Commits · 512f52219240b0aa1be687955ab52fcdd0c5a40e · OpenDAS / vllm_cscc · GitLab

24 Apr, 2026 19 commits
- [Model] Gemma4: add bidirectional vision attention for sliding layers with window guard (#40534) · 512f5221
  Luciano Martins authored Apr 24, 2026
```
Signed-off-by: Luciano Martins <lucianommartins@users.noreply.github.com>
Signed-off-by: Luciano Martins <lucianomartins@google.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Luciano Martins <lucianommartins@users.noreply.github.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  512f5221
- [XPU] Enable torch.compile for XPU GDN attention (#39466) · 4c34b2f6
  Yuwen Zhou authored Apr 24, 2026
```
Signed-off-by: yuwenzho <yuwen.zhou@intel.com>
Signed-off-by: Yuwen Zhou <yuwen.zhou@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
```
  4c34b2f6
- Support only half types for concat_mla_q kernel (#37892) · cf8a613a
  Xin Yang authored Apr 23, 2026
```
Signed-off-by: Xin Yang <xyangx@amazon.com>
```
  cf8a613a
- [XPU][CI] Fix Docker cleanup races on Intel CI runners (#40761) · 01acf96c
  xiangdong authored Apr 24, 2026
```
Signed-off-by: zengxian <xiangdong.zeng@intel.com>
```
  01acf96c
- [MoE] Move cutlass moe to fused_moe/experts/ (#40574) · 079a4cf3
  Jackmin801 authored Apr 23, 2026
```
Signed-off-by: Jackmin801 <ongjackm@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
```
  079a4cf3
- [Deprecate] Deprecate LLM.reward offline api, use LLM.encode instead. (#40688) · 9744b699
  wang.yuqi authored Apr 24, 2026
```
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: wang.yuqi <noooop@126.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
```
  9744b699
- [Bugfix] Avoid mutating `chat_template_kwargs` in `HYV3ReasoningParser` initialization (#40713) · c662b435
  Bugen Zhao authored Apr 24, 2026
```
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  c662b435
- [Platform] Fix RISC-V platform detection (lscpu parsing + non-NUMA meminfo) (#40427) · 100c7b65
  lyd1992 authored Apr 24, 2026
```
Signed-off-by: liuyudong <liuyudong@iscas.ac.cn>
```
  100c7b65
- [Feature] Avoid eager import of the "mistral_common" package. (#40043) · 56bdf85e
  Neil Schemenauer authored Apr 23, 2026
```
Signed-off-by: Neil Schemenauer <nas@arctrix.com>
```
  56bdf85e
- [Doc] fix capitalization consistency in README (vLLM, Hugging Face) (#40729) · eba73068
  Vinayak Kumar authored Apr 24, 2026
```
Signed-off-by: Vinayak Mishra <vinayakmishra448@gmail.com>
```
  eba73068
- [MRV2] Ensure warmup covers prefill path (#40746) · e9f331d7
  Nick Hill authored Apr 23, 2026
```
Signed-off-by: Nick Hill <nickhill123@gmail.com>
```
  e9f331d7
- [BUG]: fix HF tokenizer concurrent borrow in tool parsers (#40059) · c9bf77df
  yzong-rh authored Apr 23, 2026
```
Signed-off-by: Yifan <yzong@redhat.com>
Co-authored-by: timon0305 <timon0305@outlook.com>
Co-authored-by: sfeng33 <4florafeng@gmail.com>
```
  c9bf77df
- [Misc] Added curl retries in install_python_libraries.sh (#36700) · 30413442
  Dmitry Tokarev authored Apr 23, 2026
```
Signed-off-by: Dmitry Tokarev <dtokarev@nvidia.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  30413442
- [Bugfix] Treat <tool_call> as implicit reasoning end in Qwen3 parser (#35687) · 92762edc
  Doug Campos authored Apr 23, 2026
```
Signed-off-by: Doug Campos <qmx@qmx.me>
```
  92762edc
- [Feat] Unified Synthetic Acceptance Rate for V1 and V2 (#40662) · 626daa20
  Benjamin Chislett authored Apr 23, 2026
```
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>
```
  626daa20
- [Core] Avoid seq_lens_cpu GPU->CPU sync (#40654) · fe85a92e
  Nick Hill authored Apr 23, 2026
```
Signed-off-by: Nick Hill <nickhill123@gmail.com>
```
  fe85a92e
- [EPLB] Remove asyncio infrastructure from Async EPLB (#40730) · 62b1bbe4
  Sage Moore authored Apr 23, 2026
```
Signed-off-by: Sage Moore <sage@neuralmagic.com>
```
  62b1bbe4
- [ROCm] Cast score correction bias tensor during model construction for DeepSeek/Kimi-K2 (#39999) · fa4b7055
  Hemanth Acharya authored Apr 24, 2026
```
Signed-off-by: Hemanth Acharya <heachary@amd.com>
```
  fa4b7055
- [MoE] Move remaining PrepareAndFinalize to prepare finalize folder (#39009) · 447c372a
  Jackmin801 authored Apr 23, 2026
```
Signed-off-by: Robert Shaw <robertgshaw2@gmail.com>
Signed-off-by: Jackmin801 <ongjackm@gmail.com>
Co-authored-by: Robert Shaw <robertgshaw2@gmail.com>
```
  447c372a
23 Apr, 2026 21 commits
- [Docs]Add documentation for bench serve visualization arguments (#40539) · ff2c2bd8
  Sophie du Couédic authored Apr 24, 2026
```
Signed-off-by: Sophie du Couédic <sop@zurich.ibm.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  ff2c2bd8
- [Spec Decode] Move `SpecDecodeBaseProposer` out of `eagle.py` (#40732) · cde8d247
  Matthew Bonanni authored Apr 23, 2026
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  cde8d247
- [Bugfix] Fix DeepSeek V2-Lite Accuracy drop (#40673) · 4a6dd1c3
  bnellnm authored Apr 23, 2026
```
Signed-off-by: Bill Nell <bnell@redhat.com>
```
  4a6dd1c3
- [Bugfix] Fix workspace resize leaking reserved GPU memory (#39226) · 7ff65b19
  czhu-cohere authored Apr 23, 2026
```
Signed-off-by: root <conway.zhu@cohere.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
```
  7ff65b19
- [NVIDIA] Add sm_110 (Jetson Thor) to CUDA 13.0 build targets (#39233) · 7f95a66c
  Johnny authored Apr 23, 2026
  
  7f95a66c
- [MoE] Move xpu moe to fused_moe/experts/ (#40568) · 1b1c01de
  Jackmin801 authored Apr 23, 2026
```
Signed-off-by: Jackmin801 <ongjackm@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
```
  1b1c01de
- [DP][Ray] Pin DP control bundle to same node as first GPU bundle (#39167) · e9ba519f
  shaharmor98 authored Apr 23, 2026
```
Signed-off-by: Shahar Mor <smor@nvidia.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
```
  e9ba519f
- [kv_offload+HMA][10/N]: Support load with multiple KV groups (#39402) · 5ef33ab2
  Or Ozeri authored Apr 23, 2026
```
Signed-off-by: Or Ozeri <oro@il.ibm.com>
```
  5ef33ab2
- [MoE Refactor] Rename FusedMoE.make_expert_params_mapping to... · 1c2c1eb8
  bnellnm authored Apr 23, 2026
```
[MoE Refactor] Rename FusedMoE.make_expert_params_mapping to fused_moe_make_expert_params_mapping (#40671)
Signed-off-by: Bill Nell <bnell@redhat.com>
```
  1c2c1eb8
- [CI] Split disaggregated tests into own test-area (#40623) · 8824f50f
  Nicolò Lucchesi authored Apr 23, 2026
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  8824f50f
- [ROCm] Implement GPU-to-NUMA-node detection (#40015) · 0098db9e
  pschlan-amd authored Apr 23, 2026
```
Signed-off-by: Patrick Schlangen <pschlan@amd.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
```
  0098db9e
- [XPU] Upgrade torch 2.11 for xpu (#37947) · 53ecc807
  Kunshang Ji authored Apr 23, 2026
```
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
```
  53ecc807
- [Bugfix] Make Attention Backend Auto-Selection Batch-Invariance-Aware (#40193) · b7a26050
  Srreyansh Sethi authored Apr 23, 2026
```
Signed-off-by: Srreyansh Sethi <srreyansh.sethi@gmail.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
```
  b7a26050
- [Model] Support Hy3 preview (#40681) · d0009ddb
  stevenkuang authored Apr 23, 2026
```
Signed-off-by: stevenkuang <stevenkuang@tencent.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
```
  d0009ddb
- [Bugfix] Include inductor and functorch configs in compilation cache key (#40627) · 424033f4
  Richard Zou authored Apr 23, 2026
```
Signed-off-by: Richard Zou <zou3519@gmail.com>
```
  424033f4
- [Misc] use model arch converter for bidi models identification (#40701) · da1e7311
  Isotr0py authored Apr 23, 2026
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  da1e7311
- [XPU][CI]Temporary disable 3 cases on Intel GPU in CI (#40683) · 01cb41dc
  xiangdong authored Apr 23, 2026
```
Signed-off-by: zengxian <xiangdong.zeng@intel.com>
```
  01cb41dc
- [CPU] Added faster exp routine for lower precision data types. (#38112) · 2f314bc5
  almayne authored Apr 23, 2026
```
Signed-off-by: Anna Mayne <anna.mayne@arm.com>
Co-authored-by: Fadi Arafeh <fadi.arafeh@arm.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
```
  2f314bc5
- [Compilation] Refactor SiluMul activation+quant Fusion Pass (#39684) · 2196bac1
  BadrBasowid authored Apr 23, 2026
```
Signed-off-by: BadrBasowid <badr.basowid@gmail.com>
```
  2196bac1
- [ROCm] Add gfx1102/gfx1103 support (#40037) · 4b7869d6
  Matthias Gehre authored Apr 23, 2026
```
Signed-off-by: Matthias Gehre <matthias.gehre@amd.com>
```
  4b7869d6
- [UT][Hardware] let torchrun example tests use the default backend (#39879) · 4a79262e
  liuzhenwei authored Apr 23, 2026
```
Signed-off-by: zhenwei-intel <zhenwei.liu@intel.com>
```
  4a79262e