Commits · 5282c7d4d0d1487eb283f09d322b0140dea5a968 · OpenDAS / vllm_cscc

"docs/vscode:/vscode.git/clone" did not exist on "7dd872ae2dfe7cc4104316702cb8cab71a4663ef"

12 Mar, 2026 17 commits
- [Perf] add packed recurrent fast path for decode (#36596) · 9e19f833
  caozuoba authored Mar 12, 2026
```
Signed-off-by: hdj <1293066020@qq.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
```
  9e19f833
- [Frontend] Split `OpenAIServingModels` into `OpenAIModelRegistry` + `OpenAIServingModels` (#36536) · 06e0bc21
  Sage authored Mar 12, 2026
```
Signed-off-by: Sage Ahrac <sagiahrak@gmail.com>
```
  06e0bc21
- [Bugfix] Fix crash when tool_choice=required exceeds max_tokens (#36841) · 5a71cdd7
  Chauncey authored Mar 12, 2026
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
  5a71cdd7
- [MM][OOT] Support CPU `seq_lens` for OOT MMEncoderAttention kernels (#36605) · f0d3658c
  Shanshan Shen authored Mar 12, 2026
```
Signed-off-by: shen-shanshan <467638484@qq.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  f0d3658c
- [UX] Only show FP4 Marlin fallback warning for w4a4 models (#36806) · 57431d82
  Michael Goin authored Mar 12, 2026
```
Co-authored-by: Claude <noreply@anthropic.com>
```
  57431d82
- [Bugfix] Warm up Triton autotuner for GDN layers during V1 profiling (#36599) · 3e64fe4a
  Xu Jinyang authored Mar 12, 2026
```
Signed-off-by: AuYang <459461160@qq.com>
```
  3e64fe4a
- [KV Connector] Support using FlexKV as KV Cache Offloading option. (#34328) · 8cb24d3a
  sfeiqiang authored Mar 12, 2026
```
Signed-off-by: phaedonsun <phaedonsun@tencent.com>
Co-authored-by: phaedonsun <phaedonsun@tencent.com>
```
  8cb24d3a
- [Bugfix][Model] Fix DeepSeek-OCR TensorSchema crash on empty images_crop (#36670) · 00726c74
  István Ketykó authored Mar 12, 2026
```
Signed-off-by: István Ketykó <istvan.ketyko@gmail.com>
```
  00726c74
- [Frontend] OpenAI Responses API supports Tool/Function calling with streaming (#29947) · 9fe404ed
  Chauncey authored Mar 12, 2026
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
  9fe404ed
- replace `with torch.cuda.device` with `with torch.accelerator.device_index` (#36144) · 894843eb
  Yan Ma authored Mar 12, 2026
```
Signed-off-by: Yan Ma <yan.ma@intel.com>
```
  894843eb
- [Kernel][Helion][13/N] Force static_shapes=False in helion register (#36677) · 584a3f56
  Yanan Cao authored Mar 11, 2026
```
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
```
  584a3f56
- [BugFix] Fix multiple/duplicate stdout prefixes (#36822) · 36735fd7
  Nick Hill authored Mar 11, 2026
```
Signed-off-by: Nick Hill <nickhill123@gmail.com>
```
  36735fd7
- [Model Runner V2] Do not initialize sampler for non-last PP ranks (#36824) · 2f8b4ce0
  Woosuk Kwon authored Mar 11, 2026
```
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
```
  2f8b4ce0
- [LMCache] Fault Tolerance Mechanism (#36586) · 2ef69456
  Yuwei An authored Mar 11, 2026
```
Signed-off-by: Oasis-Git <ayw.sirius19@gmail.com>
```
  2ef69456
- [Bugfix] Fix minimax_m2 tool parser when stream interval > 1 (#35895) · 8647c6cf
  Flora Feng authored Mar 11, 2026
```
Signed-off-by: sfeng33 <4florafeng@gmail.com>
```
  8647c6cf
- [Frontend] Exclude anthropic billing header to avoid prefix cache miss (#36829) · 262b76a0
  Nick Hill authored Mar 11, 2026
```
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  262b76a0
- [Perf] Optimize compute maxsim using batched version, 3.2% E2E throughput improvement (#36710) · c34ba6b9
  Wentao Ye authored Mar 11, 2026
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  c34ba6b9
11 Mar, 2026 23 commits
- [BUG] Fix async rlhf tests (#35811) · d6b61e51
  Aaron Hao authored Mar 11, 2026
```
Signed-off-by: ahao-anyscale <ahao@anyscale.com>
```
  d6b61e51
- [Kernel] [Helion] [15/N] Split config files into per-platform files (#36698) · cf632499
  Yanan Cao authored Mar 11, 2026
```
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
```
  cf632499
- [Kernel] [Helion] [14/N] Set autotune_ignore_errors=True during autotuning (#36683) · 0ce21c46
  Yanan Cao authored Mar 11, 2026
```
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
```
  0ce21c46
- [Model Runner V2] Add WhisperModelState [6/N] (#35790) · 55eed6b7
  Woosuk Kwon authored Mar 11, 2026
```
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
```
  55eed6b7
- [Model Runner V2] Add probabilistic rejection sampling for spec decoding (#35461) · c77181e5
  Giancarlo Delfin authored Mar 11, 2026
```
Signed-off-by: Giancarlo Delfin <gdelfin@inferact.ai>
```
  c77181e5
- [LMCache] Pass TP size in lookup for MLA multi-reader locking (#36129) · 12001f2e
  maobaolong authored Mar 12, 2026
```
Signed-off-by: baoloongmao <baoloongmao@tencent.com>
Co-authored-by: Yihua Cheng <yihua98@uchicago.edu>
```
  12001f2e
- [BugFix][kv_offload] Fix offloading decodes with async scheduling (#33881) · 7ee5d509
  Or Ozeri authored Mar 11, 2026
```
Signed-off-by: Or Ozeri <oro@il.ibm.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>
```
  7ee5d509
- [Bugfix][ROCm] Strip block_size before attention backend validation (#36274) · 428bc718
  jennyyyyzhen authored Mar 11, 2026
```
Signed-off-by: jennyyyyzhen <yzhen@hmc.edu>
Co-authored-by: Lu Fang <30275821+houseroad@users.noreply.github.com>
```
  428bc718
- [BugFix]: add bagel to MM_PREFIX_LM_MODELS (#36316) · ff1e3d9c
  汪志鹏 authored Mar 12, 2026
```
Signed-off-by: princepride <wangzhipeng628@gmail.com>
```
  ff1e3d9c
- [Refactor] Remove dead code in KV connector (#36424) · 35bdca54
  Wentao Ye authored Mar 11, 2026
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  35bdca54
- [ROCm] add tuned moe_wna16_triton kernel configs for CDNA4 (#35093) · 8a248427
  Amanzhol Salykov authored Mar 11, 2026
```
Signed-off-by: salykova <amsalykov@gmail.com>
Signed-off-by: amd-asalykov <asalykov@amd.com>
```
  8a248427
- Make Gemma and Gemma 2 accept `inputs_embeds` like Gemma 3 (#36787) · 65986db6
  Harry Mellor authored Mar 11, 2026
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  65986db6
- [torch.compile] Add support for non-contiguous fused RMSNorm + group quant (#36551) · 9556af87
  Luka Govedič authored Mar 11, 2026
```
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com>
Co-authored-by: ProExpertProg <11367180+ProExpertProg@users.noreply.github.com>
```
  9556af87
- [KVConnector] Support worker -> scheduler metadata (#31964) · a1a3523a
  Or Ozeri authored Mar 11, 2026
```
Signed-off-by: Or Ozeri <oro@il.ibm.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>
```
  a1a3523a
- fix: align lfm2 thumbnail token counting with HF (#36707) · 741f4e04
  tianshu-Michael-yu authored Mar 11, 2026
  
  741f4e04
- Add 320 dimension size support to MLA (#36161) · a5d06dc5
  Julien Denize authored Mar 11, 2026
```
Signed-off-by: Julien Denize <julien.denize@mistral.ai>
```
  a5d06dc5
- [Misc] Clean up renderers (#36770) · 196802df
  Cyrus Leung authored Mar 12, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  196802df
- [Bugfix] Fix negative max_tokens when input prompt is too long (#36789) · c84b519c
  Isotr0py authored Mar 12, 2026
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  c84b519c
- [Bugfix] Fix DP/EP Shared Expert With Monolithic Kernels (#36061) · b7e5a588
  Robert Shaw authored Mar 11, 2026
```
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
```
  b7e5a588
- [torch.compile] Use FakeTensors instead of real GPU tensors for single-size compilation (#36093) · 822e250a
  Richard Zou authored Mar 11, 2026
```
Signed-off-by: Richard Zou <zou3519@gmail.com>
```
  822e250a
- Fix routed experts capture for hybrid models (Mamba + Attention) (#35744) · bea02cdf
  Hongxin Xu authored Mar 11, 2026
```
Signed-off-by: arlenxu <arlenxu@tencent.com>
Signed-off-by: xhx1022 <1737006628@qq.com>
Co-authored-by: arlenxu <arlenxu@tencent.com>
```
  bea02cdf
- Add 'none' reasoning effort to ChatCompletionRequest (#36238) · a3ea760e
  Julien Denize authored Mar 11, 2026
```
Signed-off-by: Julien Denize <julien.denize@mistral.ai>
```
  a3ea760e
- Add support to Mistral large 3 eagle with dense layers (#36163) · afebeffb
  Julien Denize authored Mar 11, 2026
```
Signed-off-by: juliendenize <julien.denize@mistral.ai>
Signed-off-by: Julien Denize <40604584+juliendenize@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  afebeffb