Commits · 4e68cc9b6aa2b9cfe8d799c2b1cd156a01bca438 · OpenDAS / vllm_cscc

30 Oct, 2025 3 commits

[Model] Introduce Kimi Linear to vLLM (#27809) · 4e68cc9b

Zhiyuan Li authored Oct 30, 2025


Signed-off-by: lizhiyuan <lizhiyuan@moonshot.cn>
Signed-off-by: Zhiyuan Li <uniartisan2017@gmail.com>

4e68cc9b

[Frontend][Doc][5/N] Improve all pooling task | Polish encode (pooling) api & Document. (#25524) · 4464723f

wang.yuqi authored Oct 30, 2025

Signed-off-by: wang.yuqi <noooop@126.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>

4464723f

[BugFix][VL] Fix FA selection on Qwen2.5-VL (#27790) · e806178d
Zhewen Li authored Oct 30, 2025
```
Signed-off-by: zhewenli <zhewenli@meta.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
```
e806178d

29 Oct, 2025 5 commits

[Temp fix] Disable torch.compile for Qwen2.5 VL's VisionBlock temporarily. (#27760) · 48eb8eba

Chenheli Hua authored Oct 29, 2025


Signed-off-by: Chenheli Hua <huachenheli@outlook.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.io>

48eb8eba

[FIXBUG] Qwen3VL hallucinations without Contiguous on Torch.SDPA (#27744) · 7568a282
JartX authored Oct 29, 2025
```
Signed-off-by: JartX <sagformas@epdcenter.es>
Co-authored-by: Lukas Geiger <lukas.geiger94@gmail.com>
```
7568a282
Fix MiniMax-M2 rmsnorm precision and remove useless code (#27627) · d6704dd0
Roger Young authored Oct 29, 2025
```
Signed-off-by: xuebi <xuebi@minimaxi.com>
Co-authored-by: xuebi <xuebi@minimaxi.com>
```
d6704dd0

[perf] Enable concurrent execution of "shared_experts" and "selected_experts"... · 8df98c21

Jiangyun Zhu authored Oct 29, 2025


[perf] Enable concurrent execution of "shared_experts" and "selected_experts" in qwen3-next (#27578)
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>

8df98c21

[Model] Fix Qwen3VL and Qwen3Omni after torch.compile changes (#27705) · 0d8161b0

Lukas Geiger authored Oct 29, 2025


Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.io>

0d8161b0

28 Oct, 2025 2 commits

[Misc][qwen2_5_vl][torch.compile] Enable `supports_torch_compile` on generic... · 94666612

Lucas Kabela authored Oct 28, 2025


[Misc][qwen2_5_vl][torch.compile] Enable `supports_torch_compile` on generic nn.Module and demonstrate speedup on Qwen Vision model (#23207)
Signed-off-by: Lucas Kabela <lucaskabela@meta.com>
Signed-off-by: Lucas Kabela <lucasakabela@gmail.com>

94666612

[Hybrid] Add mamba_block_size to Engine Args (#27289) · 05181cc5
Asaf Joseph Gardin authored Oct 28, 2025
```
Signed-off-by: asafg <39553475+Josephasafg@users.noreply.github.com>
```
05181cc5

27 Oct, 2025 7 commits
- fixing mm placeholder replacement issue with gemma3 (#27538) · 23ad8205
  tingtinggithub authored Oct 27, 2025
```
Signed-off-by: tingtingtang1992 <streamttt@gmail.com>
```
  23ad8205
- [Model] Siglip2 Model Support (#27566) · 4f882be4
  Yu Jiaqi authored Oct 27, 2025
```
Signed-off-by: piood <2477084691@qq.com>
```
  4f882be4
- [Hybrid] Added supports_mamba_prefix_caching Protocol (#27339) · 92737542
  Asaf Joseph Gardin authored Oct 27, 2025
```
Signed-off-by: asafg <39553475+Josephasafg@users.noreply.github.com>
```
  92737542
- [Doc] Slight improvement to M2 and beyond (#27554) · 2d631d28
  Jee Jee Li authored Oct 27, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
```
  2d631d28
- [Model] Use merge_by_field_config for MM models (Qwen series) (#27546) · cbd5e07a
  Cyrus Leung authored Oct 27, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  cbd5e07a
- [Model][Bugfix] fix ernie45 moe 300B SharedFusedMoE output tuple (#27316) · 63b22e0d
  CSWYF3634076 authored Oct 27, 2025
```
Signed-off-by: wangyafeng <wangyafeng@baidu.com>
```
  63b22e0d
- Fix MiniMax-M2 copyright (#27537) · 5980604c
  Roger Young authored Oct 27, 2025
```
Signed-off-by: xuebi <xuebi@minimaxi.com>
Co-authored-by: xuebi <xuebi@minimaxi.com>
```
  5980604c
26 Oct, 2025 3 commits

[Model][MiniMax-M2] Support MiniMax-M2 Model (#27535) · 720af6ab
Roger Young authored Oct 27, 2025
```
Signed-off-by: xuebi <xuebi@minimaxi.com>
Co-authored-by: xuebi <xuebi@minimaxi.com>
```
720af6ab

[Chore]:Extract math and argparse utilities to separate modules (#27188) · 71b1c8b6

Yeshwanth N authored Oct 26, 2025


Signed-off-by: Yeshwanth Surya <yeshsurya@gmail.com>
Signed-off-by: Yeshwanth N <yeshsurya@gmail.com>
Signed-off-by: yeshsurya <yeshsurya@gmail.com>

71b1c8b6

[BUGFIX][ROCM] ViT FlashAttention on ROCm (no GFX9) and contiguous on qwen3vl... · 65d2cf95

JartX authored Oct 26, 2025


[BUGFIX][ROCM] ViT FlashAttention on ROCm (no GFX9) and contiguous on qwen3vl ROCm TORCH_SDPA (#27190)
Signed-off-by: JartX <sagformas@epdcenter.es>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>

65d2cf95

25 Oct, 2025 1 commit

[CI/Build] Refactor processing tests (#27470) · 66a168a1

Cyrus Leung authored Oct 26, 2025


Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>

66a168a1

24 Oct, 2025 5 commits

[Bugfix] Fix interns1-vit qk norm code path (#27480) · acc78aeb
Isotr0py authored Oct 25, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
acc78aeb

[MISC] `cudagraph_capture_sizes` related improvements (#26016) · 284cc922

fhl2000 authored Oct 24, 2025

Signed-off-by: fhl <2410591650@qq.com>
Signed-off-by: fhl2000 <63384265+fhl2000@users.noreply.github.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

284cc922

[MM][Bugfix] Replace `PatchEmbed`'s conv3d to linear layer (#27418) · 42efe609
Isotr0py authored Oct 24, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Roger Wang <hey@rogerw.io>
```
42efe609
Fix pooling adapters for Transformers backend (#27338) · 1f9460c4
Harry Mellor authored Oct 24, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
1f9460c4

Granite 4.0 quark quantization support (#26944) · 70022ffc

xiao-llm authored Oct 23, 2025


Signed-off-by: Xiao YU <Xiao.YU@xilinx.com>
Signed-off-by: Xiao Yu <xiao.yu.dc@outlook.com>
Co-authored-by: Xiao YU <Xiao.YU@xilinx.com>

70022ffc

23 Oct, 2025 7 commits

[Model] Siglip Embedding Support (#27324) · 0552cfb1
Yu Jiaqi authored Oct 24, 2025
```
Signed-off-by: piood <2477084691@qq.com>
```
0552cfb1
[Chore] Separate out `vllm.utils.platform_utils.py` (#27374) · ca76486a
Jonathan Chen authored Oct 23, 2025
```
Signed-off-by: Jonathan <chenleejonathan@gmail.com>
```
ca76486a

[Frontend][4/N] Improve all pooling task | Add plugin pooling task (#26973) · 3fa2c121

wang.yuqi authored Oct 23, 2025

Signed-off-by: wang.yuqi <noooop@126.com>
Signed-off-by: Christian Pinto <christian.pinto@ibm.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Christian Pinto <christian.pinto@ibm.com>

3fa2c121

[CI/Build] Remove unnecessary flags from test registry (#27353) · fe2016de
Cyrus Leung authored Oct 23, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
fe2016de

[Bugfix] Honor --mm_encoder_attn_backend when used (#27124) · 570c3e1c

Bradley D authored Oct 23, 2025


Co-authored-by: Bradley D <4551889+bradleyhd@users.noreply.github.com>
Co-authored-by: Roger Wang <hey@rogerw.io>

570c3e1c

[Model] Add MoE support for NemotronH (#25863) · 61089465
tomeras91 authored Oct 23, 2025
```
Signed-off-by: Tomer Asida <57313761+tomeras91@users.noreply.github.com>
```
61089465

[Bugfix] Fix deepseek-ocr multi-image inference and add... · 2566dca2

Isotr0py authored Oct 23, 2025


[Bugfix] Fix deepseek-ocr multi-image inference and add `merge_by_field_config=True` with tensor schema support (#27361)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>

2566dca2

22 Oct, 2025 4 commits
- [Model] Revert PR #26715: Restore custom PaliGemma and Gemma3-MM impl… (#27309) · e05a6754
  Luciano Martins authored Oct 22, 2025
```
Signed-off-by: Luciano Martins <lucianommartins@users.noreply.github.com>
Co-authored-by: Luciano Martins <lucianommartins@users.noreply.github.com>
```
  e05a6754
- [Bugfix] Fix HF format InternVL large variants video processing (#27330) · db6f28d8
  Isotr0py authored Oct 22, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  db6f28d8
- [Bugfix] Make `get_mrope_input_positions` instance methods (#27342) · 14e2f123
  Cyrus Leung authored Oct 22, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  14e2f123
- [Model] Upstream Deepseek-OCR model (#27247) · 675aa2ec
  Isotr0py authored Oct 22, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.io>
```
  675aa2ec
21 Oct, 2025 3 commits

[Deepseek v3.2] Remove extra logics in indexer (#26465) · 09a7e6f6

Lain authored Oct 21, 2025


Signed-off-by: Siyuan Fu <siyuanf@nvidia.com>
Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>
Signed-off-by: Lain <siyuanf@nvidia.com>
Co-authored-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

09a7e6f6

[Performance] Dual stream execution of "shared_experts" and "selected_experts"... · 344a0017

Alexander Matveev authored Oct 21, 2025


[Performance] Dual stream execution of "shared_experts" and "selected_experts" inside FusedMoE (#26440)
Signed-off-by: Alexander Matveev <amatveev@redhat.com>

344a0017

[Deepseek v3.2] Optimize top_k_per_row (#26763) · 80e94529
Daniel Cámpora authored Oct 21, 2025
```
Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>
```
80e94529