Commits · dcd80206b7a9143c81f7f2808e84914f8e38ce95 · OpenDAS / vllm_cscc

26 Jan, 2026 8 commits
- [Chore] Update type annotation of `input_ids` in model forward (#33063) · dcd80206
  Cyrus Leung authored Jan 26, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  dcd80206
- [Performance] Tune Mamba selective scan kernel for B200 (#32873) · f4a0921c
  danisereb authored Jan 26, 2026
```
Signed-off-by: Daniel Serebrenik <daserebrenik@nvidia.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
```
  f4a0921c
- [Feature] Add LoRA support for Gemma3 vision components (#32764) · 208c5625
  VihaanThat authored Jan 26, 2026
  
  208c5625
- [Model] Use mm_position to compute mrope positions for Qwen3-Omni (#33010) · 6ca2c91b
  Itay Etelis authored Jan 26, 2026
```
Signed-off-by: Itay Etelis <itay.etelis@ibm.com>
Co-authored-by: Itay Etelis <itay.etelis@ibm.com>
```
  6ca2c91b
- [Refactor] Use data parser for matching data items to multi-modal UUIDs (#32955) · 11b55687
  Cyrus Leung authored Jan 26, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  11b55687
- [StepVL] support close img patch (#32923) · 105d1045
  ltd0924 authored Jan 26, 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>
```
  105d1045
- [CI] Fix MHA attention test failure (AttributeError when model_config is None... · 566cdb6c
  Lucas Wilkinson authored Jan 25, 2026
```
[CI] Fix MHA attention test failure (AttributeError when model_config is None in ViT attention backend) (#33033)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
  566cdb6c
- [Bugfix][VLM] Fix transformers backend embed_multimodal for Qwen2.5-VL profiling (#32969) · 22aeb430
  Andreas Karatzas authored Jan 25, 2026
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  22aeb430
25 Jan, 2026 3 commits

[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

[Bugfix] fix encoder cache hang in Qwen3VL (#32684) · 7e67df55

JJJYmmm authored Jan 25, 2026


Signed-off-by: JJJYmmm <92386084+JJJYmmm@users.noreply.github.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>

7e67df55

[Perf][Kernel] Optimize FP4 quantization kernels (SM100F) (#32520) · fcb9df99
Roberto L. Castro authored Jan 25, 2026
```
Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
```
fcb9df99

24 Jan, 2026 5 commits

[MLA] Fuse cat and qaunt for fp8 kv-cache (#32950) · da5e7b12
Lucas Wilkinson authored Jan 24, 2026
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
da5e7b12
feat: Complete LoRA support for MiniMaxM2 Fixes #32736 (#32763) · bc0d291b
david guan authored Jan 24, 2026
```
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
```
bc0d291b
[Models]: Make Multimodal config implicit in ViT implementation (#31972) · 9ad7f89f
Isotr0py authored Jan 24, 2026
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
9ad7f89f
[Models] Add `SharedFusedMoE` support to Qwen3MoE (#32082) · 8edaf385
Isotr0py authored Jan 24, 2026
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
8edaf385

[Performance] Split FlashAttn attention and cache update (#25954) · a28b94e6

ElizaWszola authored Jan 24, 2026


Signed-off-by: ElizaWszola <ewszola@redhat.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Luka Govedič <luka.govedic@gmail.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Varun Sundar Rabindranath <varunsundar08@gmail.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Luka Govedič <luka.govedic@gmail.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Luka Govedič <lgovedic@redhat.com>

a28b94e6

23 Jan, 2026 15 commits
- [Bugfix] Fix missing is_layer_skipped check for FusedMoE in AWQConfig (#32935) · ebd0a17e
  joninco authored Jan 23, 2026
```
Signed-off-by: jon <joninco@bullpoint.org>
```
  ebd0a17e
- [Refactor] Clean up unused variables & func (#32692) · 37c9859f
  Wentao Ye authored Jan 23, 2026
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  37c9859f
- [Refactor] Rename `gptq_marlin` to `marlin` to match MoE (#32952) · 4561f139
  Michael Goin authored Jan 23, 2026
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  4561f139
- fix: Add glm4_moe_lite to MLA detection (#32614) · 586a57ad
  Markus / Mark authored Jan 23, 2026
```
Signed-off-by: marksverdhei <marksverdhei@hotmail.com>
Signed-off-by: Markus / Mark <46672778+marksverdhei@users.noreply.github.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
```
  586a57ad
- [V1][Hybrid] Mamba Prefix Caching with align mode (#30877) · 5206e5e2
  Harry Huang authored Jan 24, 2026
```
Signed-off-by: huanghaoyan.hhy <huanghaoyan.hhy@alibaba-inc.com>
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>
```
  5206e5e2
- [Model] Enable LoRA support for internvl2 (#32397) · fec9da0a
  Matteo Fari authored Jan 23, 2026
```
Signed-off-by: Matteo Fari <matteofari06@gmail.com>
```
  fec9da0a
- [Bugfix] Fix FP8 MoE EP Weight Loading for ModelOpt Llama4 (#32886) · 1fb648bf
  baonudesifeizhai authored Jan 23, 2026
```
Signed-off-by: baonudesifeizhai <baonudesifeizhai@gmail.com>
```
  1fb648bf
- [Bugfix] Disable tma_aligned_scales in test_fusions_e2e (#32916) · 90c20079
  Xin Yang authored Jan 23, 2026
```
Signed-off-by: Xin Yang <xyangx@amazon.com>
```
  90c20079
- [Bugfix] Fix getting vision features in Transformer Multimodal backend (#32933) · d95d6507
  Raushan Turganbay authored Jan 23, 2026
```
Signed-off-by: raushan <raushan@huggingface.co>
```
  d95d6507
- [Feature]: Remove DtoH Copy for lfm2_vl On Default Stream (#32815) · 13d8746c
  tianshu-Michael-yu authored Jan 23, 2026
```
Signed-off-by: Tianshu Yu <tianshuyu.formal@gmail.com>
```
  13d8746c
- [Voxtral] Add new streaming arch (#32861) · 3f3f8952
  Patrick von Platen authored Jan 23, 2026
```
Signed-off-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  3f3f8952
- [CI/Build][CPU] Fix failed pooling tests and macos smoke test (#32907) · 5da4c7d7
  Li, Jiang authored Jan 23, 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>
```
  5da4c7d7
- [CI][Models] Add VLM Support for Sequence Classification Conversion (#32885) · a8eb1182
  Andreas Karatzas authored Jan 23, 2026
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  a8eb1182
- [Bugfix] Fix _CPU_MOE_ACT AssertionError when vLLM config not set (#32777) · fa6e599a
  Karan Bansal authored Jan 23, 2026
```
Signed-off-by: Karan Bansal <karanb192@gmail.com>
```
  fa6e599a
- [torch.compile] Compile `CustomOp.forward_native` for `SiluAndMul` and... · 5e4e0e51
  Luka Govedič authored Jan 22, 2026
```
[torch.compile] Compile `CustomOp.forward_native` for `SiluAndMul` and `QuantFP8` to avoid raw torch ops inside opaque custom ops (#32806)
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
  5e4e0e51
22 Jan, 2026 9 commits
- [MoE Refactor] Move `select_experts` from `FusedMoEQuantMethod` -> `FusedMoE` (#31996) · dc917cce
  bnellnm authored Jan 22, 2026
```
Signed-off-by: Bill Nell <bnell@redhat.com>
```
  dc917cce
- [BugFix] Fix invalid flashinfer_fused_moe_blockscale_fp8 op registration (#32855) · fc56f4a0
  Fadi Arafeh authored Jan 22, 2026
```
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
```
  fc56f4a0
- [Perf] Create TMA-aligned input scale tensor for DeepGemm on Hopper (#32619) · d08b356e
  Xin Yang authored Jan 22, 2026
```
Signed-off-by: Xin Yang <xyangx@amazon.com>
```
  d08b356e
- Add llmcompressor fp8 kv-cache quant (per-tensor and per-attn_head) (#30141) · 44f08af3
  Eldar Kurtić authored Jan 22, 2026
```
Signed-off-by: Eldar Kurtic <8884008+eldarkurtic@users.noreply.github.com>
Signed-off-by: eldarkurtic <8884008+eldarkurtic@users.noreply.github.com>
```
  44f08af3
- [Bugfix][Attention] Explicitly report support for kv_cache_dtype bfloat16 (#32795) · 955b43a5
  Matthew Bonanni authored Jan 22, 2026
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  955b43a5
- Support bge-m3 sparse embeddings and colbert embeddings (#14526) · ff365eea
  Maximilien de Bayser authored Jan 22, 2026
```
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Signed-off-by: Max de Bayser <maxdebayser@gmail.com>
```
  ff365eea
- [torch.compile] Improve Cold Start for MoEs (#32805) · 654a71fc
  Richard Zou authored Jan 22, 2026
```
Signed-off-by: Richard Zou <zou3519@gmail.com>
```
  654a71fc
- [AMD][ROCm] MoRI EP: a high-performance all2all backend (#28664) · 49a12622
  Alex Sun authored Jan 22, 2026
```
Signed-off-by: Alex Sun <alex.s@amd.com>
```
  49a12622
- [Model] Extend `collect_children` and `no_init_weights` contexts (#32757) · 2b8a38b6
  Cyrus Leung authored Jan 22, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  2b8a38b6