Commits · fc6acc88caac881a92d84bcef5bc734d67035786 · OpenDAS / vllm_cscc · GitLab

01 Dec, 2025 18 commits
- [Bugfix] Missing cached item in the MultiModalReceiverCache (#28525) · fc6acc88
  knlnguyen1802 authored Dec 02, 2025
```
Signed-off-by: knlnguyen1802 <knlnguyen1802@gmail.com>
Co-authored-by: Chenguang Zheng <645327136@qq.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
  fc6acc88
- [Hardware][AMD] Remove ROCm skip conditions for transformers backend tests (#29782) · d0985c5f
  BADAOUI Abdennacer authored Dec 01, 2025
```
Signed-off-by: badaoui <abdennacerbadaoui0@gmail.com>
```
  d0985c5f
- [Frontend] add 'verbose_json' and 'timestamp' feature on Whisper Transcription/Translation (#24209) · 092bb73b
  sangbumlikeagod authored Dec 02, 2025
```
Signed-off-by: sangbumlikeagod <oironese@naver.com>
Signed-off-by: sangbumlikeagod <98077576+sangbumlikeagod@users.noreply.github.com>
```
  092bb73b
- [Doc] Update description disable_any_whitespace (#29784) · 5d43f737
  FredericOdermatt authored Dec 01, 2025
```
Signed-off-by: Frederic Odermatt <frederic.odermatt@44ai.ch>
```
  5d43f737
- [CI] fix url-encoding behavior in nightly metadata generation (#29787) · 37593deb
  Shengqi Chen authored Dec 01, 2025
```
Signed-off-by: Shengqi Chen <harry-chen@outlook.com>
```
  37593deb
- [Doc] fix heading levels (#29783) · f5516039
  Liu Jinyi authored Dec 01, 2025
```
Signed-off-by: KKKZOZ <kkkzoz@qq.com>
```
  f5516039
- [CI] Renovation of nightly wheel build & generation (#29690) · 36db0a35
  Shengqi Chen authored Dec 01, 2025
```
Signed-off-by: Shengqi Chen <harry-chen@outlook.com>
```
  36db0a35
- [Bugfix] TypeError: 'NoneType' object is not callable (#29414) · 5cfa967e
  Marcin Ostrowski authored Dec 01, 2025
```
Signed-off-by: Marcin Ostrowski <marcinx.ostrowski@intel.com>
```
  5cfa967e
- [v1] Add real sliding window calculation to FlexAttention direct BlockMask building (#26015) · b95db244
  Isotr0py authored Dec 01, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: baonudesifeizhai <baonudesifeizhai@gmail.com>
Co-authored-by: baonudesifeizhai <baonudesifeizhai@gmail.com>
```
  b95db244
- [multimodal][test] Reduce memory utilization for test_siglip to avoid OOM (#29504) · ad9d656b
  Zhengxu Chen authored Dec 01, 2025
```
Signed-off-by: zhxchen17 <zhxchen17@fb.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
  ad9d656b
- [XPU] Fix AWQ skipped layer detection in IPEX quantization (#29774) · f37e8938
  Fanli Lin authored Dec 01, 2025
```
Signed-off-by: Fanli Lin <fanli.lin@intel.com>
```
  f37e8938
- [Misc] Unify tokenizer registration (#29767) · f0a28bf6
  Cyrus Leung authored Dec 01, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  f0a28bf6
- [crashfix] Eagle + multimodal can crash on mm cache miss (#29750) · 86e178f7
  Mickaël Seznec authored Dec 01, 2025
```
Signed-off-by: Mickael Seznec <mickael@mistral.ai>
Co-authored-by: Roger Wang <hey@rogerw.io>
```
  86e178f7
- [Frontend] Add tool filtering support to ToolServer (#29224) · 014ece97
  daniel-salib authored Dec 01, 2025
```
Signed-off-by: Daniel Salib <danielsalib@meta.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
```
  014ece97
- [Frontend] Resettle pooling entrypoints (#29634) · 62de4f42
  wang.yuqi authored Dec 01, 2025
```
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
```
  62de4f42
- [CI] Skip paddleocr_vl for transformer 4.57.3 (#29758) · 83805a60
  Huamin Li authored Nov 30, 2025
```
Signed-off-by: Huamin Li <3ericli@gmail.com>
```
  83805a60
- Make PyTorch profiler gzip and CUDA time dump configurable (#29568) · 1ab8fc81
  Yifei Zhang authored Dec 01, 2025
```
Signed-off-by: Yifei Zhang <yifei.zhang1992@outlook.com>
```
  1ab8fc81
- [MoE] CuteDSL MoE with Nvfp4 DeepEP dispatch (#27141) · f72a817b
  Shu Wang authored Nov 30, 2025
```
Signed-off-by: Shu Wang <shuw@nvidia.com>
Signed-off-by: Shu Wang. <shuw@nvidia.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: root <root@umbriel-b200-017.ipp4a1.colossus.nvidia.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
  f72a817b
30 Nov, 2025 13 commits
- [Model Runner V2] Use packed mask for prompt bin counts (#29756) · ec38a736
  Woosuk Kwon authored Nov 30, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  ec38a736
- [Misc]Remove redundant hidden_size property in ModelConfig (#29749) · 21c26279
  Xingyu Liu authored Dec 01, 2025
```
Signed-off-by: Xingyu Liu <charlotteliu12x@gmail.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  21c26279
- [Feat] Support non-gated activations in NVFP4 modelopt path (#29004) · 39d28108
  Omer Ullman Argov authored Nov 30, 2025
  
  39d28108
- Fix RoPE failures in Transformers nightly (#29700) · cd719de5
  Harry Mellor authored Nov 30, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  cd719de5
- [ROCm][Attention] Sliding window support for `AiterFlashAttentionBackend` (#29234) · 8c363ed6
  Pleaplusone authored Nov 30, 2025
```
Signed-off-by: ganyi <ygan@amd.com>
```
  8c363ed6
- [Core] Enable `inputs_embeds_size` separate from `hidden_size` (#29741) · 64bc09ba
  Cyrus Leung authored Nov 30, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  64bc09ba
- [Bugfix] Fix mismatched nvfp4 gemm output shape (#29742) · 47539cfd
  Isotr0py authored Nov 30, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  47539cfd
- [Misc] Update `TokenizerLike` interface and move `get_cached_tokenizer` (#29730) · 2afcec4d
  Cyrus Leung authored Nov 30, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  2afcec4d
- [Doc]: Fix typo in fused_moe layer (#29731) · 9381b5cd
  朝 authored Nov 30, 2025
```
Signed-off-by: BowTen <bowten@qq.com>
```
  9381b5cd
- [Bugfix][sleepmode][fp8 kv cache]: Fix FP8 KV cache + sleep(level=2) gibberish output (#28783) · 66b58402
  Vensen authored Nov 30, 2025
```
Signed-off-by: vensen <vensenmu@gmail.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
```
  66b58402
- Fix AttributeError about _use_fi_prefill (#29734) · 82c795d6
  Huamin Li authored Nov 29, 2025
```
Signed-off-by: Huamin Li <3ericli@gmail.com>
```
  82c795d6
- [Quantization] Enable compressed-tensors AWQ for Turing GPU (#29732) · e1464c3a
  Isotr0py authored Nov 30, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  e1464c3a
- [LoRA] Support FusedMoE LoRA Triton kernel for mxfp4 (#29708) · a491b091
  Xin Yang authored Nov 29, 2025
```
Signed-off-by: Xin Yang <xyangx@amazon.com>
Signed-off-by: Xin Yang <105740670+xyang16@users.noreply.github.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
```
  a491b091
29 Nov, 2025 9 commits
- [Bugfix] Revert test_tokenization.py (#29729) · b9d0504a
  Jee Jee Li authored Nov 30, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  b9d0504a
- [Kernel][Quantization] add w4a8 support for marlin kernel (#24722) · 1656ad37
  Jinzhen Lin authored Nov 29, 2025
```
Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Signed-off-by: Jinzhen Lin <linjinzhen@hotmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Michael Goin <mgoin@redhat.com>
```
  1656ad37
- [Chore] Move `detokenizer_utils` to `vllm/tokenizers` (#29727) · fa59fe41
  Cyrus Leung authored Nov 29, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  fa59fe41
- [Chore] Enable passing `tokenizer=None` into MM processor (#29724) · fe3398fa
  Cyrus Leung authored Nov 29, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  fe3398fa
- hfrunner.classify should return list[list[float]] not list[str] (#29671) · ad7f714d
  Chukwuma Nwaugha authored Nov 29, 2025
```
Signed-off-by: Chukwuma Nwaugha <nwaughac@gmail.com>
```
  ad7f714d
- [Doc]: fix code block rendering (#29728) · f4341f45
  dublc authored Nov 29, 2025
```
Signed-off-by: dublc <jdublc0x@gmail.com>
```
  f4341f45
- [Misc] Refactor tokenizer interface (#29693) · 34a98427
  Cyrus Leung authored Nov 29, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  34a98427
- [Model Runner V2] Fuse penalties and temperature into single kernel (#29720) · f223ed41
  Woosuk Kwon authored Nov 29, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  f223ed41
- [Doc]: fixing typos in various files. (#29717) · 04a797cd
  Didier Durand authored Nov 29, 2025
```
Signed-off-by: Didier Durand <durand.didier@gmail.com>
```
  04a797cd