Commits · 33bcd3dc3bf4d581c051400c8d9bb9433d2c87af · OpenDAS / vllm_cscc

10 Feb, 2026 3 commits
- [Misc] Introduce ec_both role EC (encoder cache) connector (#34182) · 33bcd3dc
  Qi Wang authored Feb 10, 2026
```
Signed-off-by: Qi Wang <qiwa@nvidia.com>
```
  33bcd3dc
- [Misc] allow specify is_mm_prefix_lm in hf_config (#34215) · 94de8715
  Phúc H. Lê Khắc authored Feb 10, 2026
  
  94de8715
- [Doc] Update usage of `--limit-mm-per-prompt` (#34148) · 25e48a3a
  Cyrus Leung authored Feb 10, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  25e48a3a
09 Feb, 2026 3 commits

[UX] Add `--language-model-only` for hybrid models (#34120) · 64a9c252
Roger Wang authored Feb 09, 2026
```
Signed-off-by: Roger Wang <hey@rogerw.io>
```
64a9c252

[MODEL] Adding Support for Qwen3.5 Models (#34110) · 9562912c

JJJYmmm authored Feb 09, 2026


Signed-off-by: JJJYmmm <1650675829@qq.com>
Signed-off-by: JJJYmmm <92386084+JJJYmmm@users.noreply.github.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: wulipc <wulipc@users.noreply.github.com>
Co-authored-by: ywang96 <ywang96@users.noreply.github.com>
Co-authored-by: Isotr0py <Isotr0py@users.noreply.github.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Roger Wang <hey@rogerw.io>

9562912c

[Model] GLM adaptation (#34124) · 978a37c8
Jee Jee Li authored Feb 09, 2026

978a37c8

08 Feb, 2026 3 commits

Add support for ModelOpt MXFP8 dense models (#33786) · 084aa19f
danisereb authored Feb 08, 2026
```
Signed-off-by: Daniel Serebrenik <daserebrenik@nvidia.com>
```
084aa19f
[torch.compile] Add an option to force-enable the MOE cold start optimization (#33735) · 4df841fe
Richard Zou authored Feb 08, 2026
```
Signed-off-by: Richard Zou <zou3519@gmail.com>
```
4df841fe

Add embedding input functionality for disabled modalities [remake] (#32493) · c4df59ad

Reagan Lee authored Feb 08, 2026

Signed-off-by: Reagan Lee <“reaganjlee@gmail.com”>
Signed-off-by: Reagan Lee <reaganjlee@gmail.com>
Signed-off-by: Reagan Lee <96998476+reaganjlee@users.noreply.github.com>
Co-authored-by: Reagan Lee <“reaganjlee@gmail.com”>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

c4df59ad

07 Feb, 2026 3 commits
- [Kernel] Add KernelConfig flag to enable/disable FlashInfer autotune (#34006) · dd6a6e11
  Mohammad Miadh Angkad authored Feb 07, 2026
```
Signed-off-by: Mohammad Miadh Angkad <176301910+mmangkad@users.noreply.github.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
```
  dd6a6e11
- [Revert] Add util `handle_deprecated` back (#33998) · 18e85452
  Wentao Ye authored Feb 06, 2026
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  18e85452
- [CI][AMD]Bugfix] Check that model_config is not None in enable_norm_pad_fusion (#34007) · ec28784f
  rasmith authored Feb 06, 2026
```
Signed-off-by: Randall Smith <Randall.Smith@amd.com>
```
  ec28784f
06 Feb, 2026 5 commits

Update `WeightTransferConfig` to be more standard like the others (#33989) · 51a7bda6
Harry Mellor authored Feb 06, 2026
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
51a7bda6

[Docs] Improve documentation (#33799) · 6e7b1c4b

SorenDreano authored Feb 06, 2026


Co-authored-by: Soren Dreano <soren@numind.ai>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>

6e7b1c4b

[torch.compile] Reorganize vllm/compilation and tests/compile (0/N for vLLM IR) (#33731) · ac32e66c

Luka Govedič authored Feb 06, 2026


Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Signed-off-by: ProExpertProg <luka.govedic@gmail.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>

ac32e66c

Onboard voyage-4-nano (#33720) · 96552566

chengchengpei authored Feb 05, 2026

Signed-off-by: Chengcheng Pei <chengchengpei@outlook.com>
Signed-off-by: chengchengpei <5881383+chengchengpei@users.noreply.github.com>
Co-authored-by: chengchengpei <5881383+chengchengpei@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

96552566

[Feature] OTEL tracing during loading (#31162) · 325ab6b0
emricksini-h authored Feb 06, 2026

325ab6b0

05 Feb, 2026 4 commits

[Spec Decode] Unified Parallel Drafting (#32887) · af3162d3
Benjamin Chislett authored Feb 05, 2026
```
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
```
af3162d3

[Feat][RL][1/2] Native Weight Syncing API: NCCL (#31943) · c1858b7e

Aaron Hao authored Feb 05, 2026


Signed-off-by: ahao-anyscale <ahao@anyscale.com>
Signed-off-by: Aaron Hao <ahao@anyscale.com>
Co-authored-by: SumanthRH <sumanthrh99@gmail.com>

c1858b7e

[CI][torch.compile] Reduce e2e fusion test time (#33293) · 4d951353

Luka Govedič authored Feb 04, 2026


Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Signed-off-by: ProExpertProg <luka.govedic@gmail.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>

4d951353

feat: Add ColBERT late interaction model support (#33686) · 439afa4e

Ilya Boytsov authored Feb 05, 2026


Signed-off-by: Ilya Boytsov <ilyaboytsov1805@gmail.com>
Signed-off-by: Ilya Boytsov <boytsovpanamera@mail.ru>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: wang.yuqi <yuqi.wang@daocloud.io>

439afa4e

04 Feb, 2026 2 commits
- [compile] Remove runner type from ignored caching factor list. (#33712) · a2084395
  Zhengxu Chen authored Feb 04, 2026
```
Signed-off-by: zhxchen17 <zhxchen17@fb.com>
```
  a2084395
- [Refactor] Remove unused dead code (#33718) · 5e1e0a0f
  Wentao Ye authored Feb 04, 2026
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  5e1e0a0f
03 Feb, 2026 5 commits
- Turn `@config` into a `dataclass_transform` (#31541) · 61e632ae
  Harry Mellor authored Feb 03, 2026
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  61e632ae
- [Misc] Remove deprecated VLLM_ALL2ALL_BACKEND environment variable (#33535) · b95cc501
  杨朱 · Kiki authored Feb 03, 2026
```
Signed-off-by: carlory <baofa.fan@daocloud.io>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
```
  b95cc501
- [Misc] Remove deprecated profiler environment variables (#33536) · ef248ff7
  杨朱 · Kiki authored Feb 03, 2026
```
Signed-off-by: carlory <baofa.fan@daocloud.io>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
```
  ef248ff7
- [XPU][1/N] Deprecate ipex and switch to vllm-xpu-kernels for xpu platform (#33379) · e1060448
  Kunshang Ji authored Feb 03, 2026
```
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
```
  e1060448
- [torch.compile] Don't do the fast moe cold start optimization if there is... · 5eac9a1b
  Richard Zou authored Feb 02, 2026
```
[torch.compile] Don't do the fast moe cold start optimization if there is speculative decoding (#33624)
Signed-off-by: Richard Zou <zou3519@gmail.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
```
  5eac9a1b
02 Feb, 2026 2 commits

Reduce the kernel overhead when num of active loras is smaller than max... · ffe1fc7a

yugong333 authored Feb 02, 2026


  Reduce the kernel overhead when num of active loras is smaller than max loras. Multiple cuda graphs are captured for each num of active-loras. (#32005)
Signed-off-by: Yu Gong <yu3.gong@gmail.com>

ffe1fc7a

[Models] Step-3.5-Flash (#33523) · c3b40dc3

csy0225 authored Feb 02, 2026


Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: i-zhangmingming <i-zhangmingming@stepfun.com>
Co-authored-by: xiewuxun <xiewuxun@stepfun.com>
Co-authored-by: zetaohong <i-hongzetao@stepfun.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>

c3b40dc3

31 Jan, 2026 4 commits
- [Deprecation] Remove deprecated items related to pooling (#33477) · 92924b2d
  Cyrus Leung authored Feb 01, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  92924b2d
- [fix][torch.compile] Fix cold-start compilation time increase by adding kv... · 15f40b20
  Luka Govedič authored Jan 31, 2026
```
[fix][torch.compile] Fix cold-start compilation time increase by adding kv cache update to splitting ops (#33441)
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Co-authored-by: Richard Zou <zou3519@gmail.com>
```
  15f40b20
- [Frontend] Use new Renderer for Completions and Tokenize API (#32863) · f0a1c845
  Cyrus Leung authored Jan 31, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  f0a1c845
- Add EAGLE3 support for AFMoE (#33111) · f3888aca
  AutumnAurelium authored Jan 30, 2026
```
Signed-off-by: AutumnAurelium <88015631+AutumnAurelium@users.noreply.github.com>
```
  f3888aca
30 Jan, 2026 6 commits
- Fix encoder-decoder model disabling mm processor cache (#33236) · 67239c4c
  Harry Mellor authored Jan 30, 2026
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  67239c4c
- Disable Cascade Attention for Batch Invariance (#32561) · 8f5d5120
  Frank Wang authored Jan 30, 2026
```
Signed-off-by: frankwang28 <frank.wbb@hotmail.com>
Signed-off-by: Frank Wang <41319051+frankwang28@users.noreply.github.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
```
  8f5d5120
- Improve Mistral format checks. (#33253) · ae5b7aff
  Julien Denize authored Jan 30, 2026
```
Signed-off-by: Julien Denize <julien.denize@mistral.ai>
Signed-off-by: juliendenize <julien.denize@mistral.ai>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
  ae5b7aff
- Move decode context parallel validationn to `ParallelConfig` (#33239) · d334dd26
  Harry Mellor authored Jan 30, 2026
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  d334dd26
- [BugFix] Disable async scheduling for Mamba prefix caching (#33352) · ec51831a
  Harry Huang authored Jan 30, 2026
```
Signed-off-by: huanghaoyan.hhy <huanghaoyan.hhy@alibaba-inc.com>
```
  ec51831a
- Fix `tie_word_embeddings` for multimodal models in Transformers v5 (#33359) · 80b918f2
  Harry Mellor authored Jan 30, 2026
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  80b918f2