Commits · 05972ea7e5f81250cc4ceaae8a174cfffe7755ac · OpenDAS / vllm_cscc

26 Feb, 2026 6 commits
- [Refactor] Remove dead or duplicate func utils or variables (#35318) · 05972ea7
  Wentao Ye authored Feb 26, 2026
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  05972ea7
- [Model] Add nvidia/llama-nemotron-embed-vl-1b-v2 multimodal embedding model (#35297) · 111d8690
  Jakub Zakrzewski authored Feb 26, 2026
```
Signed-off-by: Jakub Zakrzewski <jzakrzewski@nvidia.com>
```
  111d8690
- [Misc] Standardize handling of `mm_processor_kwargs.size` (#35284) · 845ee348
  Cyrus Leung authored Feb 26, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  845ee348
- [Bugfix] Fix Qwen2.5-Omni and Qwen3-Omni mixed-modality embed regression (#35368) · c0615a29
  Yueqian Lin authored Feb 26, 2026
```
Signed-off-by: linyueqian <linyueqian@outlook.com>
```
  c0615a29
- [Model] Ring 2.5 (#35102) · ab87f852
  Jiangyun Zhu authored Feb 26, 2026
```
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
```
  ab87f852
- [offloader] v2: Hide weight onloading latency via prefetching (#29941) · 6831650c
  Ming Yang authored Feb 25, 2026
```
Signed-off-by: Ming Yang <minos.future@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
  6831650c
24 Feb, 2026 5 commits

[Model][Spec Decode] Nemotron-H MTP and Mamba Speculative Decoding Support (#33726) · f5972a87

Benjamin Chislett authored Feb 24, 2026


Signed-off-by: Shahar Mor <smor@nvidia.com>
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Shahar Mor <smor@nvidia.com>
Co-authored-by: Roi Koren <roik@nvidia.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>

f5972a87

Remove `padding_index` from models that don't use it for better Transformers... · c38b8d5a

Harry Mellor authored Feb 24, 2026


Remove `padding_index` from models that don't use it for better Transformers v5 compatibility (#35189)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

c38b8d5a

[Feature] Add LoRA tower/connector support for Llama 4 Vision (mllama4) (#35147) · 012dee92
Dor Huri authored Feb 24, 2026
```
Signed-off-by: dorhuri123 <dor.huri1@live.biu.ac.il>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
```
012dee92

Make voxtral compile friendly (#33959) · f1c66454

Tugsbayasgalan Manlaibaatar authored Feb 24, 2026


Signed-off-by: Tugsbayasgalan Manlaibaatar <tmanlaibaatar@fb.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>

f1c66454

[BUGFIX][Qwen3.5] Hardcode `mlp.gate` as not quantizable (#35156) · 33a0d43c
Vadim Gimpelson authored Feb 24, 2026
```
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
```
33a0d43c

23 Feb, 2026 7 commits
- [Refactor] Decouple TimingContext from InputProcessingContext (#35083) · 39264545
  Cyrus Leung authored Feb 23, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  39264545
- [Llama4,CI] Bring back Llama-4 bug fixes, and also fix Maverick tests (#35033) · 1e8438a8
  Eldar Kurtić authored Feb 23, 2026
```
Signed-off-by: Eldar Kurtic <you@example.com>
Co-authored-by: Eldar Kurtic <you@example.com>
```
  1e8438a8
- [ModelBash][DSV3] Add TRTLLM DSV3 Router GEMM kernel (6% B1 Speedup) (#34302) · 8435b2e0
  Robert Shaw authored Feb 23, 2026
```
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
```
  8435b2e0
- [Refactor] Remove dead private func `_fp8_perm` and `_extract_mask_for_item` (#35068) · 7f40e9e5
  Wentao Ye authored Feb 23, 2026
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  7f40e9e5
- Fix pipeline parallel with embed scaling in the Transformers modelling backend (#35094) · 103e614b
  Harry Mellor authored Feb 23, 2026
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  103e614b
- fix: Apply embedding_multiplier to inputs_embeds (#34813) · e631f8e7
  Gabe Goodhart authored Feb 23, 2026
```
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
  e631f8e7
- [Refactor] Simplify dummy data generation (#35025) · 987506bc
  Cyrus Leung authored Feb 23, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  987506bc
22 Feb, 2026 3 commits

[Spec Decode] Reduce TP communication for speculative decoding draft token generation (#34049) · 2bcf71b9
qizixi authored Feb 22, 2026
```
Signed-off-by: qizixi <qizixi@meta.com>
Co-authored-by: Lu Fang <30275821+houseroad@users.noreply.github.com>
```
2bcf71b9

[Model] Add NVFP4 quantization support for Step3.5-Flash (#34478) · b7892a3b

tacos8me authored Feb 22, 2026


Signed-off-by: tacos8me <ian@cloudhabit.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>

b7892a3b

[New Model] Add ColModernVBERT (#34558) · 970861ac

Athrael Soju authored Feb 22, 2026


Signed-off-by: Athrael Soju <athrael.soju@gmail.com>
Signed-off-by: athrael-soju <athrael-soju@users.noreply.github.com>

970861ac

21 Feb, 2026 4 commits

[Frontend] Add automatic language detection for Whisper transcription (#34342) · 98b0205c

Roman authored Feb 21, 2026


Signed-off-by: space_check <roman.vuskov@rwth-aachen.de>
Signed-off-by: Roman <45857014+spacecheck@users.noreply.github.com>
Co-authored-by: Nicolò Lucchesi <nicolo.lucchesi@gmail.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>

98b0205c

[Frontend] Support multimodal inputs for late-interaction scoring (ColQwen3) +... · 5719a4e4

Kata Coder authored Feb 21, 2026


[Frontend] Support multimodal inputs for late-interaction scoring (ColQwen3) + NewModel: nvidia/nemotron-colembed (#34574)
Signed-off-by: craftsangjae <craftsangjae@gmail.com>

5719a4e4

[Realtime] Add Qwen3-ASR realtime streaming support (#34613) · 11be2c74

pougetat authored Feb 20, 2026


Signed-off-by: Thomas Pouget-Abadie <thomaspou@microsoft.com>
Co-authored-by: Thomas Pouget-Abadie <thomaspou@microsoft.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>

11be2c74

Revert "[Llama4,Quantization] Simplify and generalize logic for Q/K... · 0e22cd61
Lucas Wilkinson authored Feb 20, 2026
```
Revert "[Llama4,Quantization] Simplify and generalize logic for Q/K permutations in quantized self-attn layers " (#34997)
```
0e22cd61

20 Feb, 2026 2 commits

Bump Flashinfer Version and Re-enable DeepSeek NVFP4 AR+Norm Fusion (#34899) · ea5f903f
Wei Zhao authored Feb 20, 2026
```
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
ea5f903f

[Models] LFM2: Support LoRA (#34921) · ea37530b

tianshu-Michael-yu authored Feb 19, 2026


Co-authored-by: Piotr Mazurek <piotr635@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

ea37530b

19 Feb, 2026 9 commits
- [Refactor] Deprecate `head_first` for `chunk_gated_delta_rule` (#34263) · c683d11c
  Wentao Ye authored Feb 19, 2026
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  c683d11c
- Revert "[NemotronH] Do not force router to run in fp32 (#34582)" (#34808) · 3eff45d7
  roikoren755 authored Feb 19, 2026
```
Signed-off-by: Roi Koren <roik@nvidia.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
  3eff45d7
- [Model Bash][DeepSeekR1] Remove Shared Expert Clone (#34344) · 4685a630
  Robert Shaw authored Feb 19, 2026
```
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
```
  4685a630
- [Llama4,Quantization] Simplify and generalize logic for Q/K permutations in... · ee1d25f1
  Eldar Kurtić authored Feb 19, 2026
```
[Llama4,Quantization] Simplify and generalize logic for Q/K permutations in quantized self-attn layers  (#34471)
Signed-off-by: Your Name <you@example.com>
Co-authored-by: Your Name <you@example.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
```
  ee1d25f1
- [Bugfix] Qwen3.5 kv-scale weight remapping (#34719) · 6fff24f3
  Linda authored Feb 19, 2026
```
Signed-off-by: Linda-Stadter <57756729+Linda-Stadter@users.noreply.github.com>
```
  6fff24f3
- [Voxtral Realtime] Fix engine crash on empty multimodal embeddings (#34862) · f75b61a9
  Tal Nir authored Feb 19, 2026
```
Signed-off-by: Tal Nir <tal@nervexneurotech.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
```
  f75b61a9
- [Bug] Fix DeepSeek V3 weight loading caused by incorrect prefix (#34876) · 7f51e938
  Wei Zhao authored Feb 19, 2026
```
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
```
  7f51e938
- [Bugfix] Add Quant Config to Llava Next Projector (#34847) · 4611af16
  Alex Brooks authored Feb 19, 2026
```
Signed-off-by: Alex Brooks <albrooks@redhat.com>
```
  4611af16
- fix(docs): fix typos in comments and docstrings (#34836) · ad5aa6bd
  Manrique Vargas authored Feb 19, 2026
```
Signed-off-by: machov <mv1742@nyu.edu>
```
  ad5aa6bd
18 Feb, 2026 4 commits
- [Bugfix] Redo Qwen3.5/Qwen3-Next GDN projector fusion (#34697) · c0bd8b13
  Isotr0py authored Feb 19, 2026
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: JJJYmmm <92386084+JJJYmmm@users.noreply.github.com>
```
  c0bd8b13
- [Model Bash] DeepSeek R1 BF16 Min Latency QKV A GEMM (0.5% E2E Speedup) (#34758) · 6874638b
  Robert Shaw authored Feb 18, 2026
```
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
```
  6874638b
- [Bugfix] Fix prefix creation for Qwen3.5 (#34723) · 909b1471
  Michael Goin authored Feb 18, 2026
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  909b1471
- [Renderer] Move MM Hash parsing into Renderer (#34711) · a0d8d944
  Cyrus Leung authored Feb 18, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  a0d8d944