Commits · 83c9d525b623566f45d161593e7610cb65aaad60 · OpenDAS / vllm_cscc

"tests/vscode:/vscode.git/clone" did not exist on "6d42ce83155d42f04643c1fa54eaed8abf8170c2"

24 Mar, 2026 3 commits
- [CI] Add batch invariant test: Block FP8 + small MOE (#37895) · 83c9d525
  Wentao Ye authored Mar 23, 2026
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  83c9d525
- [Model Runner V2] Gather multimodal embeddings before draft model postprocess (#37932) · 8f4824b6
  Giancarlo Delfin authored Mar 23, 2026
```
Signed-off-by: Giancarlo Delfin <gdelfin@inferact.ai>
```
  8f4824b6
- [Test] E2E Nemotron-3-Super tests (#36803) · 56777b5c
  roikoren755 authored Mar 24, 2026
```
Signed-off-by: Roi Koren <roik@nvidia.com>
```
  56777b5c
23 Mar, 2026 31 commits
- [CI] Split V1 Others into 3 separate jobs (#37016) · 2488a82f
  Kevin H. Luu authored Mar 23, 2026
```
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
```
  2488a82f
- [Bugfix] Register VLLM_BATCH_INVARIANT in envs.py to fix spurious unknown env var warning (#35007) · dc6908ac
  Ranran authored Mar 23, 2026
```
Signed-off-by: Ranran <1012869439@qq.com>
Signed-off-by: Ranran <hzz5361@psu.edu>
Signed-off-by: ran <hzz5361@psu.edu>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
```
  dc6908ac
- [Bug][MoE] Strengthen _supports_current_device() checks in the TRTLLM FP8,... · e85f8f09
  yzong-rh authored Mar 23, 2026
```
[Bug][MoE] Strengthen _supports_current_device() checks in the TRTLLM FP8, NVFP4, and FlashInfer CuteDSL MoE experts (#36728)
Signed-off-by: Yifan Zong <yzong@redhat.com>
```
  e85f8f09
- [Bug][MoE] Fix TRTLLM NVFP4 Routing Kernel Precision (#36725) · 5bf3c42d
  Robert Shaw authored Mar 23, 2026
```
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
```
  5bf3c42d
- [Sparse24] [Deprecation] Remove Sparse24 CT integration and kernels (#36799) · 38364a7e
  Kyle Sayers authored Mar 23, 2026
```
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
```
  38364a7e
- [Async][Spec Decoding] Zero-bubble async scheduling + spec decoding (#32951) · fafe76b4
  Matthew Bonanni authored Mar 23, 2026
```
Signed-off-by: zhuhaoran <zhuhaoran.zhr@alibaba-inc.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: zhuhaoran <zhuhaoran.zhr@alibaba-inc.com>
Co-authored-by: zhrrr <43847754+izhuhaoran@users.noreply.github.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Benjamin Chislett <chislett.ben@gmail.com>
```
  fafe76b4
- [MRV2] Consider spec decoding in warmup (#37812) · ffb5b32b
  Woosuk Kwon authored Mar 23, 2026
```
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
```
  ffb5b32b
- [CI] split Entrypoints Integration (API Server 1) into 3 jobs (#37882) · 91fd695b
  Kunshang Ji authored Mar 24, 2026
```
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
```
  91fd695b
- [CI][PD] Add Hybrid SSM integration tests to CI (#37657) · 1cbbcfe8
  Nicolò Lucchesi authored Mar 23, 2026
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  1cbbcfe8
- Use lazy graph module during split_module to defer recompile() (#37609) · aceadb5e
  Angela Yi authored Mar 23, 2026
```
Signed-off-by: angelayi <yiangela7@gmail.com>
```
  aceadb5e
- [Bugfix] Fix RoBERTa position_ids accumulation on CUDA graph padding (#37884) · ec228061
  Yufeng He authored Mar 23, 2026
  
  ec228061
- [Bugfix] RoBERTa position_id accumulation in CUDA graph padding region (#37873) · 7151ae65
  yanghui1-arch authored Mar 23, 2026
```
Signed-off-by: dass90 <3053034939@qq.com>
```
  7151ae65
- [Mypy] Fix mypy for `vllm/config` (#37808) · 45bd5c8e
  Wentao Ye authored Mar 23, 2026
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  45bd5c8e
- [ROCm] fix sleep mode not releasing GPU memory problem on ROCm (#37533) · 10a1018c
  Zhaodong Bing authored Mar 23, 2026
```
Signed-off-by: bingzhaodong <aaab8b@gmail.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
```
  10a1018c
- [Bugfix][LoRA] Fix incorrect LoRA Log (#37877) · aec2dc6c
  Jee Jee Li authored Mar 23, 2026
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  aec2dc6c
- [Bugfix] Fix CPU backend crash in KV cache block zeroing (#37550) · 7938d121
  DorBernsohn authored Mar 23, 2026
```
Signed-off-by: DorBernsohn <dor.bernsohn@gmail.com>
```
  7938d121
- [XPU][MoE Refactor] Refactor xpu mxfp4 support into oracle (#37784) · debd6e76
  Kunshang Ji authored Mar 23, 2026
```
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
```
  debd6e76
- [Frontend][Responses API] Fix arrival_time recording for TTFT on initial request (#37498) · 9ace378a
  Andrew Xia authored Mar 23, 2026
```
Signed-off-by: Andrew Xia <axia@meta.com>
```
  9ace378a
- [FP8]add FP8 WoQ kernel abstraction. (#32929) · 27d5ee3e
  Kunshang Ji authored Mar 23, 2026
```
Signed-off-by: Zhu, Zufang <zufang.zhu@intel.com>
```
  27d5ee3e
- [Misc]Update gitignore (#37863) · 35141a7e
  wangxiyuan authored Mar 23, 2026
```
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
```
  35141a7e
- [ROCm] Fix fused_moe_fake signature mismatch and other AITER bugs (#36100) · e99fb988
  Chuan (Richard) Li authored Mar 23, 2026
```
Signed-off-by: Li <chuali@amd.com>
```
  e99fb988
- [Perf] [Bugfix] Fix Triton autotuning in inference for Qwen3.5 (#37338) · a16133a0
  Artem Perevedentsev authored Mar 23, 2026
```
Signed-off-by: Artem Perevedentsev <aperevedents@nvidia.com>
```
  a16133a0
- [Bugfix] Store Qwen3Next A_log in fp32 (#37810) · 54ab804e
  Hojin Yang authored Mar 23, 2026
```
Signed-off-by: effortprogrammer <yhjhoward7@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
```
  54ab804e
- [Bugfix] JAIS: Only apply ALiBi when position_embedding_type='alibi' (#37820) · 02e6efe5
  r266-tech authored Mar 23, 2026
```
Co-authored-by: r266-tech <r266-tech@users.noreply.github.com>
```
  02e6efe5
- [ROCm][Refactor] Enable AWQMarlinConfig on ROCm to use choose_mp_linear_kernel (#36505) · 410d3008
  Matthias Gehre authored Mar 23, 2026
```
Signed-off-by: Matthias Gehre <matthias.gehre@amd.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
  410d3008
- update doc for online fp8 quantization (#37851) · d3fe8571
  Yan Ma authored Mar 23, 2026
```
Signed-off-by: Yan Ma <yan.ma@intel.com>
```
  d3fe8571
- [Feature] ViT Full CUDA Graph (#35963) · f85e479e
  Baorun (Lauren) Mu authored Mar 23, 2026
```
Signed-off-by: Baorun Mu <bmu@nvidia.com>
```
  f85e479e
- [CI/Build][LoRA] Update Qwen35 LoRA testing (#37816) · 1f0d2106
  Jee Jee Li authored Mar 23, 2026
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  1f0d2106
- [Test] Consolidate tool parser unit tests to tests/tool_parsers (#37834) · 3bbe2e1e
  Ben Browning authored Mar 23, 2026
```
Signed-off-by: Ben Browning <bbrownin@redhat.com>
```
  3bbe2e1e
- always use `embed&token_classify` for bge-m3 (#37632) · 6e04e793
  Augusto Yao authored Mar 23, 2026
```
Signed-off-by: augusto.yjh <augusto.yjh@antgroup.com>
Co-authored-by: wang.yuqi <yuqi.wang@daocloud.io>
```
  6e04e793
- Fix AudioFlamingo3/MusicFlamingo HF parity and RoTE handling (#37643) · e7767ecc
  Lasha Koroshinadze authored Mar 22, 2026
```
Signed-off-by: Lasha <26011196+lashahub@users.noreply.github.com>
```
  e7767ecc
22 Mar, 2026 6 commits
- [MRV2] Enable PP CUDA graph test (#37830) · 43877a62
  Woosuk Kwon authored Mar 22, 2026
```
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
```
  43877a62
- [Model Runner V2] Enable piecewise CUDA graphs for pipeline parallelism (#35162) · 63f49b8b
  zhanqiuhu authored Mar 22, 2026
```
Signed-off-by: Zhanqiu Hu <zh338@cornell.edu>
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Woosuk Kwon <woosuk@inferact.ai>
```
  63f49b8b
- [MRV2] Use FP64 for Gumbel noise (#37798) · a5e9d511
  Woosuk Kwon authored Mar 22, 2026
```
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
```
  a5e9d511
- [Bigfix]fix lora test by pass padded size back to the layer (#37811) · c058ff44
  Yongye Zhu authored Mar 22, 2026
  
  c058ff44
- [MRV2] Skip hidden states allocation for PW CUDA graphs (#37818) · ce9b1d76
  Woosuk Kwon authored Mar 22, 2026
```
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
```
  ce9b1d76
- Enable `NemotronHPuzzle` + `NemotronHMTP` (#37803) · e74c17e1
  Netanel Haber authored Mar 22, 2026
  
  e74c17e1