Commits · a3432f18fdd85eb18e29fc32327507fe1063ad57 · OpenDAS / vllm_cscc · GitLab

28 Aug, 2025 17 commits
- [BugFix][Spec Decode] Use float64 for uniform_probs (#23803) · a3432f18
  Woosuk Kwon authored Aug 28, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  a3432f18
- [CI/Build][Bugfix] Fix Qwen VL tests on CPU (#23818) · 67cee40d
  Li, Jiang authored Aug 28, 2025
```
Signed-off-by: jiang1.li <jiang1.li@intel.com>
```
  67cee40d
- [Doc]: fix typos in .md files (including those of #23751) (#23825) · d99c3a4f
  Didier Durand authored Aug 28, 2025
```
Signed-off-by: Didier Durand <durand.didier@gmail.com>
```
  d99c3a4f
- [FIXBUG] Add return_success parameter to moe_wna16_weight_loader function (#22797) · 3462c1c5
  JartX authored Aug 28, 2025
```
Signed-off-by: JartX <sagformas@epdcenter.es>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
  3462c1c5
- [Model] Add PP support and VLM backbone compatability for GPT-OSS (#23680) · c5d004aa
  Isotr0py authored Aug 28, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  c5d004aa
- [New Model]: Support GteNewModelForSequenceClassification (#23524) · 11a7fafa
  wang.yuqi authored Aug 28, 2025
```
Signed-off-by: wang.yuqi <noooop@126.com>
```
  11a7fafa
- [Kernel] cuda kernels for upcoming decode context parallel feature (#23791) · 186aced5
  yzds authored Aug 28, 2025
```
Co-authored-by: hongchao <hongchao@msh.team>
```
  186aced5
- [Bugfix] when set offline model running error (#23711) · daa1273b
  rongfu.leng authored Aug 28, 2025
```
Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>
```
  daa1273b
- [CI] enable idefics3 and fuyu-8b test in multimodal test (#23790) · c07a7331
  Jiangyun Zhu authored Aug 28, 2025
```
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
```
  c07a7331
- [Transform] [Quantization] Add transforms to compressed tensors (#22486) · 22feac8e
  Kyle Sayers authored Aug 28, 2025
  
  22feac8e
- Add deprecation warning for lora_extra_vocab_size (#23635) · c8851a47
  Jinheng authored Aug 28, 2025
```
Signed-off-by: Jinheng Li <ahengljh@gmail.com>
```
  c8851a47
- [CI] make all multi-gpu weight loading tests run nightly (#23792) · f48a9af8
  Alex authored Aug 27, 2025
```
Signed-off-by: Alex Yun <alexyun04@gmail.com>
```
  f48a9af8
- Gracefully handle edge cases in harmony utils (#23155) · a11adafd
  Jan Kessler authored Aug 28, 2025
```
Signed-off-by: Jan Kessler <jakessle@uni-mainz.de>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
  a11adafd
- [Perf] Tune configs for triton block fp8 gemm H100/H200 (#23748) · a781e84e
  Michael Goin authored Aug 27, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  a781e84e
- [Feature] models: pass layer prefix to replace_linear_class for per-layer... · 1b7b161a
  Shrey Gupta authored Aug 28, 2025
```
[Feature] models: pass layer prefix to replace_linear_class for per-layer quantization routing. Addresses #23239 (#23556)
Signed-off-by: Shrey Gupta <shreyg1303@gmail.com>
```
  1b7b161a
- Migrate Qwen inputs to TensorSchema (#23473) · a69693e3
  Benji Beck authored Aug 27, 2025
```
Signed-off-by: Benji Beck <benjibeck@meta.com>
```
  a69693e3
- [Bugfix] Fix for V1 priority scheduling crashes at preemption (#23713) · 5da4f5d8
  Hanchenli authored Aug 27, 2025
```
Signed-off-by: Hanchenli <lihanc2002@gmail.com>
```
  5da4f5d8
27 Aug, 2025 23 commits
- [Feature] Add `VLLM_DISABLE_PAD_FOR_CUDAGRAPH` to Avoid Hang Issue (#23595) · 321938e9
  Wentao Ye authored Aug 27, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  321938e9
- [Bugfix] Fix Marlin NVFP4 for modelopt (#23659) · f9ca2b40
  Michael Goin authored Aug 27, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  f9ca2b40
- DP/EP Support for gpt-oss with deepep-ht comm kernel on SM100 (#23608) · 082cc07e
  Yongye Zhu authored Aug 27, 2025
  
  082cc07e
- [V1][Mamba] - Enable V1 by default for Mamba Models (#23650) · 853c371f
  Asaf Joseph Gardin authored Aug 27, 2025
```
Signed-off-by: asafg <39553475+Josephasafg@users.noreply.github.com>
```
  853c371f
- [Multimodal] Generate mm_hash based on request metadata when caching is turned off (#23690) · 8bf6266a
  Roger Wang authored Aug 27, 2025
```
Signed-off-by: Roger Wang <hey@rogerw.io>
```
  8bf6266a
- Disable `torch.compile` for dynamic rope models in Transformers backend (#23738) · 0585a9e7
  Harry Mellor authored Aug 27, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  0585a9e7
- ci: Add arm64 docker build to release pipeline (#23210) · 3c0ef769
  Eli Uriegas authored Aug 27, 2025
```
Signed-off-by: Eli Uriegas <eliuriegas@meta.com>
Signed-off-by: Eli Uriegas <1700823+seemethere@users.noreply.github.com>
```
  3c0ef769
- [Docs] Fix warnings in `mkdocs build` (continued) (#23743) · 4e4d017b
  Hyogeun Oh (오효근) authored Aug 28, 2025
```
Signed-off-by: Zerohertz <ohg3417@gmail.com>
Signed-off-by: Hyogeun Oh (오효근) <ohg3417@gmail.com>
```
  4e4d017b
- [V1] [Hybrid] Enable compile and piecewise CUDA graph for MiniMax-Text models (#22589) · dd589322
  Thomas Parnell authored Aug 27, 2025
```
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
```
  dd589322
- [Model] Merge `SupportsMultiModalWithRawInput` with `SupportsMultiModal` (#23749) · 52883ed0
  Cyrus Leung authored Aug 28, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  52883ed0
- [BugFix] Fix topk_softmax assert (#19764) · 4f35be10
  Luka Govedič authored Aug 27, 2025
```
Signed-off-by: Luka Govedic <lgovedic@redhat.com>
```
  4f35be10
- [Docs] Remove in-tree Gaudi install instructions (#23628) · 2b61d2e2
  Harry Mellor authored Aug 27, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  2b61d2e2
- [LogitsProcs] Deduplicate built-in LP implementation logic (#23362) · 3ce8285d
  Nick Hill authored Aug 27, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  3ce8285d
- [Doc]: upgrade version of crate-ci tool for improved typo detection (#23755) · 83f555f6
  Didier Durand authored Aug 27, 2025
```
Signed-off-by: Didier Durand <durand.didier@gmail.com>
```
  83f555f6
- [Model] Enable native HF format InternVL support (#23742) · 84149043
  Isotr0py authored Aug 27, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  84149043
- [Feature] Add Hopper DeepGEMM E8M0 for DeepSeekV3.1 scale_fmt (#23666) · 3af47c3c
  Wentao Ye authored Aug 27, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
```
  3af47c3c
- Only run `get_attr_docs` if generating help text (#23723) · 513c1fe2
  Harry Mellor authored Aug 27, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  513c1fe2
- [Model] Interface to enable batch-level DP support (#23733) · fe8d7b6f
  Cyrus Leung authored Aug 27, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  fe8d7b6f
- Fix pre-commit on main (#23747) · 16dc4052
  Harry Mellor authored Aug 27, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  16dc4052
- Add vLLM Korea Meetup in the README.md and meetups.md (#23746) · 8dd2baa5
  rebel-hongseok authored Aug 27, 2025
```
Signed-off-by: rebel-hongseok <hongseok@rebellions.ai>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  8dd2baa5
- [Model] Explicit `default_pooling_type` interface (#23736) · 5eeef1b9
  Cyrus Leung authored Aug 27, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  5eeef1b9
- [V1] [Hybrid] Disable prefix caching by default for hybrid or mamba-based models (#23716) · 704432af
  Thomas Parnell authored Aug 27, 2025
```
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
```
  704432af
- [Misc] Remove unnecessary `_send_reconfig_message()` in `core_client.py` (#23127) · a403d0fa
  Nick Hill authored Aug 27, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  a403d0fa