Commits · af9b69f977bd1166ed63c46f9ccbd3a02344ae4f · OpenDAS / vllm_cscc

28 Jan, 2026 2 commits

[Quantization][Deprecation] Remove Marlin 24 (#32688) · af9b69f9

Robert Shaw authored Jan 28, 2026


Signed-off-by: Robert Shaw <robshaw@redhat.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

af9b69f9

[Quantization][Deprecation] Remove BitBlas (#32683) · 247d1a32

Robert Shaw authored Jan 28, 2026


Signed-off-by: Robert Shaw <robshaw@redhat.com>
Signed-off-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>

247d1a32

24 Jan, 2026 1 commit
- [UX] Deduplicate sampling parameter startup logs (#32953) · 51931c5c
  Cyrus Leung authored Jan 24, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  51931c5c
20 Jan, 2026 1 commit
- [Model] Use context managers for encoder- and LM-only mode (#32605) · 4753f3bf
  Cyrus Leung authored Jan 20, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  4753f3bf
14 Jan, 2026 2 commits
- Add Molmo2 multimodal model support (#30997) · 7e6f1238
  sangho.lee authored Jan 13, 2026
```
Signed-off-by: sanghol <sanghol@allenai.org>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  7e6f1238
- Consolidate Intel Quantization Toolkit Integration in vLLM (#31716) · 50632adc
  Yi Liu authored Jan 14, 2026
```
Signed-off-by: yiliu30 <yi4.liu@intel.com>
```
  50632adc
13 Jan, 2026 1 commit
- [Misc] improve warning/assert messages (#32226) · 15b33ff0
  cjackal authored Jan 13, 2026
```
Signed-off-by: cjackal <44624812+cjackal@users.noreply.github.com>
```
  15b33ff0
12 Jan, 2026 1 commit

[Feature] Support recording expert indices for rollout router replay (#28284) · 49e6b86c

Hongxin Xu authored Jan 12, 2026


Signed-off-by: xhx1022 <1737006628@qq.com>
Signed-off-by: Hongxin Xu <70438206+xhx1022@users.noreply.github.com>
Signed-off-by: arlenxu <arlenxu@tencent.com>
Co-authored-by: 22quinn <33176974+22quinn@users.noreply.github.com>
Co-authored-by: arlenxu <arlenxu@tencent.com>

49e6b86c

10 Jan, 2026 1 commit
- [Refactor] Separate sequence and token pooling types (#32026) · 583a90e0
  Cyrus Leung authored Jan 10, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  583a90e0
09 Jan, 2026 2 commits

[1/N][Attention] Restructure attention: move files (#31916) · 2612ba92
Matthew Bonanni authored Jan 09, 2026
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
2612ba92

[Quantization] Deprecate Long Tail of Schemes (#31688) · 5825bbc1

Robert Shaw authored Jan 08, 2026

Signed-off-by: Robert Shaw <robshaw@redhat.com>
Signed-off-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>

5825bbc1

08 Jan, 2026 1 commit

RayLLM Bugfix - Preserve obj store URL for multi engine_config creation (#30803) · 04a49669

omer-dayan authored Jan 08, 2026


Signed-off-by: Omer Dayan <omdayan@nvidia.com>
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>

04a49669

06 Jan, 2026 2 commits

[Quantization][Refactor] Move CPU GPTQ kernel into MP linear (#31801) · 8becf146

Li, Jiang authored Jan 07, 2026

Signed-off-by: jiang1.li <jiang1.li@intel.com>
Signed-off-by: Li, Jiang <bigpyj64@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

8becf146

[Model] rename use_pad_token to use_sep_token (#31784) · 96860af6
wang.yuqi authored Jan 06, 2026
```
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
```
96860af6

05 Jan, 2026 1 commit
- [Misc] Enable Paligemma's PrefixLM attention mask computation (#31725) · 51e38a8e
  Isotr0py authored Jan 06, 2026
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  51e38a8e
02 Jan, 2026 2 commits
- [Core] Parse vLLM engine required fields from hf_config to model_arch_config (#28454) · 0eee877f
  Xingyu Liu authored Jan 02, 2026
```
Signed-off-by: Xingyu Liu <charlotteliu12x@gmail.com>
Signed-off-by: Xingyu Liu <38244988+charlotte12l@users.noreply.github.com>
```
  0eee877f
- [BugFix] Support online dense model DP without overhead (#30739) · bd877162
  Nick Hill authored Jan 02, 2026
```
Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: njhill <nickhill123@gmail.com>
```
  bd877162
30 Dec, 2025 1 commit
- [Minor] Various small code cleanups/simplifications (#31508) · 3b312fb7
  Nick Hill authored Dec 29, 2025
```
Signed-off-by: njhill <nickhill123@gmail.com>
```
  3b312fb7
24 Dec, 2025 3 commits
- [Bugfix] Fix `max_model_len="auto"` handling (#31260) · 7adeb4bf
  Cyrus Leung authored Dec 24, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  7adeb4bf
- [Model] Introduce verify_and_update_model_config for VerifyAndUpdateConfig. (#31131) · bd89ce16
  wang.yuqi authored Dec 24, 2025
```
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: wang.yuqi <noooop@126.com>
```
  bd89ce16
- Add `--max-model-len auto` to auto-fit context to available memory (#29431) · 8ee90c83
  Michael Goin authored Dec 24, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  8ee90c83
23 Dec, 2025 3 commits
- Use helper function instead of looping through attribute names (#29788) · c016c95b
  Harry Mellor authored Dec 23, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  c016c95b
- adapt voxtral (#31095) · 3faa8bee
  Patrick von Platen authored Dec 23, 2025
```
Signed-off-by: Patrick von Platen <patrick.v.platen@gmail.com>
```
  3faa8bee
- Add util function for checking nesting of rope parameters (#31146) · b10d47e0
  Harry Mellor authored Dec 23, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  b10d47e0
22 Dec, 2025 2 commits
- [BugFix] skip language model in Encoder (#30242) · 8f8f469b
  dengyunyang authored Dec 22, 2025
```
Signed-off-by: dengyunyang <584797741@qq.com>
```
  8f8f469b
- [Feature]: Support NVIDIA ModelOpt HF FP8 variants FP8_PER_CHANNEL_PER_TOKEN... · 19cc9468
  CedricHuang authored Dec 22, 2025
```
[Feature]: Support NVIDIA ModelOpt HF FP8 variants FP8_PER_CHANNEL_PER_TOKEN and FP8_PB_WO  in vLLM (#30957)
```
  19cc9468
19 Dec, 2025 1 commit

[Model] Add MiMo-V2-Flash support (#30836) · 969bbc7c

Zhonghua Deng authored Dec 20, 2025


Signed-off-by: Abatom <abzhonghua@gmail.com>
Signed-off-by: Jumiar <liuanqim10@126.com>
Signed-off-by: Zyann7 <zyann7@outlook.com>
Co-authored-by: Jumiar <liuanqim10@126.com>
Co-authored-by: Zyann7 <zyann7@outlook.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>

969bbc7c

15 Dec, 2025 2 commits
- Remove `SkipValidation` from `ModelConfig` (#30695) · 970713d4
  Harry Mellor authored Dec 15, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  970713d4
- [Model] Automatic conversion of TokenClassification model (#30666) · 4429d934
  wang.yuqi authored Dec 15, 2025
```
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
```
  4429d934
14 Dec, 2025 1 commit
- [Bugfix] Improve error messages in ModelConfig validation (#30213) · 5ccf0efa
  yifant-code authored Dec 14, 2025
```
Signed-off-by: ytian218 <ytian218@bloomberg.net>
Co-authored-by: ytian218 <ytian218@bloomberg.net>
```
  5ccf0efa
11 Dec, 2025 3 commits
- [Core] Whisper Enable Encoder Batching (#29421) · 0efd9f86
  Nicolò Lucchesi authored Dec 11, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  0efd9f86
- [Deprecation] Deprecation `--convert reward`, use `--convert embed` instead. (#30463) · a5f9fb59
  wang.yuqi authored Dec 11, 2025
```
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
```
  a5f9fb59
- [Deprecation] Remove deprecated task, seed and MM settings (#30397) · 7e24e5d4
  Cyrus Leung authored Dec 11, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  7e24e5d4
08 Dec, 2025 1 commit

[Model][7/N] Improve all pooling task | Deprecation as_reward_model. Extract... · 9e77ffca

wang.yuqi authored Dec 08, 2025


[Model][7/N] Improve all pooling task | Deprecation as_reward_model. Extract hidden states prefer using new multi-vector retrieval API (#26686)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>

9e77ffca