosukKwon

  authored
  951fdd6

  Copy full SHA for 951fdd6

• [core] [3/N] multi-step args and sequence.py (vllm-project#7452)

  SolitaryThinker

  authored
  2ecf7b1

  Copy full SHA for 2ecf7b1

• [VLM][Core] Support profiling with multiple multi-modal inputs per prompt (vllm-project#7126)

  DarkLight1337

  authored
  3f674a4

  Copy full SHA for 3f674a4

• [Misc] Deprecation Warning when setting --engine-use-ray (vllm-project#7424)

  Show description for 70b746e
  

  3 peopleauthored
  70b746e

  Copy full SHA for 70b746e

• [Bugfix][Frontend] Disable embedding API for chat models (vllm-project#7504)

  Show description for 67d115d
  

  QwertyJack

  and

  jack

  authored
  67d115d

  Copy full SHA for 67d115d

Pagination

Previous

Next