Commits · e680723eba82c8f486dfb8ba00f72cccb6be5727 · OpenDAS / vllm_cscc · GitLab

08 Sep, 2025 31 commits
- [Bugfix] Disable the statslogger if the api_server_count is greater than 1 (#22227) · e680723e
  Chauncey authored Sep 09, 2025
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
```
  e680723e
- [Attention] FlashAttention MLA cudagraph support (#23958) · 620db1fc
  Matthew Bonanni authored Sep 08, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
```
  620db1fc
- [Spec Decode] Fix offline spec_decode.py (#24257) · 41183c1f
  Ekagra Ranjan authored Sep 08, 2025
```
Signed-off-by: Ekagra Ranjan <3116519+ekagra-ranjan@users.noreply.github.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
```
  41183c1f
- [Model loader]: support multi-thread model weight loading (#23928) · 43d9ad03
  Yang Kaiyong authored Sep 09, 2025
```
Signed-off-by: Yang Kaiyong <yangkaiyong.yky@antgroup.com>
Signed-off-by: Simon Mo <simon.mo@hey.com>
Co-authored-by: Simon Mo <simon.mo@hey.com>
```
  43d9ad03
- [CI] Enable encoder model compilation test (#24442) · 7be141b2
  Jiangyun Zhu authored Sep 09, 2025
```
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
```
  7be141b2
- [Model] Remove quantized mixtral (#24437) · 8d7f39b4
  Jee Jee Li authored Sep 09, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  8d7f39b4
- [Spec Decode][Benchmark] Add Blitzedit dataset (#23605) · cd086369
  Ekagra Ranjan authored Sep 08, 2025
```
Signed-off-by: Ekagra Ranjan <3116519+ekagra-ranjan@users.noreply.github.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
```
  cd086369
- [Spec Decode][Benchmark] Add Spec Bench Dataset for benchmarking (#23563) · 3feeeb9f
  Ekagra Ranjan authored Sep 08, 2025
```
Signed-off-by: Ekagra Ranjan <3116519+ekagra-ranjan@users.noreply.github.com>
```
  3feeeb9f
- [Model] Enable BNB support for qwen2_5_omni_thinker (#24420) · 6f4a82f8
  Jee Jee Li authored Sep 09, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  6f4a82f8
- [Docs]add eplb_config param use docs (#24213) · c44797a4
  rongfu.leng authored Sep 09, 2025
```
Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>
```
  c44797a4
- [Doc]: fix 2 hyperlinks leading to Ray site after they changed Ray's doc structure (#24438) · 55be93ba
  Didier Durand authored Sep 08, 2025
```
Signed-off-by: Didier Durand <durand.didier@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  55be93ba
- [Docs] Move feature compatibility tables to README (#24431) · 717fc00e
  Harry Mellor authored Sep 08, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  717fc00e
- [Frontend] User-provided uuids for medias in chat. (RFC #22044) (#23449) · 01dfb5e9
  Chenheli Hua authored Sep 08, 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>
Signed-off-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.me>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
```
  01dfb5e9
- Move `KVEventsConfig` from `config/__init__.py` to `config/kv_events.py` (#24433) · 03dd652c
  Harry Mellor authored Sep 08, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  03dd652c
- [Misc] Terratorch related fixes (#24337) · 9cd76b71
  Christian Pinto authored Sep 08, 2025
```
Signed-off-by: Christian Pinto <christian.pinto@ibm.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
  9cd76b71
- [Bugfix] Fix mamba2 prefill chunking (#23279) · e0413141
  tomeras91 authored Sep 08, 2025
```
Signed-off-by: Tomer Asida <57313761+tomeras91@users.noreply.github.com>
Signed-off-by: tomeras91 <57313761+tomeras91@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  e0413141
- [Bugfix] Fix get_quant_config when using modelscope (#24421) · 5e537f45
  Li Wang authored Sep 08, 2025
```
Signed-off-by: wangli <wangli858794774@gmail.com>
```
  5e537f45
- [Doc] Fix issues in integrations/llamastack.md (#24428) · c2a8b08f
  Michael Yao authored Sep 08, 2025
```
Signed-off-by: windsonsea <haifeng.yao@daocloud.io>
```
  c2a8b08f
- [Doc]: fix typos in Python comments (#24417) · f4962a6d
  Didier Durand authored Sep 08, 2025
```
Signed-off-by: Didier Durand <durand.didier@gmail.com>
```
  f4962a6d
- [Docs] Fix a tip indentation and typo (#24419) · 2f0b833a
  Michael Yao authored Sep 08, 2025
```
Signed-off-by: windsonsea <haifeng.yao@daocloud.io>
```
  2f0b833a
- [gpt-oss][Responses API] Fix the function call id format (#24409) · 425b04b8
  Chauncey authored Sep 08, 2025
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
  425b04b8
- [Model] Remove unnecessary CUDA sync of Qwen2VL image and video preprocess (#24334) · 60f0843e
  Chatcharin Sangbutsarakum authored Sep 08, 2025
```
Signed-off-by: Win <chatcharinsang@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
```
  60f0843e
- [Model] Remove unnecessary CUDA sync of GLM-4.1V image and video preprocess (#24332) · 8a466026
  Chatcharin Sangbutsarakum authored Sep 08, 2025
```
Signed-off-by: Win <chatcharinsang@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
```
  8a466026
- [P/D] Add a shutdown method to the Connector API (#22699) · 61aa4b29
  Chauncey authored Sep 08, 2025
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
  61aa4b29
- [Doc] Fix UTF-8 encoding issues in documentation generation on Windows (#24361) · 8c892b18
  Al-Ekram Elahee Hridoy authored Sep 07, 2025
```
Signed-off-by: alekramelaheehridoy <aliqramalaheehridoy@gmail.com>
Signed-off-by: alekramelaheehridoy <alekramelaheehridoy@gmail.com>
Co-authored-by: alekramelaheehridoy <alekramelaheehridoy@gmail.com>
```
  8c892b18
- [CI/Build] Fix local image inputs in test_pixtral.py (#24401) · 3bca396f
  Chenheli Hua authored Sep 07, 2025
```
Signed-off-by: Chenheli Hua <huachenheli@outlook.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
```
  3bca396f
- [CI/Build] Disable flaky test_structured_output tests (#24404) · 3a3e91bd
  22quinn authored Sep 07, 2025
```
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
```
  3a3e91bd
- [Sampler] Support returning all prompt logprobs (#23868) · b3d7e3c8
  Xingyu Liu authored Sep 07, 2025
```
Signed-off-by: Xingyu Liu <charlotteliu12x@gmail.com>
Co-authored-by: 22quinn <33176974+22quinn@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
  b3d7e3c8
- [xpu] upgrade ipex/python3.12 for xpu (#23830) · 67841317
  Yan Ma authored Sep 08, 2025
```
Signed-off-by: Yan Ma <yan.ma@intel.com>
```
  67841317
- [Kernel] Support decode context parallelism on Blackwell with CUTLASS MLA (#24385) · 86173ad5
  Ming Yang authored Sep 07, 2025
```
Signed-off-by: Ming Yang <minos.future@gmail.com>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
```
  86173ad5
- Add @luccafong to codeowner for spec decode (#24397) · 795b6951
  Lucia Fang authored Sep 07, 2025
```
Signed-off-by: Lu Fang <fanglu@fb.com>
```
  795b6951
07 Sep, 2025 9 commits
- Skip MM Encoder for non-first PP ranks (#24387) · 2e5d2137
  Woosuk Kwon authored Sep 07, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  2e5d2137
- Add renderer-based prompt processing for embedding and classification endpoints (#24356) · 0661cb9d
  Flora Feng authored Sep 07, 2025
```
Signed-off-by: sfeng33 <4florafeng@gmail.com>
```
  0661cb9d
- [TPU] Remove TopKTopPSampler dependency for TPU sampler (#24391) · 105d3d62
  Woosuk Kwon authored Sep 07, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  105d3d62
- [Bugfix] Fix Qwen3-coder moe tuned config (#24072) · 62f66be1
  Jee Jee Li authored Sep 07, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  62f66be1
- [Misc] collect flashinfer version in collect_env.py (#24378) · 81c53ef5
  Ye (Charlotte) Qi authored Sep 06, 2025
```
Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com>
```
  81c53ef5
- QWEN3 Thinking Fused MoE kernels Optimization configs (#24330) · 75334956
  Saman A. Pour authored Sep 06, 2025
```
Signed-off-by: Saman Keon <samanamp@outlook.com>
```
  75334956
- [Benchmark] add benchmark for custom activation op (#23908) · 77aec83b
  Jiangyun Zhu authored Sep 07, 2025
```
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Signed-off-by: Jiangyun Zhu <riverclouds.zhu@qq.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
```
  77aec83b
- [CI][Fix] deterministic seed for flaky CI runs on structured outputs (#24380) · e6759754
  Aaron Pham authored Sep 06, 2025
```
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
```
  e6759754
- Migrate Qwen2 inputs to TensorSchema (#23475) · 37a6fa95
  Benji Beck authored Sep 06, 2025
```
Signed-off-by: Benji Beck <benjibeck@meta.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  37a6fa95