Commits · 11be2c74dc1eb08aaaeb260f84a31c2b36bbd454 · OpenDAS / vllm_cscc

21 Feb, 2026 2 commits

[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
17 Feb, 2026 2 commits
- [Renderer] Move InputPreprocessor into Renderer (2/2) (#34560) · 574fe752
  Cyrus Leung authored Feb 17, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  574fe752
- Revert "[Models] Fuse Qwen3.5 GDN's qkvz_proj and ba_proj" (#34683) · 1d65283e
  Jiangyun Zhu authored Feb 17, 2026
  
  1d65283e
16 Feb, 2026 5 commits
- [NemotronH] Do not force router to run in fp32 (#34582) · 3b30e615
  roikoren755 authored Feb 16, 2026
```
Signed-off-by: Roi Koren <roik@nvidia.com>
```
  3b30e615
- [ROCm][CI] Fix plugins test group; updating terratorch and dependencies (#34589) · 03a8770a
  Andreas Karatzas authored Feb 16, 2026
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  03a8770a
- [Models] Fuse Qwen3.5 GDN's qkvz_proj and ba_proj (#34492) · 3bb4e431
  Isotr0py authored Feb 16, 2026
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  3bb4e431
- [Renderer] Move InputPreprocessor into Renderer (1.5/2) (#34598) · ec17bdd8
  Cyrus Leung authored Feb 16, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  ec17bdd8
- [CI/Build] Enable tests for recent day-0 new models (#34585) · 91ac5d9b
  Isotr0py authored Feb 16, 2026
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  91ac5d9b
15 Feb, 2026 2 commits

[torch.compile] Disable ar-rms fusion for ds3-fp4 & DP, fix CI test (#34392) · 23d825ab

Luka Govedič authored Feb 15, 2026

Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

23d825ab

[MM Encoder] Add Triton ViT attention backend (#32183) · 71cd8926
Isotr0py authored Feb 15, 2026
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
71cd8926

14 Feb, 2026 4 commits
- [Renderer] Move InputPreprocessor into Renderer (1/2) (#34510) · 73391a1b
  Cyrus Leung authored Feb 15, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
```
  73391a1b
- [new model] add COLQwen3 code & Inference (#34398) · d1ea65d0
  Kata Coder authored Feb 14, 2026
```
Signed-off-by: craftsangjae <craftsangjae@gmail.com>
Signed-off-by: katacoder <craftsangjae@gmail.com>
```
  d1ea65d0
- [CI] Heavy refactoring of Voxtral multimodal audio model tests (#34294) · de42abb3
  Andreas Karatzas authored Feb 13, 2026
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  de42abb3
- [Feature][Perf] Support Selective CPU Weight Offloading (#34535) · b37b6797
  Wei Zhao authored Feb 13, 2026
```
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
```
  b37b6797
13 Feb, 2026 10 commits
- [Hybrid] Enable spec decoding in mamba cache align mode (#33705) · c027541e
  Harry Huang authored Feb 14, 2026
```
Signed-off-by: huanghaoyan.hhy <huanghaoyan.hhy@alibaba-inc.com>
```
  c027541e
- [Feature] Support CPU Offloading without Pytorch Pinned Memory that leads to... · 59d53066
  Wei Zhao authored Feb 13, 2026
```
[Feature] Support CPU Offloading without Pytorch Pinned Memory that leads to doubled allocation (#32993)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
  59d53066
- [Bugfix] Add quant_config in ViT of Kimi-K2.5 (#34501) · 4a9952ec
  LoganJane authored Feb 14, 2026
```
Signed-off-by: LoganJane <LoganJane73@hotmail.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  4a9952ec
- [Misc] Port Qwen3.5 Configs (#34512) · 5885e330
  Roger Wang authored Feb 13, 2026
```
Signed-off-by: Roger Wang <hey@rogerw.io>
```
  5885e330
- Extend ColBERT support to non-standard BERT backbones (#34170) · 071d863e
  Ilya Boytsov authored Feb 13, 2026
```
Signed-off-by: Ilya Boytsov <ilya.boytsov@aleph-alpha.com>
```
  071d863e
- [New Model] support new model ovis2.6 (#34426) · bcf0731a
  myselvess authored Feb 13, 2026
```
Signed-off-by: myselvess <23743269+myselvess@users.noreply.github.com>
```
  bcf0731a
- [Bugfix] Fix mamba state dtype setting for Qwen3-Next and Qwen3.5 (#34489) · eea3024f
  Roger Wang authored Feb 12, 2026
```
Signed-off-by: Roger Wang <hey@rogerw.io>
```
  eea3024f
- [Bugfix] Fix encoder cache underestimation for GLM-4V/GLM-OCR single image (#34483) · dcf6ee85
  haosdent authored Feb 13, 2026
```
Signed-off-by: haosdent <haosdent@gmail.com>
```
  dcf6ee85
- [Bugfix] Standardize getting number of image patches/tokens (#34358) · 372b2e76
  Cyrus Leung authored Feb 13, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  372b2e76
- [Bugfix] Delete unused redundant code in Kimi-K2.5 (#34427) · 62788f99
  LoganJane authored Feb 13, 2026
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  62788f99