Commits · c277fbdf31f49c15049fe361ef92a7e34abc7b74 · OpenDAS / vllm_cscc

16 Jan, 2026 1 commit

[Feat] Support non-gated MoE with Marlin, NVFP4 CUTLASS, FP8, INT8, compressed-tensors (#32257) · c277fbdf

TomerBN-Nvidia authored Jan 16, 2026


Signed-off-by: Tomer Natan <tbarnatan@computelab-frontend-8.nvidia.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Tomer Natan <tbarnatan@computelab-frontend-8.nvidia.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Tomer Natan <tbarnatan@ipp1-1429.ipp1a1.colossus.nvidia.com>

c277fbdf

15 Jan, 2026 2 commits

[ROCM] DSfp4 mla projection gemms weight dynamic quantization (#32238) · 8c11001b
Aleksandr Malyshev authored Jan 15, 2026
```
Signed-off-by: Aleksandr Malyshev <maleksan@amd.com>
Co-authored-by: Aleksandr Malyshev <maleksan@amd.com>
```
8c11001b

[ROCm][Perf] Enable shuffle kv cache layout and assembly paged attention... · 130d6c95

Pleaplusone authored Jan 15, 2026


[ROCm][Perf] Enable shuffle kv cache layout and assembly paged attention kernel for `AiterFlashAttentionBackend` (#29887)
Signed-off-by: ganyi <ygan@amd.com>

130d6c95

13 Jan, 2026 1 commit

[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

11 Jan, 2026 1 commit
- [CPU][BugFix] Disable AOT Compile for CPU (#32037) · 9103ed16
  Fadi Arafeh authored Jan 11, 2026
```
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
```
  9103ed16
09 Jan, 2026 3 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
- [UX] Add vLLM model inspection view (#29450) · d5ec6c05
  Michael Goin authored Jan 09, 2026
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  d5ec6c05
- [ROCm][PD] add moriio kv connector. (#29304) · 4505849b
  inkcherry authored Jan 09, 2026
```
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
```
  4505849b
07 Jan, 2026 1 commit

[Perf][Kernels] Enable FlashInfer DeepGEMM swapAB on SM90 (for W8A8 Linear Op) (#29213) · cc6dafae

Kate Cheng authored Jan 07, 2026


Signed-off-by: Kate Cheng <yunhsuanc@nvidia.com>
Signed-off-by: Jhao-Ting Chen <jhaotingc@nvidia.com>
Co-authored-by: Jhao-Ting Chen <jhaotingc@nvidia.com>

cc6dafae

05 Jan, 2026 1 commit
- [Bug] Revert torch warning fix (#31585) · af9a7ec2
  Wentao Ye authored Jan 05, 2026
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  af9a7ec2
19 Dec, 2025 1 commit
- Make engine core client handshake timeout configurable (#27444) · 1ab52135
  Seiji Eicher authored Dec 19, 2025
```
Signed-off-by: Seiji Eicher <seiji@anyscale.com>
```
  1ab52135
18 Dec, 2025 2 commits

Remove all2all backend envvar (#30363) · 41b6f920

Elizabeth Thomas authored Dec 18, 2025

Signed-off-by: Elizabeth Thomas <email2eliza@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

41b6f920

[Metrics] Model FLOPs Utilization estimation (#30738) · a0b782f9

SungMinCho authored Dec 17, 2025


Signed-off-by: SungMinCho <tjdals4565@gmail.com>
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
Co-authored-by: Mark McLoughlin <markmc@redhat.com>

a0b782f9

17 Dec, 2025 1 commit
- [compile] Ignore VLLM_FORCE_AOT_LOAD from cache factors (#30809) · 9db1db59
  Zhengxu Chen authored Dec 17, 2025
```
Signed-off-by: zhxchen17 <zhxchen17@fb.com>
```
  9db1db59
16 Dec, 2025 1 commit
- [Attention] Cache attention metadata builds across hybrid KV-cache groups (#29627) · 9fec0e13
  Lucas Wilkinson authored Dec 16, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Stanislaw Wozniak <stw@zurich.ibm.com>
```
  9fec0e13
12 Dec, 2025 1 commit
- [Attention] Use sparse prefill kernel for fp8 kv-cache in DeepSeek-v3.2 (#27532) · 3e41992f
  Lucas Wilkinson authored Dec 12, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
  3e41992f
11 Dec, 2025 2 commits
- [Chore] Fix torch precision warning (#30428) · d6464f26
  Wentao Ye authored Dec 10, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  d6464f26
- [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
10 Dec, 2025 1 commit

[Perf] Enable environment cache in EngineCore to enable the feature for... · 9f042ba2

Jialin Ouyang authored Dec 10, 2025


[Perf] Enable environment cache in EngineCore to enable the feature for UniProcExecutor as well (#29289)
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>

9f042ba2

09 Dec, 2025 3 commits

[Cleanup] Refactor profiling env vars into a CLI config (#29912) · e858bfe0

Benjamin Chislett authored Dec 09, 2025

Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
Signed-off-by: Benjamin Chislett <chislett.ben@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

e858bfe0

[Compile] Fix torch warning `TensorFloat32 tensor cores for float32 matrix... · 83319b44

Wentao Ye authored Dec 09, 2025


[Compile] Fix torch warning `TensorFloat32 tensor cores for float32 matrix multiplication available but not enabled` (#29897)
Signed-off-by: yewentao256 <zhyanwentao@126.com>

83319b44

[moe] Allow disabling DP chunking (#29936) · 9d6235ca
Ming Yang authored Dec 08, 2025
```
Signed-off-by: Ming Yang <minos.future@gmail.com>
```
9d6235ca

04 Dec, 2025 1 commit

[P/D] Introduce Mooncake Transfer Engine as kv_connector (#24718) · 842aba50

dtc authored Dec 04, 2025


Signed-off-by: Tianchen Ding <dtcccc@linux.alibaba.com>
Signed-off-by: dtc <dtcccc@linux.alibaba.com>
Co-authored-by: Nicolò Lucchesi <nicolo.lucchesi@gmail.com>

842aba50

03 Dec, 2025 3 commits

[CI] fix docker image build by specifying merge-base commit id when... · 1109f982

Shengqi Chen authored Dec 04, 2025


[CI] fix docker image build by specifying merge-base commit id when downloading pre-compiled wheels (#29930)
Signed-off-by: Shengqi Chen <harry-chen@outlook.com>

1109f982

[Bugfix] Respect VLLM_CONFIGURE_LOGGING value (#28671) · b5407869

Elizabeth Thomas authored Dec 03, 2025


Signed-off-by: Elizabeth Thomas <email2eliza@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Signed-off-by: Jane Xu <janeyx@meta.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: Johnny Yang <johnnyyang@google.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: bruceszchen <bruceszchen@tencent.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Jane (Yuan) Xu <31798555+janeyx99@users.noreply.github.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Johnny Yang <24908445+jcyang43@users.noreply.github.com>

b5407869

[docker] Build CUDA kernels in separate Docker stage for faster rebuilds (#29452) · f5d3d93c
Amr Mahdi authored Dec 03, 2025
```
Signed-off-by: Amr Mahdi <amrmahdi@meta.com>
```
f5d3d93c

02 Dec, 2025 2 commits
- [responsesAPI][3] ResponsesParser to set up non harmony MCP (#29413) · 52cb349f
  Andrew Xia authored Dec 02, 2025
```
Signed-off-by: Andrew Xia <axia@fb.com>
Co-authored-by: Andrew Xia <axia@fb.com>
```
  52cb349f
- [CI] Renovation of nightly wheel build & generation (take 2) (#29838) · 4b612664
  Shengqi Chen authored Dec 02, 2025
```
Signed-off-by: Shengqi Chen <harry-chen@outlook.com>
```
  4b612664
01 Dec, 2025 4 commits
- Revert #29787 and #29690 (#29815) · 1336a1ea
  Kevin H. Luu authored Dec 01, 2025
  
  1336a1ea
- [CI] Renovation of nightly wheel build & generation (#29690) · 36db0a35
  Shengqi Chen authored Dec 01, 2025
```
Signed-off-by: Shengqi Chen <harry-chen@outlook.com>
```
  36db0a35
- Make PyTorch profiler gzip and CUDA time dump configurable (#29568) · 1ab8fc81
  Yifei Zhang authored Dec 01, 2025
```
Signed-off-by: Yifei Zhang <yifei.zhang1992@outlook.com>
```
  1ab8fc81
- [MoE] CuteDSL MoE with Nvfp4 DeepEP dispatch (#27141) · f72a817b
  Shu Wang authored Nov 30, 2025
```
Signed-off-by: Shu Wang <shuw@nvidia.com>
Signed-off-by: Shu Wang. <shuw@nvidia.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: root <root@umbriel-b200-017.ipp4a1.colossus.nvidia.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
  f72a817b
29 Nov, 2025 1 commit

[Kernel][Quantization] add w4a8 support for marlin kernel (#24722) · 1656ad37

Jinzhen Lin authored Nov 29, 2025


Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Signed-off-by: Jinzhen Lin <linjinzhen@hotmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Michael Goin <mgoin@redhat.com>

1656ad37

28 Nov, 2025 1 commit

[Rocm] Set VLLM_ROCM_USE_AITER_FUSION_SHARED_EXPERTS default is disabled (#28985) · 3cb32e5d

杰兮 authored Nov 28, 2025


Signed-off-by: zhyajie <yajizhan@amd.com>
Co-authored-by: zhyajie <yajizhan@amd.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>

3cb32e5d

24 Nov, 2025 1 commit
- [Core] Deprecate `xformers` (#29262) · 0ff70821
  Roger Wang authored Nov 23, 2025
```
Signed-off-by: Roger Wang <hey@rogerw.io>
```
  0ff70821
21 Nov, 2025 2 commits

[BugFix] Make sure to allocate worst case MoE workspace during profile run in... · 1840c5cb

Lucas Wilkinson authored Nov 21, 2025


[BugFix] Make sure to allocate worst case MoE workspace during profile run in the DP + EP case (#27426)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>

1840c5cb

GPU Model Runner V2 (#25266) · 30b44a15
Woosuk Kwon authored Nov 21, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
30b44a15

20 Nov, 2025 2 commits

[Feat] Iteration-level profiling for Torch and CUDA profiler (#28987) · fcbcba6c

Benjamin Chislett authored Nov 19, 2025

fcbcba6c

[Misc] Colorize logs (#29017) · 9ccef8e3
Nick Hill authored Nov 19, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
9ccef8e3

19 Nov, 2025 1 commit

[MoE] Nvfp4 Masked Gemm: Add flashinfer grouped_gemm_nt_masked (#25990) · 613abb50

Shu Wang authored Nov 19, 2025


Signed-off-by: Shu Wang. <shuw@nvidia.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>

613abb50