Commits · 86daa875fe1a1cf76709af1637f95891d3ef0707 · OpenDAS / vllm_cscc

16 Sep, 2025 10 commits

[gpt-oss][1][bugfix] fix streaming final output (#24466) · 86daa875
Andrew Xia authored Sep 16, 2025
```
Signed-off-by: Andrew Xia <axia@meta.com>
```
86daa875
[gpt-oss][1b] streaming add item id, content id (#24788) · f4d6eb95
Andrew Xia authored Sep 16, 2025
```
Signed-off-by: Andrew Xia <axia@meta.com>
```
f4d6eb95

[Core/DBO][1/N] Add Dual-Batch Overlap mechanism to VLLM (#23693) · 56793995

Sage Moore authored Sep 16, 2025


Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Sage Moore <sage@neuralmagic.com>
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Co-authored-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>

56793995

[CI] Add Decode Context Parallelism (DCP) test to CI (#24487) · 4e5affea
Ming Yang authored Sep 16, 2025
```
Signed-off-by: Ming Yang <minos.future@gmail.com>
```
4e5affea

[Feat][EPLB] A novel static EPLB placement strategy for MoE models. (#23745) · 7ea5c73a

Chen Bruce authored Sep 16, 2025


Signed-off-by: bruceszchen <bruceszchen@tencent.com>
Signed-off-by: Chen Bruce <bruceszchen@tencent.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: Chen Bruce <cszwwdz@vip.qq.com>
Co-authored-by: lemon412 <lemon412@foxmail.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

7ea5c73a

[Bugfix] Fix sequence parallelism bug when enable pipeline parallelism (#24021) · 17871983
cascade authored Sep 15, 2025
```
Signed-off-by: cascade812 <cascade812@outlook.com>
```
17871983
Remove V0 Encoder-Decoder Support (#24907) · 759ef49b
Woosuk Kwon authored Sep 15, 2025
```
Signed-off-by: Woosuk Kwon <woosuk@thinkingmachines.ai>
```
759ef49b
[Metrics] Hide deprecated metrics with gpu_ prefix (#24245) · 2942970d
Mark McLoughlin authored Sep 16, 2025
```
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
```
2942970d
[CI] Small Accuracy Eval Test for Deepseek Model (#24259) · 3c96e7b8
Wentao Ye authored Sep 15, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
3c96e7b8
[ROCm][Bugfix] Fix the case where there's bias (#24895) · 2891603e
Gregory Shtrasberg authored Sep 15, 2025
```
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
```
2891603e

15 Sep, 2025 10 commits
- [Compile] Fix noop_elimination pass and add tests for noop_elimination (#24880) · 5bcc153d
  Jiangyun Zhu authored Sep 16, 2025
```
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
```
  5bcc153d
- [Tests] fix initialization of kv hash in tests (#24273) · 45bfa49c
  Mickaël Seznec authored Sep 15, 2025
```
Signed-off-by: Mickael Seznec <mickael@mistral.ai>
```
  45bfa49c
- [gpt-oss] Add IncompleteDetails to ResponsesRepsonse (#24561) · 25aba2b6
  Andrew Xia authored Sep 15, 2025
```
Signed-off-by: Andrew Xia <axia@meta.com>
```
  25aba2b6
- [Transform] Deterministic Hadacore Transforms (#24106) · a0b26701
  Kyle Sayers authored Sep 15, 2025
```
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
```
  a0b26701
- Move `MultiModalConfig` from `config/__init__.py` to `config/multimodal.py` (#24659) · c4afdb69
  Harry Mellor authored Sep 15, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  c4afdb69
- [Bugfix] Fix GLM4.1V multimodal processor with compatability for Transformers v4.56 (#24822) · 0e219cd5
  Isotr0py authored Sep 15, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  0e219cd5
- [Model]: support Ling2.0 (#24627) · 72c99f2a
  ant-yy authored Sep 15, 2025
```
Signed-off-by: vito.yy <vito.yy@antgroup.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  72c99f2a
- [UT] enhance free kv cache block queue popleft_n (#24220) · bc0f6059
  Ning Xie authored Sep 15, 2025
```
Signed-off-by: Andy Xie <andy.xning@gmail.com>
```
  bc0f6059
- [Frontend] Skip `stop` in reasoning content (#14550) · f4a948f3
  Ce Gao authored Sep 15, 2025
```
Signed-off-by: Ce Gao <cegao@tensorchord.ai>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
```
  f4a948f3
- [kv cache] update num_free_blocks in the end (#24228) · 3f331398
  Ning Xie authored Sep 15, 2025
```
Signed-off-by: Andy Xie <andy.xning@gmail.com>
```
  3f331398
14 Sep, 2025 1 commit
- [Hybrid Allocator] Support Pipeline Parallel (#23974) · 8e5cdcda
  Chen Zhang authored Sep 14, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  8e5cdcda
13 Sep, 2025 6 commits
- [CI][Spec Decode] Adjust threshold for flaky ngram spec decoding test again (#24771) · cfa3234a
  Wenlong Wang authored Sep 13, 2025
```
Signed-off-by: wwl2755 <wangwenlong2755@gmail.com>
```
  cfa3234a
- [CI Failure] Fix test_flashinfer_cutlass_mxfp4_mxfp8_fused_moe (#24750) · 59d7ffc1
  Michael Goin authored Sep 13, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  59d7ffc1
- [Kernels][DP/EP] Optimize Silu Kernel for R1 (#24054) · 98229db2
  Elvir Crnčević authored Sep 13, 2025
```
Signed-off-by: elvircrn <elvircrn@gmail.com>
```
  98229db2
- [Chore] Remove unused batched RoPE op & kernel (#24789) · 5febdc87
  Woosuk Kwon authored Sep 13, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  5febdc87
- [Model] Add Olmo3 model implementation (#24534) · 89e08d6d
  Shane A authored Sep 12, 2025
```
Signed-off-by: Shane A <shanea@allenai.org>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  89e08d6d
- [Frontend][Multimodal] Allow skipping media data when UUIDs are provided. (#23950) · 7f2ea707
  Chenheli Hua authored Sep 12, 2025
```
Signed-off-by: Roger Wang <hey@rogerw.io>
Signed-off-by: Chenheli Hua <huachenheli@outlook.com>
Signed-off-by: Roger Wang <hey@rogerw.me>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.me>
```
  7f2ea707
12 Sep, 2025 13 commits

[Core] Support async scheduling with uniproc executor (#24219) · 4fdd6f5c

Nick Hill authored Sep 12, 2025


Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: Ronald1995 <ronaldautomobile@163.com>
Co-authored-by: Ronald1995 <ronaldautomobile@163.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>

4fdd6f5c

Add FLASHINFER_MLA to backend selector test (#24753) · 5fe643fc
Matthew Bonanni authored Sep 12, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
```
5fe643fc
[Attention][FlashInfer] Enable FP8 FlashInfer (TRTLLM) MLA decode (#24705) · 7ba32aa6
Matthew Bonanni authored Sep 12, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
```
7ba32aa6
[CI] Speed up model unit tests in CI (#24253) · c8c42597
afeldman-nm authored Sep 12, 2025
```
Signed-off-by: Andrew Feldman <afeldman@redhat.com>
```
c8c42597
[Core] Shared memory based object store for Multimodal data caching and IPC (#20452) · a5b84f1c
dongluw authored Sep 12, 2025
```
Signed-off-by: donglu <donglu@cohere.com>
```
a5b84f1c
[Multimodal] Remove legacy multimodal fields in favor of MultiModalFeatureSpec (#24548) · 0377802c
Flora Feng authored Sep 12, 2025
```
Signed-off-by: sfeng33 <4florafeng@gmail.com>
```
0377802c
[Multi Modal] Add FA3 in VIT (#24347) · 72fc8aa4
Wenlong Wang authored Sep 12, 2025
```
Signed-off-by: wwl2755 <wangwenlong2755@gmail.com>
```
72fc8aa4
[CI/Build] Skip prompt embeddings tests on V1-only CPU backend (#24721) · 59d5d2c7
Li, Jiang authored Sep 12, 2025
```
Signed-off-by: jiang1.li <jiang1.li@intel.com>
```
59d5d2c7
[CI] Add ci_envs for convenient local testing (#24630) · d21a36f5
wang.yuqi authored Sep 12, 2025
```
Signed-off-by: wang.yuqi <noooop@126.com>
```
d21a36f5

[CI] Fix flaky test ... · 561a0bae

Chen Zhang authored Sep 12, 2025


[CI] Fix flaky test  v1/worker/test_gpu_model_runner.py::test_kv_cache_stride_order          (#24640)
Signed-off-by: Chen Zhang <zhangch99@outlook.com>

561a0bae

Fix implementation divergence for BLOOM models between vLLM and HuggingFace... · ddcec289

Andrew Sansom authored Sep 11, 2025


Fix implementation divergence for BLOOM models between vLLM and HuggingFace when using prompt embeds (#24686)
Signed-off-by: Andrew Sansom <andrew@protopia.ai>

ddcec289

Enable conversion of multimodal models to pooling tasks (#24451) · e090b7b4
Maximilien de Bayser authored Sep 12, 2025
```
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
```
e090b7b4

[V1] feat:add engine v1 tracing (#20372) · 40b6c912

RichardoMu authored Sep 12, 2025


Signed-off-by: Mu Huai <tianbowen.tbw@antgroup.com>
Signed-off-by: Ye Zhang <zhysishu@gmail.com>
Signed-off-by: RichardoMu <44485717+RichardoMrMu@users.noreply.github.com>
Signed-off-by: simon-mo <simon.mo@hey.com>
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
Co-authored-by: Mu Huai <tianbowen.tbw@antgroup.com>
Co-authored-by: Ye Zhang <zhysishu@gmail.com>
Co-authored-by: Benjamin Bartels <benjamin@bartels.dev>
Co-authored-by: simon-mo <simon.mo@hey.com>
Co-authored-by: 瑜琮 <ly186375@antfin.com>
Co-authored-by: Aaron Pham <contact@aarnphm.xyz>
Co-authored-by: 22quinn <33176974+22quinn@users.noreply.github.com>

40b6c912