Commits · e1a34c3a5d9273431ee182253750d39b546d37a1 · OpenDAS / vllm_cscc

"vscode:/vscode.git/clone" did not exist on "165cb56329e6cdbf58741b420c349793ec2390b3"

20 Jan, 2026 3 commits
- [2/N] Initialize MM components in context managers (E-H) (#32641) · e1a34c3a
  Cyrus Leung authored Jan 20, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  e1a34c3a
- [1/N] Initialize MM components in context managers (A-D) (#32632) · b75e85de
  Cyrus Leung authored Jan 20, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  b75e85de
- [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
19 Jan, 2026 6 commits
- support dynamic resolution image encoding for Nemotron Nano VL (#32121) · cd3ac5b7
  Netanel Haber authored Jan 19, 2026
```
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
```
  cd3ac5b7
- [Misc] Remove unused ModelKeys (#32608) · 2636d762
  Jee Jee Li authored Jan 20, 2026
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  2636d762
- Add support for LoRA adapters in Nemotron-H models (#30802) · aa7f37cc
  danisereb authored Jan 19, 2026
```
Signed-off-by: Daniel Serebrenik <daserebrenik@nvidia.com>
```
  aa7f37cc
- [Core] Whisper support `torch.compile` (#30385) · 74c583bc
  Nicolò Lucchesi authored Jan 19, 2026
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  74c583bc
- [GLM-4.7] GLM Model support for GLM-Lite (#31386) · 71832ba7
  Yuxuan Zhang authored Jan 19, 2026
```
Signed-off-by: zRzRzRzRzRzRzR <2448370773@qq.com>
Signed-off-by: Yuxuan Zhang <2448370773@qq.com>
```
  71832ba7
- [BugFix] Fix embed_input_ids argument error of QwenVLForConditionalGeneration (#32462) · 976af2f3
  honglyua authored Jan 19, 2026
  
  976af2f3
18 Jan, 2026 5 commits
- [MoE Refactor] Separate Router into OO Classes (#30623) · 327a02d8
  bnellnm authored Jan 18, 2026
```
Signed-off-by: Bill Nell <bnell@redhat.com>
```
  327a02d8
- "refactor: refactor_repeated_interfaces" (#32486) · 2f03035a
  tjp_zju authored Jan 18, 2026
```
Signed-off-by: tom-zju <tanjianpingzju1990@gmail.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
```
  2f03035a
- [Bugfix] Fix GLM-ASR audio encoder RoPE dim (#32540) · 38bf2ffb
  Isotr0py authored Jan 18, 2026
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  38bf2ffb
- [Model] Support Step1 Model (#32511) · c826c72a
  Li Xie authored Jan 18, 2026
```
Signed-off-by: xieli <xieli@stepfun.com>
```
  c826c72a
- [Model] Remove the unnecessary dtype conversion in MiniCPM (#32523) · fe36bf5e
  Canlin Guo authored Jan 18, 2026
```
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
```
  fe36bf5e
17 Jan, 2026 2 commits
- [Model] Molmo2: Enable quantized weight mapping for vision backbone (#32385) · 1646fea6
  Kim Hee Su authored Jan 17, 2026
```
Signed-off-by: kimheesu <wlskaka4@gmail.com>
```
  1646fea6
- [Models] Lfm2Moe: minor name changes for resolving lora conflicts (#29063) · d3317bbb
  Paul Pak authored Jan 16, 2026
```
Signed-off-by: Paul Pak <paulpak58@gmail.com>
```
  d3317bbb
16 Jan, 2026 3 commits

[Chore] Replace swish with silu (#32459) · 180e981d
Cyrus Leung authored Jan 16, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
180e981d

[Bugfix] [DeepSeek-V3.2] fix sparse_attn_indexer padding (#32175) · 5de6dd06

Kebe authored Jan 16, 2026


Signed-off-by: Kebe <mail@kebe7jun.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>

5de6dd06

[Model] Add Step3vl 10b (#32329) · 70950255

ltd0924 authored Jan 16, 2026


Signed-off-by: luotingdan <luotingdan@stepfun.com>
Signed-off-by: ltd0924 <32387785+ltd0924@users.noreply.github.com>
Co-authored-by: luotingdan <luotingdan@stepfun.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>

70950255

15 Jan, 2026 1 commit
- [Model] Avoid token selection in SigLIP pooling head (#32389) · cdba4c74
  Cyrus Leung authored Jan 15, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  cdba4c74
14 Jan, 2026 3 commits
- [1/N] Reorganize multimodal processing code (#32327) · 9ea07b41
  Cyrus Leung authored Jan 14, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  9ea07b41
- [Model] Re-implement Qwen3Omni Audio Encoder (#32167) · b8199f60
  Roger Wang authored Jan 13, 2026
```
Signed-off-by: Roger Wang <hey@rogerw.io>
```
  b8199f60
- 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
13 Jan, 2026 6 commits
- [6/N][Attention] Move utils to more appropriate locations (#32215) · 98f60e5a
  Matthew Bonanni authored Jan 13, 2026
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  98f60e5a
- [Bugfix] Replace `PoolingParams.normalize` with `use_activation` (#32243) · 232214b2
  Cyrus Leung authored Jan 13, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  232214b2
- [Refactor] Remove `get_encoder_dummy_data` (#32241) · eb28e806
  Cyrus Leung authored Jan 13, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  eb28e806
- [Model] Use mm_position to compute mrope positions for Qwen2-VL/2.5-VL (#32126) · 542a4059
  YunzhuLu authored Jan 13, 2026
```
Signed-off-by: YunzhuLu <lucia.yunzhu@gmail.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  542a4059
- [ROCm][Bugfix] Fix Mamba batched decode producing incorrect output (#32099) · 11b6af52
  Andreas Karatzas authored Jan 12, 2026
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  11b6af52
- [Model] Handle `trust_remote_code` for transformers backend (#32194) · 78d13ea9
  Cyrus Leung authored Jan 13, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  78d13ea9
12 Jan, 2026 9 commits
- [BUGFIX] Add missed remaping of the names of fp8 kv-scale (#32199) · 9f430c94
  Vadim Gimpelson authored Jan 13, 2026
```
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
```
  9f430c94
- [Misc] Set default torch num threads for input processing (#31879) · 16abe6b8
  Roger Wang authored Jan 12, 2026
```
Signed-off-by: Roger Wang <hey@rogerw.io>
```
  16abe6b8
- [BugFix] fix FusedMoE.make_expert_params_mapping in EXAONE-MoE (#32196) · 3d962d72
  Kyungmin Lee authored Jan 13, 2026
```
Signed-off-by: lkm2835 <lkm2835@gmail.com>
```
  3d962d72
- [3/N][Attention] Move AttentionMetadata-related code from utils.py to backend.py (#32054) · 20228cb8
  Matthew Bonanni authored Jan 12, 2026
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  20228cb8
- [Model] Standardize pooling heads (#32148) · 8863c2b2
  Cyrus Leung authored Jan 13, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  8863c2b2
- [MODEL] New model support for kakaocorp/kanana-1.5-v-3b-instruct (#29384) · 6bc9c847
  Jaehyun An authored Jan 13, 2026
```
Signed-off-by: Jaehyun An <steve.ai@kakaocorp.com>
```
  6bc9c847
- Add K-EXAONE-236B-A23B (#31621) · 63ed2409
  Kyungmin Lee authored Jan 13, 2026
```
Signed-off-by: lkm2835 <lkm2835@gmail.com>
Signed-off-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: lgai-exaone <exaonemodels@lgresearch.ai>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
```
  63ed2409
- [Model] Remove incorrect `SupportsPP` from MTP models (#32150) · 600aaab8
  Cyrus Leung authored Jan 12, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  600aaab8
- [Model] Avoid hardcoding pooling type (#32119) · 9101dc75
  Cyrus Leung authored Jan 12, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  9101dc75
11 Jan, 2026 1 commit

[MTP][GLM][Bugfix] Fixed .weight_scale loading logic that dropped MTP... · 0dd63639

Andy Liu authored Jan 10, 2026


[MTP][GLM][Bugfix] Fixed .weight_scale loading logic that dropped MTP prediction accuracy with fp8+mtp (#32101)
Signed-off-by: Andy Liu <andyliu@roblox.com>

0dd63639

10 Jan, 2026 1 commit

[Bugfix] Fix Qwen3-VL-Reranker model loading for sequence classification (#32089) · 8020a604

RickyChen / 陳昭儒 authored Jan 11, 2026


Signed-off-by: rickychen-infinirc <ricky.chen@infinirc.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>

8020a604