Commits · 58cfe0dc44b29ced86cf8a6db069e55faf5d4f7d · OpenDAS / vllm_cscc

04 Mar, 2026 14 commits

Fix phi4-mm and remove cuda binding (#35964) · 58cfe0dc
Yan Ma authored Mar 05, 2026
```
Signed-off-by: Yan Ma <yan.ma@intel.com>
```
58cfe0dc
Use MMEncoderAttention (=use FlashAttention) instead of torch.sdpa in radio.py (#35653) · 289fc48a
Netanel Haber authored Mar 04, 2026

289fc48a

[Core] Add All-to-All communication backend for DCP (#34883) · 6cb90109

sungsoo ha authored Mar 04, 2026


Signed-off-by: Sungsoo Ha <sungsooh@nvidia.com>
Signed-off-by: sungsoo ha <hasungsoo@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

6cb90109

[Bugfix][Model] Fix FP8 k_scale/v_scale not loaded for Qwen3-MoE (#35656) · c8c3935b
Raghavan authored Mar 04, 2026
```
Signed-off-by: raghavan <oneraghavan@gmail.com>
```
c8c3935b

[Hardware] Replace `torch.cuda.empty_cache` with `torch.accelerator.empty_cache` (#30681) · 16d2ad1d

Kunshang Ji authored Mar 04, 2026


Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Signed-off-by: Kunshang Ji <jikunshang95@gmail.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

16d2ad1d

[ROCm][Bugfix] Fall back from CK MXFP4 MoE when GEMM dimensions are unsupported (#35893) · 5dc35387
Chuan (Richard) Li authored Mar 04, 2026
```
Signed-off-by: Li <chuali@amd.com>
```
5dc35387

[Bugfix] Add missing dynamic_arg_dims for Qwen3-ASR torch.compile (#35869) · 36bf2131

Nathan Price authored Mar 04, 2026


Signed-off-by: Nathan Price <nathan@abridge.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>

36bf2131

Support Audio Extraction from MP4 Video for Nemotron Nano VL (#35539) · 5d199ac8

Andrii Skliar authored Mar 04, 2026


Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
Signed-off-by: Andrii Skliar <askliar@nvidia.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Signed-off-by: Andrii <askliar@nvidia.com>
Co-authored-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
Co-authored-by: Andrii Skliar <askliar@oci-nrt-cs-001-vscode-01.cm.cluster>
Co-authored-by: Andrii <askliar@nvidia.com>
Co-authored-by: root <root@pool0-03748.cm.cluster>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: root <root@pool0-02416.cm.cluster>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.com>
Co-authored-by: root <root@pool0-04880.cm.cluster>

5d199ac8

[Bugfix] Guard mm_token_type_ids kwarg in get_mrope_input_positions (#35711) · edba1504
Andreas Karatzas authored Mar 03, 2026
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
edba1504
[Chore] Remove debug code in model implementation (#35883) · 6e9f21e8
Isotr0py authored Mar 04, 2026
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
6e9f21e8

[model] support FireRedASR2 (#35727) · c1d96340

AllenDou authored Mar 04, 2026


Signed-off-by: zixiao <shunli.dsl@alibaba-inc.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: zixiao <shunli.dsl@alibaba-inc.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>

c1d96340

[PluggableLayer][MM] Add PluggableLayer for RelPosAttention (#33753) · 77e6dcbb
Shanshan Shen authored Mar 04, 2026
```
Signed-off-by: shen-shanshan <467638484@qq.com>
```
77e6dcbb
[Bugfix] Fix EVS implementation for Qwen3 VL (#33607) · 70c73df6
William Zhang authored Mar 03, 2026
```
Signed-off-by: 2ez4bz <133824995+2ez4bz@users.noreply.github.com>
```
70c73df6

Enable bnb for multiple indices weight (#35838) · 9a9d4424

xjx authored Mar 04, 2026


Signed-off-by: xjx <493337577@qq.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>

9a9d4424

03 Mar, 2026 6 commits
- [Bugfix] Fix misnamed parameter in compressed_tensors_moe.py (#35813) · a9b8b13e
  bnellnm authored Mar 03, 2026
```
Signed-off-by: Bill Nell <bnell@redhat.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
```
  a9b8b13e
- [MoE Refactor] Create MK for TRTLLM Kernels (#32564) · 97995f63
  Robert Shaw authored Mar 03, 2026
```
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Signed-off-by: Robert Shaw <rshaw@neuralmagic.com>
Signed-off-by: Robert Shaw <robertgshaw2@gmail.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <rshaw@neuralmagic.com>
```
  97995f63
- [BugFix] Add support for MTP num_speculative_tokens > 1 with sparse MLA (#34552) · 28ef9ba3
  Lucas Wilkinson authored Mar 03, 2026
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
```
  28ef9ba3
- [Misc] Fix typos in comments: explict→explicit, paramaters→parameters (#35648) · 35a6f0bf
  lin-shh authored Mar 03, 2026
  
  35a6f0bf
- [V0 deprecation] Remove Swin model (#35821) · 8ea8ba27
  Isotr0py authored Mar 03, 2026
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  8ea8ba27
- [Model] Add support for nvidia/llama-nemotron-rerank-vl-1b-v2 (#35735) · c8b678e5
  Jakub Zakrzewski authored Mar 03, 2026
```
Signed-off-by: Jakub Zakrzewski <jzakrzewski@nvidia.com>
```
  c8b678e5
02 Mar, 2026 7 commits
- [MoE][Perf] Wrap DSV3 QKVAProj GEMM in custom op for torch.compile (#35751) · 9319044e
  Robert Shaw authored Mar 02, 2026
```
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
```
  9319044e
- [Bugfix] Fix missing sequence_lengths in qwen3_omni_moe_thinker (#35741) · fa6a6be5
  Ye (Charlotte) Qi authored Mar 02, 2026
```
Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com>
```
  fa6a6be5
- [Spec Decode] Add hidden states extraction system (#33736) · 9433acb8
  Fynn Schmitt-Ulms authored Mar 02, 2026
```
Signed-off-by: Fynn Schmitt-Ulms <fschmitt@redhat.com>
```
  9433acb8
- [BugFix][Model]Fix the garbled code in Ernie4.5-VL caused by fast_moe_cold_start (#35587) · 2a9e3347
  CSWYF3634076 authored Mar 03, 2026
```
Signed-off-by: wangyafeng <wangyafeng@baidu.com>
```
  2a9e3347
- [Core] Move test utility to test file (#35672) · 4034c3d3
  Turner Jabbour authored Mar 02, 2026
```
Signed-off-by: Turner Jabbour <doubleujabbour@gmail.com>
```
  4034c3d3
- [Performance] Extract kv update ops from MLA attention backends (#34627) · d9c77308
  ElizaWszola authored Mar 02, 2026
```
Signed-off-by: ElizaWszola <ewszola@redhat.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Di Wu <dw2761@nyu.edu>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
```
  d9c77308
- [XPU] fix mxfp4 activation type (#35691) · 92f5d0f0
  Kunshang Ji authored Mar 02, 2026
```
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
```
  92f5d0f0
01 Mar, 2026 7 commits
- [Attention] FA4 integration (#32974) · 8b5014d3
  Lucas Wilkinson authored Mar 01, 2026
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
```
  8b5014d3
- [torch.compile] Undo the fast_moe_cold_start hack in torch>=2.11 (#35475) · e82fbeec
  Richard Zou authored Mar 01, 2026
```
Signed-off-by: Richard Zou <zou3519@gmail.com>
```
  e82fbeec
- [Bugfix] Fix dtype mismatch in RMSNormGated.forward_native() during torch.compile (#35256) · 62904708
  haosdent authored Mar 02, 2026
```
Signed-off-by: haosdent <haosdent@gmail.com>
```
  62904708
- fix(mxfp4): return is_monolithic=False when LoRA is enabled for Triton backend (#35382) · 5a435507
  Seungho Yoon authored Mar 01, 2026
```
Signed-off-by: Seungho Yoon <yoonsnowdev@gmail.com>
```
  5a435507
- [Mamba1] - Kernel Level Chunk Alignment for Prefix Caching (#34798) · bbf81f9a
  Asaf Gardin authored Mar 01, 2026
```
Signed-off-by: Josephasafg <ajgard7@gmail.com>
```
  bbf81f9a
- Fix typo: implictly -> implicitly in isaac.py docstring (#35646) · a9ec392c
  lin-shh authored Mar 01, 2026
  
  a9ec392c
- [Bugfix][Model] Fix Qwen3.5/Qwen3Next ignoring --dtype flag on older GPUs (#35617) · afd089f2
  lailoo authored Mar 01, 2026
  
  afd089f2
28 Feb, 2026 6 commits

[Chore] Cleanup BNB utilization dead code (#35620) · e94b263b
Isotr0py authored Mar 01, 2026
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
e94b263b

[Deprecation] Deprecate code in 0.17 as scheduled (#35441) · e113a301

Wentao Ye authored Feb 28, 2026


Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

e113a301

Fix Qwen3_5MTP packed_modules_mapping for gate_up_proj (#35581) · 63d7972f
cwazai authored Feb 28, 2026

63d7972f
[Feat] Add CUDA torch fallbacks for fp8_mqa_logits/fp8_paged_mqa_logits_torch function (#35271) · 7e08c22b
Chauncey authored Feb 28, 2026
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
7e08c22b
Add padding support to wvSplitK solution for skinny GEMMs (#33762) · 7600642e
Hashem Hashemi authored Feb 28, 2026
```
Signed-off-by: Hashem Hashemi <hashem.hashemi@amd.com>
```
7600642e

[1/N] Elastic EP Milestone 2 (#34861) · dea26833

Itay Alroy authored Feb 28, 2026


Signed-off-by: Yongji Wu <wuyongji317@gmail.com>
Signed-off-by: Itay Alroy <ialroy@nvidia.com>
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Signed-off-by: Ron Tourgeman <rtourgeman@nvidia.com>
Co-authored-by: Yongji Wu <wuyongji317@gmail.com>
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Ron Tourgeman <rtourgeman@nvidia.com>

dea26833