Commits · 78f4bb0ba8c70f8876311cc414938d3d68997fc6 · OpenDAS / vllm_cscc

03 Dec, 2025 19 commits
- [DOC] Add Arm to list of compute resouces providers (#29894) · 78f4bb0b
  Fadi Arafeh authored Dec 03, 2025
```
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
```
  78f4bb0b
- [refactor] CTMoEMethods to use QuantizationArgs (#28871) · b294e28d
  HDCharles authored Dec 03, 2025
```
Signed-off-by: HDCharles <charlesdavidhernandez@gmail.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  b294e28d
- [Bugfix] Follow-up fix on MediaWithBytes (#29951) · 787b84a9
  Roger Wang authored Dec 03, 2025
```
Signed-off-by: Roger Wang <hey@rogerw.io>
```
  787b84a9
- [Bugfix][Quantization] Support BF16 tensors on GGUF (#29948) · 42c19496
  Tsukasa OI authored Dec 03, 2025
```
Signed-off-by: Tsukasa OI <floss_llm@irq.a4lg.com>
```
  42c19496
- [CI/Build] Avoid duplicate empty inputs test for common multimodal generation tests (#29907) · cc4e296e
  Isotr0py authored Dec 03, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  cc4e296e
- [Bugfix] Fix incorrect `image_grid_thw` rank for HunyuanOCR from missing... · a21cd9ed
  Isotr0py authored Dec 03, 2025
```
[Bugfix] Fix incorrect `image_grid_thw` rank for HunyuanOCR from missing `merge_by_field_config=True` (#29950)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  a21cd9ed
- [CI] Add Async Eplb nightly CI tests (#29385) · 7fe9c1a2
  WeiQing Chen authored Dec 03, 2025
```
Signed-off-by: David Chen <530634352@qq.com>
Signed-off-by: WeiQing Chen <40507679+david6666666@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
  7fe9c1a2
- [Refactor] [1/N] to simplify the vLLM serving architecture (#28040) · 3f42b05f
  Chauncey authored Dec 03, 2025
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
  3f42b05f
- Add logging for cudagraph related info (#29825) · 69520bc6
  Yong Hoon Shin authored Dec 02, 2025
```
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
```
  69520bc6
- [responsesAPI] support input output messages for non harmony models (#29549) · 3a775148
  Andrew Xia authored Dec 02, 2025
```
Signed-off-by: Andrew Xia <axia@fb.com>
Co-authored-by: Andrew Xia <axia@fb.com>
```
  3a775148
- [Misc] Allow `fetch_*` utils to access local files by default (#29932) · bbfb55c2
  Cyrus Leung authored Dec 03, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  bbfb55c2
- [BugFix] fix imgs_pos in hunyuan_vl (#29879) · 0bec63fa
  JackieWu authored Dec 03, 2025
```
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  0bec63fa
- [Bugfix] Defunctionalize TRTLLM AR+Norm op for avoiding extra clone kernel before it (#29631) · c719c405
  elvischenv authored Dec 03, 2025
```
Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
```
  c719c405
- [Docs] Discuss api key limitations in security guide (#29922) · b08025a8
  Russell Bryant authored Dec 02, 2025
```
Signed-off-by: Russell Bryant <rbryant@redhat.com>
```
  b08025a8
- [Core] Rename PassConfig flags as per RFC #27995 (#29646) · d7284a26
  Arpit Khandelwal authored Dec 02, 2025
```
Signed-off-by: arpitkh101 <arpit5khandelwal@gmail.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
```
  d7284a26
- [ROCm][CI][Bugfix] Disable Flash/MemEfficient SDP on ROCm to avoid HF... · 506ed87e
  Andreas Karatzas authored Dec 02, 2025
```
[ROCm][CI][Bugfix] Disable Flash/MemEfficient SDP on ROCm to avoid HF Transformers accuracy issues (#29909)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  506ed87e
- [Bugfix] Fix regression on pooling models from PR#29621 (#29921) · 4dd79783
  Roger Wang authored Dec 02, 2025
```
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  4dd79783
- [BugFix] Fix assert in `build_for_cudagraph_capture` (#29893) · 5cdd6645
  Lucas Wilkinson authored Dec 02, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
  5cdd6645
- Reverting re-direction to amd_mi355_X. (#29914) · 5f67361f
  Alexei-V-Ivanov-AMD authored Dec 02, 2025
```
Signed-off-by: Alexei V. Ivanov <alexei.ivanov@amd.com>
```
  5f67361f
02 Dec, 2025 21 commits

[Doc] Add allocate_slots parameter docs (#29777) · 5d91d2b2

maang-h authored Dec 03, 2025


Signed-off-by: maang <maang_h@163.com>
Signed-off-by: maang-h <55082429+maang-h@users.noreply.github.com>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>

5d91d2b2

[ROCm][CI] Fix test_cudagraph_mode.py Failure For AMD CI (#29808) · c014de1e
Micah Williamson authored Dec 02, 2025
```
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
```
c014de1e
[BUGFIX] Fix regex pattern for Mistral Tool Call (#29918) · 1b1e35aa
Julien Denize authored Dec 02, 2025
```
Signed-off-by: juliendenize <julien.denize@mistral.ai>
```
1b1e35aa
[BUGFIX] llama_4_scaling wrongly passed to DeepseekAttention (#29908) · 5e5646e2
Julien Denize authored Dec 02, 2025
```
Signed-off-by: juliendenize <julien.denize@mistral.ai>
```
5e5646e2

[Bugfix] fix --scheduling-policy=priority & n>1 crashes engine (#29764) · 0a9caca9

Chauncey authored Dec 03, 2025


Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Nick Hill <nhill@redhat.com>

0a9caca9

[Bugfix][EPLB] Prevent user-provided EPLB config from being overwritten with defaults (#29911) · e6f114ac
Sage Moore authored Dec 02, 2025
```
Signed-off-by: Sage Moore <sage@neuralmagic.com>
```
e6f114ac
Fix some more Transformers nightly tests (#29872) · 6fc5841d
Harry Mellor authored Dec 02, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
6fc5841d

Bump actions/setup-python from 6.0.0 to 6.1.0 (#29768) · 3ff5b53b

dependabot[bot] authored Dec 02, 2025


Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

3ff5b53b

[Perf] Avoid pageable HtoD transfer in MinTokensLogitsProcessor (#29826) · 1528e079
jthomson04 authored Dec 02, 2025
```
Signed-off-by: jthomson04 <jwillthomson19@gmail.com>
```
1528e079
[CI][ROCm][tests/v1/e2e] Fix multiprocessing launch for the test (#29123) · afb1e5b3
Divakar Verma authored Dec 02, 2025
```
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
```
afb1e5b3

Fix boolean nested params, add dict format support, and enhance plotting for... · 1c593e11

Copilot authored Dec 02, 2025

Fix boolean nested params, add dict format support, and enhance plotting for vllm bench sweep (#29025)
Signed-off-by: Luka Govedič <luka.govedic@gmail.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: ProExpertProg <11367180+ProExpertProg@users.noreply.github.com>
Co-authored-by: Luka Govedič <luka.govedic@gmail.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>

1c593e11

feat(model): Add BitsAndBytes quantization support for Qwen3-Omni-MoE (#29896) · a2b053dc
Navanit Dubey authored Dec 03, 2025
```
Signed-off-by: navanit-git <navanitdubey@gmail.com>
```
a2b053dc
[Attention][CUDAGraph] Remove CG padding from attention backends (#29352) · 1d93f116
Matthew Bonanni authored Dec 02, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
1d93f116
[CI/Build] Fixes missing runtime dependencies (#29822) · 2d613de9
Benjamin Bartels authored Dec 02, 2025
```
Signed-off-by: bbartels <benjamin@bartels.dev>
```
2d613de9
Update AMD-CI testing mirror (as of 2025-12-02) (#29898) · c77b9929
Alexei-V-Ivanov-AMD authored Dec 02, 2025
```
Signed-off-by: Alexei V. Ivanov <alexei.ivanov@amd.com>
```
c77b9929
[Chore]: Reorganize gguf utils funtions under `transformers_utils` (#29891) · 63b1da76
Isotr0py authored Dec 03, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
63b1da76
[responsesAPI][3] ResponsesParser to set up non harmony MCP (#29413) · 52cb349f
Andrew Xia authored Dec 02, 2025
```
Signed-off-by: Andrew Xia <axia@fb.com>
Co-authored-by: Andrew Xia <axia@fb.com>
```
52cb349f

[Bugfix] Fix incorrect channel order for idefics3 in edge case (#29881) · 0ec84221

Isotr0py authored Dec 03, 2025

Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

0ec84221

[examples] Resettle pooling examples. (#29365) · 2eb4fe91

wang.yuqi authored Dec 02, 2025

Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

2eb4fe91

[Bugfix] Fix DeepSeek R1 MTP weight loading (#29545) · 51c57b51

Matthew Bonanni authored Dec 02, 2025


Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Benjamin Chislett <bchislett@nvidia.com>

51c57b51

[Multimodal][Core] Optimize multimodal preprocessing cache by hashing image... · 60c3d413

ImaGoodFella authored Dec 02, 2025


[Multimodal][Core] Optimize multimodal preprocessing cache by hashing image bytes instead of pixel values (#29621)
Signed-off-by: Rahul Steiger <rasteiger@ethz.ch>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

60c3d413