Commits · ba45bedfd15ab01af2be5ae28af03888f3683063 · OpenDAS / vllm_cscc · GitLab

30 Jan, 2026 9 commits
- [model] Add support for openPangu7B-VL (#32449) · ba45bedf
  hujiaxin0 authored Jan 30, 2026
```
Signed-off-by: hujiaxin <524446785@qq.com>
Signed-off-by: Emilie1001 <79921183+Emilie1001@users.noreply.github.com>
Co-authored-by: Emilie1001 <79921183+Emilie1001@users.noreply.github.com>
```
  ba45bedf
- Explicitly set `return_dict` for `apply_chat_template` (#33372) · 9432ed8c
  Harry Mellor authored Jan 30, 2026
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  9432ed8c
- [CI] Enable mypy import following for `vllm/spec_decode` (#33282) · 726d8972
  Lucas Kabela authored Jan 29, 2026
```
Signed-off-by: Lucas Kabela <lucaskabela@meta.com>
```
  726d8972
- Move decode context parallel validationn to `ParallelConfig` (#33239) · d334dd26
  Harry Mellor authored Jan 30, 2026
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  d334dd26
- [CI][AMD] Skip 4 GPUs testgroup ray tests (#33305) · 070c811d
  Ryan Rock authored Jan 29, 2026
```
Signed-off-by: Ryan Rock <ryan.rock@amd.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
```
  070c811d
- [Models] Refactor Kimi-K2.5 weight loading (#33346) · 8bfc8d56
  Isotr0py authored Jan 30, 2026
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  8bfc8d56
- [BugFix] Disable async scheduling for Mamba prefix caching (#33352) · ec51831a
  Harry Huang authored Jan 30, 2026
```
Signed-off-by: huanghaoyan.hhy <huanghaoyan.hhy@alibaba-inc.com>
```
  ec51831a
- Fix `tie_word_embeddings` for multimodal models in Transformers v5 (#33359) · 80b918f2
  Harry Mellor authored Jan 30, 2026
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  80b918f2
- [Model][Multimodal] Add explicit MusicFlamingo adapter (#32696) · c46b0cd0
  Wang Haoyu authored Jan 30, 2026
```
Signed-off-by: WangHaoyuuu <mailwhaoyu@gmail.com>
```
  c46b0cd0
29 Jan, 2026 31 commits
- [Docs] Adding links and intro to Speculators and LLM Compressor (#32849) · 13376576
  Aidan Reilly authored Jan 29, 2026
```
Signed-off-by: Aidan Reilly <aireilly@redhat.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  13376576
- [Bugfix] Enable Triton MoE for FP8 per-tensor dynamic (#33300) · bfb9bdaf
  Michael Goin authored Jan 29, 2026
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  bfb9bdaf
- [release] Minor fixes to release annotation and wheel upload (#33129) · 2284461d
  Kevin H. Luu authored Jan 29, 2026
```
Signed-off-by: khluu <khluu000@gmail.com>
```
  2284461d
- Add Triton fused MoE config for B200 (Nemotron Nano) (#32804) · 8e2a469b
  danisereb authored Jan 29, 2026
  
  8e2a469b
- [Bugfix][Kernel] Fix negative memory offset in GDN Triton kernel (#33326) · 23591e63
  CarstyYou authored Jan 30, 2026
```
Signed-off-by: CarstyYou <186021327+CarstyYou@users.noreply.github.com>
```
  23591e63
- [NVIDIA] [feat] Integrate flashinfer Trtllmgen bf16 moe (#32954) · 0493d897
  Linda authored Jan 29, 2026
```
Signed-off-by: Linda-Stadter <57756729+Linda-Stadter@users.noreply.github.com>
```
  0493d897
- [BUGFIX][XPU] fix memory check after XPU reuse GPU_worker (#33358) · 8c8ebeb9
  Chendi.Xue authored Jan 29, 2026
```
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
```
  8c8ebeb9
- [Chore] Move `MediaConnector` to `vllm.multimodal.media` (#33324) · 831453fc
  Cyrus Leung authored Jan 30, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  831453fc
- [ez] Delete torch25_custom_graph_pass (#33287) · 5a66c9cc
  Angela Yi authored Jan 29, 2026
```
Signed-off-by: angelayi <yiangela7@gmail.com>
```
  5a66c9cc
- [Bugfix] Fix broken GLM-OCR initialization (#33350) · 5e73e490
  Isotr0py authored Jan 29, 2026
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  5e73e490
- [Multimodal] Simplify MM input definitions (#33331) · c6e7404c
  Cyrus Leung authored Jan 29, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  c6e7404c
- [Backport] [Kimi-K2.5] Replace torch.cuda with current_platform for d… (#33320) · 17b17c06
  sthWrong authored Jan 29, 2026
  
  17b17c06
- [Intel GPU] refine xpu worker (#32894) · 8bb6271c
  Kunshang Ji authored Jan 29, 2026
```
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
```
  8bb6271c
- [Models] Qwen3-ASR (#33312) · 8b3f0a99
  Roger Wang authored Jan 29, 2026
```
Signed-off-by: Roger Wang <hey@rogerw.io>
```
  8b3f0a99
- [Bugfix][CPU] Fix thread num for shared memory communication (#33317) · 8311f083
  Li, Jiang authored Jan 29, 2026
```
Signed-off-by: jiang1.li <jiang1.li@intel.com>
Signed-off-by: Li, Jiang <bigpyj64@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  8311f083
- [Voxtral] Streaming example (#33042) · 40c35038
  Patrick von Platen authored Jan 29, 2026
```
Signed-off-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
```
  40c35038
- [Quantization][Refactor] use platform dict to choose kernel (#33130) · a5aa4d5c
  zofia authored Jan 29, 2026
```
Signed-off-by: Zhu, Zufang <zufang.zhu@intel.com>
Signed-off-by: zofia <110436990+zufangzhu@users.noreply.github.com>
```
  a5aa4d5c
- [Bug Fix] Handle variable-length tensors in MultiModalFlatField batching (#31751) · 615e8033
  andrii.pasternak authored Jan 29, 2026
```
Signed-off-by: Andrii Pasternak <andriipasternak31@gmail.com>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
```
  615e8033
- [BugFix] Async Eplb fix potential race condition (#32881) · d09135fb
  Ilya Markov authored Jan 29, 2026
```
Signed-off-by: ilmarkov <markovilya197@gmail.com>
```
  d09135fb
- [fix] tesdt mcp_tool_calling_streaming with a more complex math question (#32769) · 8688c3d4
  daniel-salib authored Jan 29, 2026
```
Signed-off-by: Daniel Salib <danielsalib@meta.com>
```
  8688c3d4
- [Chore] Remove `use_data_parallel` kwargs from ViT implementation (#33310) · 5400014d
  Isotr0py authored Jan 29, 2026
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  5400014d
- [Misc] Cleanup Kimi-K2.5's vision chunk modality entrypoints (#33157) · 3a92c6f3
  Isotr0py authored Jan 29, 2026
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  3a92c6f3
- Bugfix: Pass router logits dtype in nemotron shared experts (#32669) · e01ff5c0
  amirkl94 authored Jan 29, 2026
```
Signed-off-by: Amir Klein <203507526+amirkl94@users.noreply.github.com>
```
  e01ff5c0
- Make `mypy` opt-out instead of opt-in (#33205) · fb946a7f
  Harry Mellor authored Jan 29, 2026
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  fb946a7f
- [Misc] Remove missed `pad_for_cudagraph` (#33283) · a650ad15
  Lucas Wilkinson authored Jan 29, 2026
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
  a650ad15
- [Doc] Update outdated link to Ray documentation (#32660) · d697581a
  graftim authored Jan 29, 2026
```
Signed-off-by: graftim <38649219+graftim@users.noreply.github.com>
```
  d697581a
- Adding optional speculator tests for larger models (#32943) · 5eeba80c
  shanjiaz authored Jan 29, 2026
```
Signed-off-by: shanjiaz <zsjwpianpian@gmail.com>
```
  5eeba80c
- [PluggableLayer][2/N] Apply PluggableLayer to linear layers (#33152) · 08b1195e
  whx authored Jan 29, 2026
```
Signed-off-by: whx-sjtu <2952154980@qq.com>
```
  08b1195e
- support returning tokenids in responses api (#33212) · 3bba2edb
  cmunley1 authored Jan 29, 2026
```
Signed-off-by: Christian Munley <cmunley@nvidia.com>
```
  3bba2edb
- [BugFix] Fix EPLB fail for MoeFP4 model with Marlin backend (#33262) · 53fc1664
  Ilya Markov authored Jan 29, 2026
```
Signed-off-by: ilmarkov <markovilya197@gmail.com>
```
  53fc1664
- [Doc]: fixing multiple typos in diverse files (#33256) · 31b25f65
  Didier Durand authored Jan 29, 2026
```
Signed-off-by: Didier Durand <durand.didier@gmail.com>
Signed-off-by: Didier Durand <2927957+didier-durand@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  31b25f65