Commits · ac0bb2c3075f87b62afde8ea7dab10207bb71df1 · OpenDAS / vllm_cscc

12 Nov, 2025 10 commits

[Core] Cache `vllm_is_batch_invariant` (#28304) · ac0bb2c3
Lukas Geiger authored Nov 12, 2025
```
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
```
ac0bb2c3
[BugFix] Add fallback path in `apply_rotary_pos_emb_flashattn` for non-cuda platforms (#28447) · b9ce9a30
Fanli Lin authored Nov 12, 2025
```
Signed-off-by: Lin, Fanli <fanli.lin@intel.com>
```
b9ce9a30

[Core] Encoder separation for Encode-Prefill-Decode Disaggregation (#25233) · 4ccffe56

Chenguang Zheng authored Nov 12, 2025


Signed-off-by: n00909098 <nguyen.kha.long@huawei.com>
Signed-off-by: knlnguyen1802 <knlnguyen1802@gmail.com>
Signed-off-by: herotai214 <herotai214@gmail.com>
Signed-off-by: Khuong Le <khuong.le.manh@huawei.com>
Signed-off-by: Khuong Le <lemanhkhuong2611@gmail.com>
Co-authored-by: n00909098 <nguyen.kha.long@huawei.com>
Co-authored-by: knlnguyen1802 <knlnguyen1802@gmail.com>
Co-authored-by: herotai214 <herotai214@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Khuong Le <khuong.le.manh@huawei.com>
Co-authored-by: Khuong Le <lemanhkhuong2611@gmail.com>

4ccffe56

[Model][Qwen3VL] Simplify `get_mrope_input_positions` using numpy (#28302) · cbb799e3
Lukas Geiger authored Nov 12, 2025
```
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
```
cbb799e3

`VLLM_USE_TRITON_FLASH_ATTN` V0 variable deprecation (#27611) · 9f0247cf

Andreas Karatzas authored Nov 11, 2025


Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>

9f0247cf

[CPU] Refactor CPU attention backend (#27954) · 7f829be7
Li, Jiang authored Nov 12, 2025
```
Signed-off-by: jiang1.li <jiang1.li@intel.com>
```
7f829be7
[[V0 deprecation]]Remove VLLM_USE_V1 env (#28204) · e1710393
wangxiyuan authored Nov 12, 2025
```
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
```
e1710393
[Performance] Cache loaded custom logitsprocs to avoid overheads (#28462) · 3f770f44
Isotr0py authored Nov 12, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
3f770f44
[Frontend] Change CompilationMode to a proper Enum (#28165) · 48c87936
Yanan Cao authored Nov 11, 2025
```
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
```
48c87936
[BugFix] Graceful handling of torch symm mem errors. (#27671) · 1788aa1e
Ilya Markov authored Nov 12, 2025
```
Signed-off-by: ilmarkov <markovilya197@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
1788aa1e

11 Nov, 2025 30 commits
- [Feature] Allow configuring FlashInfer workspace size (#28269) · 412e153d
  Max Hu authored Nov 11, 2025
```
Signed-off-by: Max Hu <hyoung2991@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  412e153d
- [Bugfix] Disable shared expert overlap if Marlin MoE is used (#28410) · e5f599d4
  Michael Goin authored Nov 11, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  e5f599d4
- [Misc] Cleanup Executor interface (#28441) · d4902ba5
  wangxiyuan authored Nov 12, 2025
```
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
```
  d4902ba5
- [TPU] Rename path to tpu platform (#28452) · df4d3a44
  Kyuyeun Kim authored Nov 11, 2025
```
Signed-off-by: Kyuyeun Kim <kyuyeunk@google.com>
```
  df4d3a44
- [LoRA][1/N]Remove LoRA extra vocab (#28382) · 9d1c4747
  Jee Jee Li authored Nov 12, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  9d1c4747
- [Misc] fix typo in DCP comment (#28389) · 8c32c6e4
  Jie Luo authored Nov 12, 2025
```
Signed-off-by: Livinfly <luojie3m@gmail.com>
```
  8c32c6e4
- [V0 deprecation] Clean up num_prefill_tokens logic for V0 (#28203) · de120bc9
  Canlin Guo authored Nov 12, 2025
```
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
```
  de120bc9
- [Perf] Use np.ndarray instead of list[list[int]] to reduce GC overhead (#28245) · 4228be79
  Jialin Ouyang authored Nov 11, 2025
```
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
```
  4228be79
- [Misc] Remove unused attention prefix prefill ops functions (#26971) · 76e4dcf2
  Lukas Geiger authored Nov 11, 2025
```
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
```
  76e4dcf2
- [BugFix] Fix Siglip2Attention on XPU (#28448) · d5edcb86
  Fanli Lin authored Nov 12, 2025
```
Signed-off-by: Lin, Fanli <fanli.lin@intel.com>
```
  d5edcb86
- Prefer FlashAttention MLA as default over FlashMLA (#27363) · 684f2545
  Matthew Bonanni authored Nov 11, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  684f2545
- [Quantization] fix attention quantization of gpt_oss model (#27334) · 5a1271d8
  xuebwang-amd authored Nov 12, 2025
```
Signed-off-by: xuebwang-amd <xuebwang@amd.com>
```
  5a1271d8
- [ROCm][Quantization] extend AMD Quark to support mixed-precision quantized model (#24239) · 05576df8
  xuebwang-amd authored Nov 12, 2025
```
Signed-off-by: xuebwang-amd <xuebwang@amd.com>
Co-authored-by: fxmarty-amd <felmarty@amd.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
  05576df8
- [Kernel][Perf] fuse QK Norm and RoPE into one cuda kernel for Qwen Model (#27165) · 68c09efc
  zhrrr authored Nov 12, 2025
```
Signed-off-by: zhuhaoran <zhuhaoran.zhr@alibaba-inc.com>
```
  68c09efc
- [NIXL] Generalize block-first backend layouts (FlashInfer-like) (#28282) · a7ef3eb0
  Nicolò Lucchesi authored Nov 11, 2025
  
  a7ef3eb0
- Remove weight_scale.T special case for SM90 Block FP8 CUTLASS kernel (#28431) · f9a40871
  Michael Goin authored Nov 11, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  f9a40871
- [BugFix] Fix RuntimeError in PixtralHFAttention on CPU/XPU (#28444) · b8860680
  Fanli Lin authored Nov 11, 2025
```
Signed-off-by: Lin, Fanli <fanli.lin@intel.com>
```
  b8860680
- [Kernels] Split up fused_moe/layer.py, isolate more modular kernel code (#28064) · a1448b4b
  bnellnm authored Nov 11, 2025
  
  a1448b4b
- [Model] Pass `mm_features` directly into `get_mrope_input_positions` (#28399) · afffd3cc
  Cyrus Leung authored Nov 11, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  afffd3cc
- Fix Fused MoE LoRA Triton kernel bug (#28450) · 7dbe6d81
  Chaojun Zhang authored Nov 11, 2025
```
Signed-off-by: chaojun-zhang <chaojun.zhang@intel.com>
```
  7dbe6d81
- [Attention] Refactor CUDA attention backend selection logic (#24794) · b30dfa03
  Matthew Bonanni authored Nov 11, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
```
  b30dfa03
- [Model][Qwen3VL] Slighly speedup `fast_pos_embed_interpolate` (#28434) · 9973e6e0
  Lukas Geiger authored Nov 11, 2025
```
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
```
  9973e6e0
- [BugFix] 'DeepseekV2Config' object has no attribute 'use_mla'` (#28387) · c7991269
  Fanli Lin authored Nov 11, 2025
```
Signed-off-by: Lin, Fanli <fanli.lin@intel.com>
```
  c7991269
- [Bugfix] fix qwen3-next crash (#28202) · f0359fff
  Jiangyun Zhu authored Nov 11, 2025
```
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
```
  f0359fff
- [EPLB] Refactor balance_packing to use numpy and optimize GPU-CPU transfers in EPLB (#28369) · 798c7beb
  Sage Moore authored Nov 11, 2025
```
Signed-off-by: Sage Moore <sage@neuralmagic.com>
```
  798c7beb
- [Bugfix] Fix max image size for PaddleOCR-VL (#28442) · 4fd4b743
  Roger Wang authored Nov 11, 2025
```
Signed-off-by: Roger Wang <hey@rogerw.io>
```
  4fd4b743
- [BugFix] Avoid calling KV connector layer APIs when metadata is unset (#28253) · cc079763
  David Ben-David authored Nov 11, 2025
```
Signed-off-by: David Ben-David <davidb@pliops.com>
Co-authored-by: David Ben-David <davidb@pliops.com>
Co-authored-by: Mark McLoughlin <markmc@redhat.com>
```
  cc079763
- [Bugfix] Fix Stream Sync for Shared Expert Overlap (#28430) · e605e8e3
  Robert Shaw authored Nov 11, 2025
```
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
Signed-off-by: Robert Shaw <robertgshaw2@gmail.com>
Co-authored-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
```
  e605e8e3
- [Frontend] Add sagemaker_standards dynamic lora adapter and stateful session... · bca74e32
  Zuyi Zhao authored Nov 10, 2025
```
[Frontend] Add sagemaker_standards dynamic lora adapter and stateful session management decorators to vLLM OpenAI API server (#27892)
Signed-off-by: Zuyi Zhao <zhaozuy@amazon.com>
Signed-off-by: Shen Teng <sheteng@amazon.com>
Co-authored-by: Shen Teng <sheteng@amazon.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
```
  bca74e32
- [Misc] FlattenLogprobs -> FlatLogprobs (#28335) · 8d706cca
  Zhuohan Li authored Nov 10, 2025
  
  8d706cca