Commits · 296839a1b07e63daecca67bfce80375614b5b863 · OpenDAS / vllm_cscc · GitLab

18 Mar, 2026 4 commits
- [Log] Reduce duplicate log (#37313) · c373b5c0
  Wentao Ye authored Mar 18, 2026
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  c373b5c0
- [2/3] Refactor InternVL-based processors (#37324) · 99267c23
  Cyrus Leung authored Mar 18, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  99267c23
- [Model] Enable LoRA support for tower and connector in H2OVL (#31696) · cef1f302
  Shwetha Poojary authored Mar 18, 2026
```
Signed-off-by: shwetha-s-poojary <shwetha.s-poojary@ibm.com>
```
  cef1f302
- [Perf] Enable dual stream execution of input projection for Qwen3 (#36795) · f1740006
  Xin Yang authored Mar 17, 2026
```
Signed-off-by: Xin Yang <xyangx@amazon.com>
```
  f1740006
17 Mar, 2026 8 commits
- [Model] Add ColQwen3.5 4.5B support (#36887) · c0745a85
  Athrael Soju authored Mar 17, 2026
```
Signed-off-by: Athrael Soju <athrael.soju@gmail.com>
Co-authored-by: wang.yuqi <yuqi.wang@daocloud.io>
```
  c0745a85
- [Models] Cohere ASR (#35809) · b5ca9c35
  Ekagra Ranjan authored Mar 17, 2026
```
Signed-off-by: Ekagra Ranjan <3116519+ekagra-ranjan@users.noreply.github.com>
```
  b5ca9c35
- [Model] Remove unused `handle_oov_mm_token` (#37321) · 51f0acda
  Cyrus Leung authored Mar 18, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  51f0acda
- [Bugfix] Standardize custom HF Processor init (#37289) · c781fbba
  Cyrus Leung authored Mar 17, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  c781fbba
- [`UltraVox`] Fix output type (#37224) · 2ff0ad96
  Anton Vlasjuk authored Mar 17, 2026
```
Signed-off-by: vasqu <antonprogamer@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  2ff0ad96
- [1/2] Move InternVL-based processors (#37260) · f3403243
  Cyrus Leung authored Mar 17, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  f3403243
- [Feature]: Support for multiple embedding types in a single inference call (#35829) · 9c7cab5e
  Augusto Yao authored Mar 17, 2026
```
Signed-off-by: augusto.yjh <augusto.yjh@antgroup.com>
```
  9c7cab5e
- [Bugfix] Fix loading Music Flamingo (#35535) · 20b14095
  Nick Cao authored Mar 17, 2026
```
Signed-off-by: Nick Cao <ncao@redhat.com>
```
  20b14095
16 Mar, 2026 9 commits
- Fix EagleMistralLarge3Model initialization (#37232) · 7961486a
  Julien Denize authored Mar 16, 2026
```
Signed-off-by: juliendenize <julien.denize@mistral.ai>
```
  7961486a
- [torch.compile][BE] Modify cudagraph callable to check for is_forward_context_set (#36288) · 714c6e0e
  Lucas Kabela authored Mar 16, 2026
```
Signed-off-by: Lucas Kabela <lucaskabela@meta.com>
```
  714c6e0e
- Remove unused EVS functions in qwen3_vl.py (#37183) · 43a73f85
  Tianyu Guo authored Mar 16, 2026
```
Signed-off-by: Tianyu Guo <guoty9@mail2.sysu.edu.cn>
```
  43a73f85
- [Models][Qwen3 ViT] Keep `max_seqlen` on CPU to prevent D2H sync (#37139) · f9e6db30
  Lukas Geiger authored Mar 16, 2026
```
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  f9e6db30
- Fix text only inputs for MRoPE models with the Transformers modelling backend (#37055) · ad041c79
  Harry Mellor authored Mar 16, 2026
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  ad041c79
- Fix pipeline parallel with multimodal models with the Transformers modelling backend (#37057) · 122f75d9
  Harry Mellor authored Mar 16, 2026
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  122f75d9
- [FlashInfer] Revert block_size 16 + head_size 256 workaround on Blackwell (#36987) · 8374387b
  Vadim Gimpelson authored Mar 16, 2026
```
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
```
  8374387b
- [Bugfix] Fix Qwen2.5-Omni/Qwen3-Omni use_audio_in_video with multi-video inputs (#37147) · 912fbe95
  Isotr0py authored Mar 16, 2026
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  912fbe95
- [Model] Add HyperCLOVAX-SEED-Think-14B language model support (#37107) · 2390d442
  bigshanedogg authored Mar 16, 2026
```
Signed-off-by: bigshanedogg <bigshane319@gmail.com>
```
  2390d442
15 Mar, 2026 1 commit
- [GDN] add a config for gdn kernel selection (#36647) · 697e4ff3
  Jiangyun Zhu authored Mar 16, 2026
```
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
```
  697e4ff3
14 Mar, 2026 2 commits
- [Misc] Clean up Kimi-audio whisper encoder loading (#36903) · a8e8d62d
  Isotr0py authored Mar 14, 2026
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  a8e8d62d
- Enable loading of fused expert weights in the Transformers modelling backend (#36997) · ffa5d74f
  Harry Mellor authored Mar 14, 2026
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  ffa5d74f
13 Mar, 2026 8 commits
- [Feat][Bugfix] Enable additional dimension for Flashinfer MLA and fix routing dtype (#36931) · 367cf5cd
  Dimitrios Bariamis authored Mar 14, 2026
```
Signed-off-by: Dimitrios Bariamis <12195802+dbari@users.noreply.github.com>
Co-authored-by: Dimitrios Bariamis <12195802+dbari@users.noreply.github.com>
```
  367cf5cd
- [Refactor] Consolidate SupportsEagle (#36063) · 8b346309
  Benjamin Chislett authored Mar 13, 2026
```
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
```
  8b346309
- Use Transformers v5 `WeightRenaming` for Transformers modeling backend (#31545) · 0005d2a3
  Harry Mellor authored Mar 13, 2026
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  0005d2a3
- [Bugfix] Fix Qwen2.5-omni/Qwen3-omni mm_processor cache for audio_in_video request (#36800) · abf61aaa
  Isotr0py authored Mar 14, 2026
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  abf61aaa
- [Bugfix] fix paddleocr crash on some image shape (#36959) · 4508532f
  bigmoyan authored Mar 13, 2026
```
Signed-off-by: wangzhengtao <wangzhengtao@msh.team>
Signed-off-by: bigmoyan <moyan_work@foxmail.com>
Co-authored-by: wangzhengtao <wangzhengtao@msh.team>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  4508532f
- [Bugfix] Fix FlashInfer GDN warmup ValueError on SM90 GPUs (#36876) · f296a196
  Thomas Parnell authored Mar 13, 2026
  
  f296a196
- [Model] Add support for BERT-like Chinese ERNIE pooling models (#36385) · 1ce13cf9
  whyiug authored Mar 13, 2026
```
Signed-off-by: whyiug <whyiug@hotmail.com>
Co-authored-by: wang.yuqi <yuqi.wang@daocloud.io>
```
  1ce13cf9
- [Model] Add ColPali late interaction model for multi-modal retrieval (#36818) · 10f08ded
  Nikita authored Mar 13, 2026
```
Signed-off-by: Nikita Sukharev <kaonael@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
  10f08ded
12 Mar, 2026 5 commits
- [Speculative Decoding] Add `norm_before_fc` for gpt-oss draft models (#36545) · 87985077
  Shubhra Pandit authored Mar 12, 2026
```
Signed-off-by: Shubhra Pandit <shubhra.pandit@gmail.com>
Co-authored-by: Benjamin Chislett <chislett.ben@gmail.com>
Co-authored-by: Benjamin Chislett <bchislett@nvidia.com>
```
  87985077
- [Perf] add packed recurrent fast path for decode (#36596) · 9e19f833
  caozuoba authored Mar 12, 2026
```
Signed-off-by: hdj <1293066020@qq.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
```
  9e19f833
- [MM][OOT] Support CPU `seq_lens` for OOT MMEncoderAttention kernels (#36605) · f0d3658c
  Shanshan Shen authored Mar 12, 2026
```
Signed-off-by: shen-shanshan <467638484@qq.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  f0d3658c
- [Bugfix] Warm up Triton autotuner for GDN layers during V1 profiling (#36599) · 3e64fe4a
  Xu Jinyang authored Mar 12, 2026
```
Signed-off-by: AuYang <459461160@qq.com>
```
  3e64fe4a
- [Bugfix][Model] Fix DeepSeek-OCR TensorSchema crash on empty images_crop (#36670) · 00726c74
  István Ketykó authored Mar 12, 2026
```
Signed-off-by: István Ketykó <istvan.ketyko@gmail.com>
```
  00726c74
11 Mar, 2026 3 commits
- Make Gemma and Gemma 2 accept `inputs_embeds` like Gemma 3 (#36787) · 65986db6
  Harry Mellor authored Mar 11, 2026
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  65986db6
- fix: align lfm2 thumbnail token counting with HF (#36707) · 741f4e04
  tianshu-Michael-yu authored Mar 11, 2026
  
  741f4e04
- [Misc] Clean up renderers (#36770) · 196802df
  Cyrus Leung authored Mar 12, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  196802df