Commits · 6d8d34be6dcaff0f5aa6de245adffc2bac5b2d3e · OpenDAS / vllm_cscc

06 Feb, 2026 1 commit
- [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

[Refactor] Move `task` outside of `PoolingParams.verify` (#33796) · 038914b7

Cyrus Leung authored Feb 05, 2026


Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Co-authored-by: wang.yuqi <yuqi.wang@daocloud.io>

038914b7

[CI/Build] Parallelize CPU CI tests (#33778) · 07daee13
Li, Jiang authored Feb 05, 2026
```
Signed-off-by: jiang1.li <jiang1.li@intel.com>
```
07daee13

04 Feb, 2026 4 commits
- [Core] Don't schedule spec tokens with prefill chunks (#33652) · fa4e0fb0
  Nick Hill authored Feb 04, 2026
```
Signed-off-by: Nick Hill <nickhill123@gmail.com>
```
  fa4e0fb0
- [rocm][ray] Fix: Unify Ray device visibility handling across CUDA and ROCm (#33308) · 2f6d17cb
  kourosh hakhamaneshi authored Feb 04, 2026
```
Signed-off-by: Kourosh Hakhamaneshi <kourosh@anyscale.com>
```
  2f6d17cb
- [Bugfix] Fix ubatch wrapper num_tokens calculate (#33694) · 87d9a261
  jiangkuaixue123 authored Feb 05, 2026
```
Signed-off-by: jiangkuaixue123 <jiangxiaozhou111@163.com>
```
  87d9a261
- [Bugfix] Fix torchrun PP broadcast deadlock with async scheduling (#33701) · 02080179
  Isotr0py authored Feb 04, 2026
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  02080179
03 Feb, 2026 1 commit
- [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
02 Feb, 2026 3 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
- [Refactor] Move profiling methods to MM budget (#33559) · d7e17aaa
  Cyrus Leung authored Feb 02, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  d7e17aaa
- [ModelRunner V2] Support spec decode with structured outputs (#33374) · cf0a99f8
  Nick Hill authored Feb 01, 2026
```
Signed-off-by: Nick Hill <nickhill123@gmail.com>
```
  cf0a99f8
01 Feb, 2026 3 commits
- [ModelRunner V2] Misc minor simplifications and optimizations (#33467) · e535d90d
  Nick Hill authored Feb 01, 2026
```
Signed-off-by: Nick Hill <nickhill123@gmail.com>
```
  e535d90d
- [Misc] skip target model mm emb in draft proposal step when draft is text-only (#33437) · 0b225fb7
  Komal Kumar Teru authored Feb 02, 2026
```
Signed-off-by: kkt-cohere <komal@cohere.com>
```
  0b225fb7
- [Bugfix] Fix inconsistent handling of cache reset (#33481) · 79b6ec6a
  Cyrus Leung authored Feb 01, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  79b6ec6a
31 Jan, 2026 6 commits
- Fix grammar (#33121) · 1e86c802
  smashyalts authored Jan 31, 2026
```
Signed-off-by: smashyalts <smashyalts@gmail.com>
```
  1e86c802
- Support clear mm and encoder cache (#33452) · 22d9a056
  jma99_2333 authored Jan 31, 2026
```
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.io>
```
  22d9a056
- [BugFix][Router Replay] Capture Logical Experts with EPLB (#33013) · 13b842f2
  ℍ𝕠𝕝𝕝𝕠𝕨 𝕄𝕒𝕟 authored Jan 31, 2026
```
Signed-off-by: Hollow Man <hollowman@opensuse.org>
```
  13b842f2
- [BugFix] Fix whisper FA2 + full cudagraphs (#33360) · 0a3c71e7
  Lucas Wilkinson authored Jan 30, 2026
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
  0a3c71e7
- [ModelRunner V2] Fix spec decoding + logprobs (#33391) · 876a16f4
  Nick Hill authored Jan 30, 2026
```
Signed-off-by: Nick Hill <nickhill123@gmail.com>
```
  876a16f4
- [Deprecation] Deprecate `seed_everything` and `scatter_mm_placeholders` in v0.15 (#33362) · 010ec0c3
  Wentao Ye authored Jan 30, 2026
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  010ec0c3
30 Jan, 2026 4 commits
- [QeRL] Layerwise Reloading (#32133) · f857a03f
  Kyle Sayers authored Jan 30, 2026
```
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
```
  f857a03f
- [Realtime API] Adds minimal realtime API based on websockets (#33187) · 10152d21
  Patrick von Platen authored Jan 30, 2026
```
Signed-off-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
```
  10152d21
- [Misc] Replace Optional[X] with X | None syntax (#33332) · 1a7894db
  杨朱 · Kiki authored Jan 30, 2026
```
Signed-off-by: carlory <baofa.fan@daocloud.io>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
```
  1a7894db
- [Refactor] Move MM item count validation outside of processor (#33396) · c87eac18
  Cyrus Leung authored Jan 30, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  c87eac18
29 Jan, 2026 3 commits
- [BUGFIX][XPU] fix memory check after XPU reuse GPU_worker (#33358) · 8c8ebeb9
  Chendi.Xue authored Jan 29, 2026
```
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
```
  8c8ebeb9
- [Multimodal] Simplify MM input definitions (#33331) · c6e7404c
  Cyrus Leung authored Jan 29, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  c6e7404c
- [Intel GPU] refine xpu worker (#32894) · 8bb6271c
  Kunshang Ji authored Jan 29, 2026
```
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
```
  8bb6271c
28 Jan, 2026 4 commits

[ModelRunner V2] Misc code simplification and cleanup (#33266) · 6bf3b46d
Nick Hill authored Jan 28, 2026
```
Signed-off-by: Nick Hill <nickhill123@gmail.com>
```
6bf3b46d

[Feature] Fully support for async scheduling + PP, 30.8% E2E throughput... · 3e440786

Wentao Ye authored Jan 28, 2026


[Feature] Fully support for async scheduling + PP, 30.8% E2E throughput improvement, 31.8% TPOT improvement (#32618)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>

3e440786

[Bugfix] Lazy import NgramProposer in GPU model runner (#32821) · a2b877df
22quinn authored Jan 27, 2026
```
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
```
a2b877df

[Model Runner V2] Use a different stream for grammar bitmask h2d copy (#33059) · 46ec6d71

Woosuk Kwon authored Jan 27, 2026


Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Co-authored-by: Nick Hill <nhill@redhat.com>

46ec6d71

27 Jan, 2026 2 commits
- [5/N][Attention] Finish eliminating `vllm/attention` folder (#32064) · a608b4c6
  Matthew Bonanni authored Jan 27, 2026
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  a608b4c6
- [Model Runner V2] Remove UvaBufferPool for cpu->gpu copy (#33055) · 6d86fde0
  Woosuk Kwon authored Jan 26, 2026
```
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Co-authored-by: Nick Hill <nhill@redhat.com>
```
  6d86fde0
26 Jan, 2026 3 commits
- [Model Runner V2] Add LoRAState to consolidate lora logic (#33062) · a9b53dd4
  Woosuk Kwon authored Jan 25, 2026
```
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
```
  a9b53dd4
- [Model Runner V2] Minor simplification for finish_requests (#33048) · 2f0d3ba7
  Woosuk Kwon authored Jan 25, 2026
```
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
```
  2f0d3ba7
- [Model Runner V2] Fix slot_mapping after #25954 (#33046) · edf927bc
  Woosuk Kwon authored Jan 25, 2026
```
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Woosuk Kwon <woosuk@inferact.ai>
```
  edf927bc
25 Jan, 2026 1 commit
- [Model] Use mm_position to compute mrope positions for Qwen2.5-Omni (#32772) · a698e8e7
  Itay Etelis authored Jan 25, 2026
```
Signed-off-by: Itay Etelis <itay.etelis@ibm.com>
Co-authored-by: Itay Etelis <itay.etelis@ibm.com>
```
  a698e8e7
24 Jan, 2026 1 commit

[Feature] add session based streaming input support to v1 (#28973) · 91601ff4

Joshua Deng authored Jan 24, 2026


Signed-off-by: Joshua Deng <joshuakdeng@gmail.com>
Signed-off-by: Patrick von Platen <patrick.v.platen@gmail.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>

91601ff4