Commits · 6fa6e7ef0c9b485e8a684211e96691731aad6faa · OpenDAS / vllm_cscc

13 Jan, 2026 6 commits
- [Kernel][Performance] Enable smaller Scaling Factor tiling for NVFP4 small-batch decoding (#30885) · 8ef50d9a
  Roberto L. Castro authored Jan 14, 2026
```
Signed-off-by: LopezCastroRoberto <roberto.lopez.castro@udc.es>
Signed-off-by: Roberto L. Castro <38211239+LopezCastroRoberto@users.noreply.github.com>
Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
```
  8ef50d9a
- [4/N][Attention] Move MLA common to model_executor (#32060) · 2263d44b
  Matthew Bonanni authored Jan 13, 2026
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
```
  2263d44b
- [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
- [Quantization] fix: overflow with static per-tensor scaling (#29867) · a5bbbd2f
  Mickaël Seznec authored Jan 13, 2026
```
Signed-off-by: Mickael Seznec <mickael@mistral.ai>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
  a5bbbd2f
- [Bugfix] Replace `PoolingParams.normalize` with `use_activation` (#32243) · 232214b2
  Cyrus Leung authored Jan 13, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  232214b2
- [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
12 Jan, 2026 6 commits

[Kernel][MoE] fix computation order of MoE weight multiplication and improve flow (#31962) · 629584bf
xuebwang-amd authored Jan 13, 2026
```
Signed-off-by: xuebwang-amd <xuebwang@amd.com>
```
629584bf
[Misc][BE] Type coverage for vllm/compilation [3/3] (#31748) · ad8818bb
Lucas Kabela authored Jan 12, 2026
```
Signed-off-by: Lucas Kabela <lucaskabela@meta.com>
```
ad8818bb
[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

[FIX] Add NO_MUL activation support for modular kernel path (#31528) · 3f72639d

danielafrimi authored Jan 12, 2026


Signed-off-by: dafrimi <dafrimi@nvidia.com>
Signed-off-by: <>
Co-authored-by: root <root@gpu-267.slurm-workers-slurm.slurm.svc.cluster.local>
Co-authored-by: root <root@gpu-537.slurm-workers-slurm.slurm.svc.cluster.local>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: root <root@pool0-01777.cm.cluster>

3f72639d

[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

11 Jan, 2026 1 commit
- [Hardware][AMD][CI][Bugfix] Fix AMD Quantization test group (#31713) · bde57ab2
  Matt authored Jan 11, 2026
```
Signed-off-by: Matthew Wong <Matthew.Wong2@amd.com>
```
  bde57ab2
10 Jan, 2026 6 commits
- [Bugfix][Quantization] Ensure input contiguity in per_token_quant_int8 (#31637) · 6ea001cf
  Vensen authored Jan 11, 2026
```
Signed-off-by: vensen <vensenmu@gmail.com>
```
  6ea001cf
- fused_moe_kernel - cast accumulator after applying router weights (#32002) · d1fd802f
  gnovack authored Jan 10, 2026
```
Signed-off-by: gnovack <gnovack@amazon.com>
```
  d1fd802f
- [Quant] Support MXFP4 W4A16 for compressed-tensors dense models (#31926) · e6c6f2c7
  Michael Goin authored Jan 10, 2026
```
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
```
  e6c6f2c7
- [Refactor] Separate sequence and token pooling types (#32026) · 583a90e0
  Cyrus Leung authored Jan 10, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  583a90e0
- [Core] Refactor ColumnParallelLinear: remove unused parameter and optimize forward (#31939) · 52d42829
  maang authored Jan 10, 2026
```
Signed-off-by: maang <maang_h@163.com>
```
  52d42829
- [Misc][LLaMa4] Compile LLaMa Vision Encoder (#30709) · ea6d067a
  Lucas Kabela authored Jan 09, 2026
```
Signed-off-by: Lucas Kabela <lucaskabela@meta.com>
```
  ea6d067a
09 Jan, 2026 13 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
[Quant] Make static quant support all group shapes (#30833) · 0a0aa077
Lucas Wilkinson authored Jan 09, 2026
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
0a0aa077
[fix] add cutedsl to global sf (#32001) · f9e2a75a
jiahanc authored Jan 09, 2026
```
Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
```
f9e2a75a
Add unpermute-aware fused MoE path and small-batch fallback (#29354) · a4d5d663
Runkai Tao authored Jan 09, 2026
```
Signed-off-by: Runkai Tao <rt572@physics.rutgers.edu>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
```
a4d5d663

[Perf] Optimize cutlass moe problem size calculation, 5.3% E2E Throughput... · 308feab3

Wentao Ye authored Jan 09, 2026


[Perf] Optimize cutlass moe problem size calculation, 5.3% E2E Throughput improvement, 2.2% TTFT improvement (#31830)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>

308feab3

[UX] Add vLLM model inspection view (#29450) · d5ec6c05
Michael Goin authored Jan 09, 2026
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
d5ec6c05
[Doc] Add developer guide for CustomOp (#30886) · 08d954f0
Shanshan Shen authored Jan 10, 2026
```
Signed-off-by: shen-shanshan <467638484@qq.com>
```
08d954f0
[Perf][Kernel] Fused SiLU+Mul+Quant kernel for NVFP4 cutlass_moe (#31832) · 34cd32fe
Michael Goin authored Jan 09, 2026
```
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
```
34cd32fe
[Bugfix] Fix Triton FusedMoE LoRA (#30585) · e7b68f4d
Xin Yang authored Jan 09, 2026
```
Signed-off-by: Xin Yang <xyangx@amazon.com>
```
e7b68f4d
[Model] Reorganize pooling layers (#31973) · c8ed39b9
Cyrus Leung authored Jan 09, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
c8ed39b9

[Bugfix] Fix Typo from NVFP4 Refactor (#31977) · 0fa8dd24

Robert Shaw authored Jan 08, 2026


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

0fa8dd24

[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

[MoE Refactoring][Bugfix]Wrap WNA16 Triton kernel into mk and change... · d62cfe54

Yongye Zhu authored Jan 08, 2026


[MoE Refactoring][Bugfix]Wrap WNA16 Triton kernel into mk and change compressed tensor kernel selection (#31752)
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>

d62cfe54

08 Jan, 2026 8 commits
- [Misc] Fix `Current vLLM config is not set.` warnings, assert to avoid issues... · 6cdf015c
  Lucas Wilkinson authored Jan 08, 2026
```
[Misc] Fix `Current vLLM config is not set.` warnings, assert to avoid issues in the future (#31747)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
```
  6cdf015c
- [Compressed-Tensors] Simplify NVFP4 Conditions, enable marlin support for NVFP4A16 MoEs (#30881) · 5d3b6097
  Dipika Sikka authored Jan 08, 2026
  
  5d3b6097
- [Misc][Refactor] Add FusedMoERouter object (#30519) · e74698c2
  bnellnm authored Jan 08, 2026
```
Signed-off-by: Bill Nell <bnell@redhat.com>
```
  e74698c2
- Revert "feat(moe): Add is_act_and_mul=False support for Triton MoE kernels" (#31978) · 87e07a6b
  Michael Goin authored Jan 08, 2026
  
  87e07a6b
- [Bugfix] Fix vllm serve failure with Nemotron Nano V3 FP8 (#31960) · b8112c1d
  danisereb authored Jan 08, 2026
```
Signed-off-by: Daniel Serebrenik <daserebrenik@nvidia.com>
```
  b8112c1d
- [Chore] Further cleanup pooler (#31951) · d1b6fe00
  Cyrus Leung authored Jan 08, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  d1b6fe00
- [ROCm][LoRA] Fix MoE accuracy regression by preserving float32 router weight scaling (#31931) · c4041f37
  Andreas Karatzas authored Jan 07, 2026
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  c4041f37
- [MoE Refactor][16/N] Apply Refactor to NVFP4 (#31692) · 9f6dcb71
  Robert Shaw authored Jan 07, 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: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Pavani Majety <pmajety@nvidia.com>
```
  9f6dcb71