Code

[DO NOT MERGE] Ibm dev rebased#255

Code

Open

prashantgupta24 wants to merge 43 commits intomainopendatahub-io/vllm:mainfrom ibm-dev-rebasedopendatahub-io/vllm:ibm-dev-rebasedCopy head branch name to clipboard

+7,787-3,228

Commits

Commits on Dec 3, 2024

• [Docs] Add Nebius as sponsors (vllm-project#10371)

  Show description for 42d3a81
  

  simon-mo

  authored and

  prashantgupta24

  committed
  42d3a81

• [Frontend] Add --version flag to CLI (vllm-project#10369)

  Show description for a18c4fb
  

  russellb

  authored and

  prashantgupta24

  committed
  a18c4fb

• [Doc] Move PR template content to docs (vllm-project#10159)

  Show description for 067dd2b
  

  russellb

  authored and

  prashantgupta24

  committed
  067dd2b

• [Docs] Misc updates to TPU installation instructions (vllm-project#10165)

  

  mikegre-google

  authored and

  prashantgupta24

  committed
  82be00f

• [Frontend] Automatic detection of chat content format from AST (vllm-project#9919)

  Show description for 2ca5912
  

  DarkLight1337

  authored and

  prashantgupta24

  committed
  2ca5912

• [doc] add doc for the plugin system (vllm-project#10372)

  Show description for ea480a1
  

  youkaichao

  authored and

  prashantgupta24

  committed
  ea480a1

• [misc][plugin] improve log messages (vllm-project#10386)

  Show description for 2e453bc
  

  youkaichao

  authored and

  prashantgupta24

  committed
  2e453bc

• [BugFix] [Kernel] Fix GPU SEGV occuring in fused_moe kernel (vllm-project#10385)

  Show description for 51813a4
  

  rasmith

  authored and

  prashantgupta24

  committed
  51813a4

• [Misc] Update benchmark to support image_url file or http (vllm-project#10287)

  Show description for 6c45f56
  

  kakao-steve-ai

  authored and

  prashantgupta24

  committed
  6c45f56

• [Misc] Medusa supports custom bias (vllm-project#10361)

  

  skylee-01

  authored and

  prashantgupta24

  committed
  d93bde9

• [Bugfix] Fix M-RoPE position calculation when chunked prefill is enabled (vllm-project#10388)

  Show description for 068451f
  

  imkero

  authored and

  prashantgupta24

  committed
  068451f

• [V1] Add code owners for V1 (vllm-project#10397)

  Show description for d49dacb
  

  WoosukKwon

  authored and

  prashantgupta24

  committed
  d49dacb

• [2/N][torch.compile] make compilation cfg part of vllm cfg (vllm-project#10383)

  Show description for 11d2bbc
  

  youkaichao

  authored and

  prashantgupta24

  committed
  11d2bbc

• [V1] Refactor model executable interface for all text-only language models (vllm-project#10374)

  Show description for 2ea854d
  

  ywang96

  authored and

  prashantgupta24

  committed
  2ea854d

• [CI/Build] Fix IDC hpu [Device not found] issue (vllm-project#10384)

  Show description for 2652ea1
  

  xuechendi

  authored and

  prashantgupta24

  committed
  2652ea1

• [Bugfix][CPU] Fix CPU embedding runner with tensor parallel (vllm-project#10394)

  Show description for 47325d5
  

  Isotr0py

  authored and

  prashantgupta24

  committed
  47325d5

• [platforms] refactor cpu code (vllm-project#10402)

  Show description for e288d72
  

  youkaichao

  authored and

  prashantgupta24

  committed
  e288d72

• [Hardware] [HPU]add mark_step for hpu (vllm-project#10239)

  Show description for f6dc8be
  

  jikunshang

  authored and

  prashantgupta24

  committed
  f6dc8be

• [Bugfix] Fix mrope_position_delta in non-last prefill chunk (vllm-project#10403)

  Show description for dcccc62
  

  imkero

  authored and

  prashantgupta24

  committed
  dcccc62

• [Misc] Enhance offline_inference to support user-configurable paramet… (vllm-project#10392)

  Show description for d97d269
  

  wchen61

  authored and

  prashantgupta24

  committed
  d97d269

• [Misc] Add uninitialized params tracking for AutoWeightsLoader (vllm-project#10327)

  Show description for d3fe99b
  

  Isotr0py

  authored and

  prashantgupta24

  committed
  d3fe99b

• [Bugfix] Ignore ray reinit error when current platform is ROCm or XPU (vllm-project#10375)

  Show description for 1f165b6
  

  HollowMan6

  authored and

  prashantgupta24

  committed
  1f165b6

• [4/N][torch.compile] clean up set_torch_compile_backend (vllm-project#10401)

  Show description for 56b9c49
  

  youkaichao

  authored and

  prashantgupta24

  committed
  56b9c49

• [VLM] Report multi_modal_placeholders in output (vllm-project#10407)

  Show description for 663fb57
  

  lk-chen

  authored and

  prashantgupta24

  committed
  663fb57

• [Model] Remove redundant softmax when using PoolingType.STEP (vllm-project#10415)

  

  Maybewuss

  authored and

  prashantgupta24

  committed
  3c64fbb

• [Model][LoRA]LoRA support added for glm-4v (vllm-project#10418)

  Show description for 20ea0c3
  

  B-201

  authored and

  prashantgupta24

  committed
  20ea0c3

• [Model] Remove transformers attention porting in VITs (vllm-project#10414)

  Show description for b1d6a6a
  

  Isotr0py

  authored and

  prashantgupta24

  committed
  b1d6a6a

• [Doc] Update doc for LoRA support in GLM-4V (vllm-project#10425)

  Show description for 5d6df78
  

  B-201

  authored and

  prashantgupta24

  committed
  5d6df78

• [5/N][torch.compile] torch.jit.script --> torch.compile (vllm-project#10406)

  Show description for b4c641f
  

  youkaichao

  authored and

  prashantgupta24

  committed
  b4c641f

• [Doc] Add documentation for Structured Outputs (vllm-project#9943)

  Show description for c973945
  

  ismael-dm

  authored and

  prashantgupta24

  committed
  c973945

• Fix open_collective value in FUNDING.yml (vllm-project#10426)

  Show description for e19e15a
  

  andrew

  authored and

  prashantgupta24

  committed
  e19e15a

• [Model][Bugfix] Support TP for PixtralHF ViT (vllm-project#10405)

  Show description for a00d8c1
  

  mgoin

  authored and

  prashantgupta24

  committed
  a00d8c1

• [Hardware][XPU] AWQ/GPTQ support for xpu backend (vllm-project#10107)

  Show description for 472b9cf
  

  yma11

  authored and

  prashantgupta24

  committed
  472b9cf

• [Kernel] Explicitly specify other value in tl.load calls (vllm-project#9014)

  Show description for 9147b76
  

  angusYuhao

  authored and

  prashantgupta24

  committed
  9147b76

• [Kernel] Initial Machete W4A8 support + Refactors (vllm-project#9855)

  Show description for ce83e18
  

  LucasWilkinson

  authored and

  prashantgupta24

  committed
  ce83e18

• Squash 9522

  Show description for bf5bf24
  

  fialhocoelho

  authored and

  prashantgupta24

  committed
  bf5bf24

• Squash 6357

  Show description for 8b27172
  

  fialhocoelho

  authored and

  prashantgupta24

  committed
  8b27172

• Squash 10235

  Show description for e8fcdee
  

  fialhocoelho

  authored and

  prashantgupta24

  committed
  e8fcdee

• Squash 10400

  Show description for 1e7f586
  

  fialhocoelho

  authored and

  prashantgupta24

  committed
  1e7f586

• Squash 10430

  Show description for 09f5b4a
  

  fialhocoelho

  authored and

  prashantgupta24

  committed
  09f5b4a

• pin mistral and install adapter from branch 🚀

  Show description for 33c1553
  

  fialhocoelho

  authored and

  prashantgupta24

  committed
  33c1553

Commits on Dec 4, 2024

• Dockerfile.ubi: remove extra line continuation

  

  dtrifiro

  authored and

  prashantgupta24

  committed
  f931d71

• Merge branch 'main' into ibm-dev-rebased

  prashantgupta24

  authored
  87ebca7