Commits · cc410e864480aee7fc01cfc6017abca677b198df · OpenDAS / vllm_cscc

02 Jan, 2026 9 commits
- [Bugfix] Fix weight_loader v1 block scale (#31103) · cc410e86
  Kyuyeun Kim authored Jan 01, 2026
```
Signed-off-by: Kyuyeun Kim <kyuyeunk@google.com>
```
  cc410e86
- [Bugfix][Hardware][AMD] Fix last_page_len calculation in AITER MLA decode (#31282) · 825c2dc1
  Kevin McKay authored Jan 01, 2026
```
Signed-off-by: c0de128 <kevin.mckay@outlook.com>
```
  825c2dc1
- Remove unused `use_marlin` variable in `Mxfp4MoEMethod` (#31549) · 1f43c121
  Vaibhav Sourirajan authored Jan 02, 2026
```
Signed-off-by: vaibhav sourirajan <vs2787@columbia.edu>
```
  1f43c121
- [Bugfix] Fix activation quantization for compressed-tensors W4A16 (#31572) · ca179d0f
  Tmn07 authored Jan 02, 2026
```
Signed-off-by: Tmn07 <tmn0796@gmail.com>
```
  ca179d0f
- [Model] Enable LoRA support for tower and connector in LLaVA (#31513) · 5ac55eb3
  Jay Hemnani authored Jan 01, 2026
```
Signed-off-by: Jay Hemnani <jayhemnani9910@gmail.com>
Co-authored-by: Jay Hemnani <jayhemnani9910@gmail.com>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
```
  5ac55eb3
- [Bugfix] Fix block size used in EAGLE slot mapping (#31540) · ea53ca5e
  Benjamin Chislett authored Jan 01, 2026
```
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
```
  ea53ca5e
- feat: support LoRA for DeepSeek-OCR(Language Model part) (#31569) · 27864a85
  zhima771 authored Jan 02, 2026
```
Signed-off-by: zhima771 <15836938703@163.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
```
  27864a85
- [Bugfix] Replace BaseException with specific exceptions in FLA utils (#31590) · 5fff4406
  Kevin McKay authored Jan 01, 2026
```
Signed-off-by: c0de128 <kevin.mckay@outlook.com>
```
  5fff4406
- Add Multimodal Processor Benchmark (#29105) · 1f5b7c41
  Reagan Lee authored Jan 01, 2026
```
Signed-off-by: Reagan Lee <reaganjlee@gmail.com>
Signed-off-by: Reagan <reaganjlee@gmail.com>
```
  1f5b7c41
31 Dec, 2025 9 commits

[BugFix] Fix async scheduling for pooling models (#31584) · 6c2cfb62
Nick Hill authored Dec 31, 2025
```
Signed-off-by: njhill <nickhill123@gmail.com>
```
6c2cfb62

[Bugfix] Fix BAGEL online serving for text and image understanding (#31546) · d8da76f3

Fanjiang Ye authored Dec 31, 2025


Signed-off-by: Dylan1229 <yvanphys@gmail.com>
Signed-off-by: UED <zxr3611244710@gmail.com>
Signed-off-by: mr-ye-cao <yecaoyc2019@gmail.com>
Co-authored-by: UED <zxr3611244710@gmail.com>
Co-authored-by: mr-ye-cao <yecaoyc2019@gmail.com>
Co-authored-by: Mr-Ye-Cao <60802056+Mr-Ye-Cao@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

d8da76f3

Add GLM-ASR multimodal support (#31436) · d722e9e6

baonudesifeizhai authored Dec 31, 2025

Signed-off-by: baonudesifeizhai <baonudesifeizhai@gmail.com>
Signed-off-by: baonudesifeizhai <85092850+baonudesifeizhai@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

d722e9e6

[Bug] Fix log issue with `\n` (#31390) · 357d435c

Wentao Ye authored Dec 31, 2025

Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>

357d435c

Add get_expert_mapping to NemotronHModel (for LoRA support) (#31539) · 108a2728
danisereb authored Dec 31, 2025
```
Signed-off-by: Daniel Serebrenik <daserebrenik@nvidia.com>
```
108a2728
[Core] Remove unused `num_tokens` parameter from `_init_model_kwargs` (#31517) · b4bb5f31
maang-h authored Dec 31, 2025
```
Signed-off-by: maang <maang_h@163.com>
```
b4bb5f31

[BugFix] Fix NUMA node validation in CPU platform (#31520) · 70e1acef

SameerAsal authored Dec 30, 2025


Signed-off-by: SameerAsal <SameerAsal@users.noreply.github.com>
Co-authored-by: SameerAsal <SameerAsal@users.noreply.github.com>

70e1acef

[Mics] add pcp basic support to MoE model (#31003) · 84f6cd74
Qiu authored Dec 31, 2025

84f6cd74
[Fix] Align fused moe lora_b shape with peft (#31534) · ecd49ce7
B-201 authored Dec 31, 2025
```
Signed-off-by: bk-201 <joy25810@foxmail.com>
```
ecd49ce7

30 Dec, 2025 12 commits

[Bugfix]Fix pooling model always disabled due to incorrect PP rank check (#31505) · 04147dcf
vintipandey authored Dec 30, 2025
```
Signed-off-by: vintipandey <vinti.pandey@gmail.com>
```
04147dcf
[BugFix] add select_gemm_impl on CompressedTensorsWNA16MoEMethod to support LoRA (#31453) · 07728bf5
JartX authored Dec 30, 2025
```
Signed-off-by: JartX <sagformas@epdcenter.es>
```
07728bf5

[Model] Add support for openPangu moe model (#28775) · 3f52fa5a

yt0428 authored Dec 31, 2025


Signed-off-by: yuantao <2422264527@qq.com>
Signed-off-by: yt0428 <51468697+yt0428@users.noreply.github.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

3f52fa5a

[CPU] Disable async schedule on CPU (#31525) · 71575961
Li, Jiang authored Dec 30, 2025
```
Signed-off-by: jiang1.li <jiang1.li@intel.com>
```
71575961

[ROCm][Bugfix] Fix accuracy issue on fmoe when... · 1a834df2

Pleaplusone authored Dec 30, 2025


[ROCm][Bugfix] Fix accuracy issue on fmoe when `VLLM_ROCM_USE_AITER_FUSION_SHARED_EXPERTS` enabled (#31523)
Signed-off-by: ganyi <ygan@amd.com>

1a834df2

[Frontend] add continue_final_message parameter to /embeddings endpoint (#31497) · 51085c2a
Kevin authored Dec 29, 2025
```
Signed-off-by: Kevin P-W <140451262+kevin-pw@users.noreply.github.com>
```
51085c2a
[Minor] Various small code cleanups/simplifications (#31508) · 3b312fb7
Nick Hill authored Dec 29, 2025
```
Signed-off-by: njhill <nickhill123@gmail.com>
```
3b312fb7
Add Loraconfig parameter to get_punica_wrapper function (#31408) · f84bf7d7
ZT-AIA authored Dec 30, 2025
```
Signed-off-by: ZT-AIA <1028681969@qq.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
```
f84bf7d7
feat(frontend): add --default-chat-template-kwargs CLI argument (#31343) · dc837bc2
Hojin Yang authored Dec 30, 2025
```
Signed-off-by: effortprogrammer <yhjhoward7@gmail.com>
```
dc837bc2
[Core] Deduplicate generate/encode logic in `AsyncLLM` (#31510) · e54ee3ea
Nick Hill authored Dec 29, 2025
```
Signed-off-by: njhill <nickhill123@gmail.com>
```
e54ee3ea

fix: update kimi k2 tool parser logic (#31207) · 358bfd31

wangln19 authored Dec 30, 2025

Signed-off-by: wangln19 <wanglinian@dev.wanglinian.msh-dev.svc.cluster.local>
Signed-off-by: Wang Linian <wanglinian@stu.pku.edu.cn>
Co-authored-by: wangln19 <wanglinian@dev.wanglinian.msh-dev.svc.cluster.local>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>

358bfd31

[Prefix Cache] Include lora_name in BlockStored event for deterministic... · 39512aba

Sage authored Dec 30, 2025


[Prefix Cache] Include lora_name in BlockStored event for deterministic KV-cache reconstruction (#27577)
Signed-off-by: Sage Ahrac <sagiahrak@gmail.com>
Co-authored-by: Sage <80211083+sagiahrac@users.noreply.github.com>

39512aba

29 Dec, 2025 10 commits

[CI]Test Group 'NixlConnector PD accuracy tests' is fixed (#31460) · 0f35429a
qli88 authored Dec 29, 2025
```
Signed-off-by: qli88 <qiang.li2@amd.com>
```
0f35429a

[Bugfix][ROCm] Fix Static Quant Issue (#31502) · 56f51625

Robert Shaw authored Dec 29, 2025


Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>

56f51625

[MoE Refactor][12/N] Marlin Fp8 MoE Pure Function (#31499) · 9152a30d
Robert Shaw authored Dec 29, 2025
```
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
```
9152a30d
[Core] Enable async scheduling by default (#27614) · c2ff33cc
Nick Hill authored Dec 29, 2025
```
Signed-off-by: Nick Hill <nickhill123@gmail.com>
```
c2ff33cc
implements register kv caches in lmcache connector (#31397) · b12cb383
chunxiaozheng authored Dec 30, 2025
```
Signed-off-by: idellzheng <idellzheng@tencent.com>
```
b12cb383
Optimize QKNorm for MiniMax-M2/M2.1 (#31493) · 5bc66411
Roger Young authored Dec 30, 2025
```
Signed-off-by: xuebi <xuebi@minimaxi.com>
Co-authored-by: xuebi <xuebi@minimaxi.com>
```
5bc66411

[Feature] Add offline FastAPI documentation support for air-gapped environments (#30184) · b3a2bdf1

RickyChen / 陳昭儒 authored Dec 30, 2025

Signed-off-by: rickychen-infinirc <ricky.chen@infinirc.com>
Signed-off-by: RickyChen / 陳昭儒 <ricky.chen@infinirc.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

b3a2bdf1

Replace `nn.ConvNd` with vLLM's `ConvNdLayer` for Transformers modeling backend (#31498) · e37e7349
Harry Mellor authored Dec 29, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
e37e7349
[Bugfix] Preserve tool call id/type/name in streaming finish chunk (#31438) · 9c884faa
amittell authored Dec 29, 2025
```
Signed-off-by: amittell <mittell@me.com>
Signed-off-by: Alex Mittell <mittell@me.com>
```
9c884faa

[Bugfix][Frontend] Fix Jina reranker multimodal input compatibility (#31445) · bf73a3e4

twj authored Dec 29, 2025

Signed-off-by: tianwenjing <tianwenjing@jfgenius.com>
Signed-off-by: twj <151701930+twjww@users.noreply.github.com>
Co-authored-by: tianwenjing <tianwenjing@jfgenius.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

bf73a3e4