Commits · 2d7b09b998980b9ccbb3708632b47bc28de076aa · OpenDAS / vllm_cscc · GitLab

01 Aug, 2025 31 commits
- Deprecate `--disable-log-requests` and replace with `--enable-log-requests` (#21739) · 2d7b09b9
  Harry Mellor authored Aug 01, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  2d7b09b9
- [Docs] use `uv` in CPU installation docs (#22089) · 97608dc2
  David Xia authored Aug 01, 2025
```
Signed-off-by: David Xia <david@davidxia.com>
```
  97608dc2
- [BugFix] Don't change title of top-level process (#22032) · 3146519a
  Nick Hill authored Aug 01, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  3146519a
- [BugFix] Update AttnFusionPass cache key (#21947) · 8026a335
  Richard Zou authored Aug 01, 2025
```
Signed-off-by: Richard Zou <zou3519@gmail.com>
```
  8026a335
- [Refactor] Fix Compile Warning #1444-D (#21462) · a59cd9d9
  Wentao Ye authored Aug 01, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  a59cd9d9
- [Bugfix][PD] set max_completion_tokens=1 if req has this value (#21841) · 5c54d975
  Abirdcfly authored Aug 01, 2025
```
Signed-off-by: Abirdcfly <fp544037857@gmail.com>
```
  5c54d975
- feat(multimodal): Add customizable background color for RGBA to RGB conversion (#22052) · 0a6d305e
  Gamhang authored Aug 01, 2025
```
Signed-off-by: Jinheng Li <ahengljh@gmail.com>
Co-authored-by: Jinheng Li <ahengljh@gmail.com>
```
  0a6d305e
- [Bugfix] Check NVIDIA artifactory is accessible before using flashinfer cubin kernels (#21893) · f81c1bb0
  Michael Goin authored Aug 01, 2025
  
  f81c1bb0
- Fix `get_kwargs` for case where type hint is `list[Union[str, type]]` (#22016) · fb0e0d46
  Harry Mellor authored Aug 01, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  fb0e0d46
- [BUG] [ROCm] Fix import bug on ROCm (#22083) · 26b5f7bd
  TJian authored Aug 01, 2025
```
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
```
  26b5f7bd
- [Speculative Decoding] Add `speculators` config support (#21345) · dfbc1f88
  Dipika Sikka authored Aug 01, 2025
  
  dfbc1f88
- Revert "Update sampling_metadata.py (#21937)" (#22088) · 87c94bc8
  Harry Mellor authored Aug 01, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  87c94bc8
- [Quantization] Enable BNB support for InternS1 (#21953) · 28b18cc7
  Jee Jee Li authored Aug 01, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  28b18cc7
- [Doc] Added warning of speculating with draft model (#22047) · 49314869
  WeiQing Chen authored Aug 01, 2025
```
Signed-off-by: Dilute-l <dilu2333@163.com>
Co-authored-by: Dilute-l <dilu2333@163.com>
```
  49314869
- [Misc] Remove upper bound in openai package version (#22060) · 0f81b310
  Woosuk Kwon authored Aug 01, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  0f81b310
- [Bugfix] Add log prefix in non-dp mode engine core (#21889) · e6680f9e
  wuhang authored Aug 01, 2025
```
Signed-off-by: wuhang <wuhang6@huawei.com>
```
  e6680f9e
- [Doc] Add example for Step3-VL (#22061) · 27a145e8
  Roger Wang authored Aug 01, 2025
```
Signed-off-by: Roger Wang <hey@rogerw.me>
```
  27a145e8
- Revert precompile wheel changes (#22055) · da31f6ad
  Simon Mo authored Aug 01, 2025
  
  da31f6ad
- [Frontend] Align tool_choice="required" behavior with OpenAI when tools is empty (#21052) · 98df153a
  Sungyoon Jeong authored Aug 01, 2025
```
Signed-off-by: Sungyoon Jeong <sungyoon.jeong@furiosa.ai>
```
  98df153a
- [Core] Avoid repeated len(block_token_ids) check in hash_request_tokens (#21781) · e0f63e4a
  Zebing Lin authored Aug 01, 2025
```
Signed-off-by: linzebing <linzebing1995@gmail.com>
```
  e0f63e4a
- [Bugfix] Disable multi-modal preprocessor cache for DP (#21896) · b4e081cb
  Cyrus Leung authored Aug 01, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  b4e081cb
- [Doc] Fix a syntax error of example code in structured_outputs.md (#22045) · 79731a79
  Hongsheng Liu authored Aug 01, 2025
```
Signed-off-by: wangzi <3220100013@zju.edu.cn>
Co-authored-by: wangzi <3220100013@zju.edu.cn>
```
  79731a79
- Update sampling_metadata.py (#21937) · 53d7c392
  Aviad Rossmann authored Aug 01, 2025
```
Signed-off-by: Aviad Rossmann <aviadr@neureality.ai>
```
  53d7c392
- [Doc] Add Voxtral to Supported Models page (#22059) · 61dcc280
  Cyrus Leung authored Aug 01, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  61dcc280
- [Model] [Quantization] Support quantization for Gemma3n (#21974) · 0f46a780
  Kyle Sayers authored Aug 01, 2025
```
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
```
  0f46a780
- [BugFix] fix: aot passes kvcache dtype information (#19750) · e1a7fe4a
  Mickaël Seznec authored Aug 01, 2025
```
Signed-off-by: Mickael Seznec <mickael@mistral.ai>
```
  e1a7fe4a
- [Misc] Automatically resolve HF processor init kwargs (#22005) · 82de9b9d
  Cyrus Leung authored Aug 01, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  82de9b9d
- [Bugfix] Fix: Fix multi loras with tp >=2 and LRU cache (#20873) · ad57f23f
  Charent authored Aug 01, 2025
```
Signed-off-by: charent <19562666+charent@users.noreply.github.com>
```
  ad57f23f
- [Refactor] Remove Duplicate `per_block_cast_to_fp8`, Remove Dependencies of DeepGEMM (#21787) · 37006420
  Wentao Ye authored Jul 31, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  37006420
- Move flashinfer-python to optional extra `vllm[flashinfer]` (#21959) · 0bd409cf
  Michael Goin authored Jul 31, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  0bd409cf
- Add DeepGEMM to Dockerfile in vllm-base image (#21533) · e360316a
  Matthew Bonanni authored Jul 31, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
```
  e360316a
31 Jul, 2025 9 commits
- [Feature] Add Flashinfer MoE Support for Compressed Tensor NVFP4 (#21639) · c3e0e933
  Wentao Ye authored Jul 31, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  c3e0e933
- Add FlashInfer allreduce RMSNorm Quant fusion (#21069) · 6e672daf
  Ilya Markov authored Jul 31, 2025
```
Signed-off-by: ilmarkov <imarkov@redhat.com>
Signed-off-by: ilmarkov <markovilya197@gmail.com>
Co-authored-by: ilmarkov <imarkov@redhat.com>
```
  6e672daf
- [Bugfix] Fix MTP weight loading (#21941) · 2dff2e21
  Benjamin Chislett authored Jul 31, 2025
  
  2dff2e21
- [Misc] Add unit tests for chunked local attention (#21692) · 71470bc4
  Yong Hoon Shin authored Jul 31, 2025
```
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
```
  71470bc4
- [Meta] Official Eagle mm support, first enablement on llama4 (#20788) · 9e0726e5
  zhiweiz authored Jul 31, 2025
```
Signed-off-by: morgendave <morgendave@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.me>
```
  9e0726e5
- Update torch_xla pin to 20250730 (#21956) · 53c21e49
  XiongfeiWei authored Jul 31, 2025
```
Signed-off-by: Xiongfei Wei <isaacwxf23@gmail.com>
```
  53c21e49
- Removing amdproduction Tests (#22027) · 0780bb57
  Alexei-V-Ivanov-AMD authored Jul 31, 2025
```
Signed-off-by: Alexei V. Ivanov <alexei.ivanov@amd.com>
```
  0780bb57
- fix(setup): improve precompiled wheel setup for Docker builds (#22025) · 58bb9021
  Doug Smith authored Jul 31, 2025
```
Signed-off-by: dougbtv <dosmith@redhat.com>
```
  58bb9021
- [ez] Remove a trailing space from compilation/decorators.py (#22028) · 7349d526
  Zhengxu Chen authored Jul 31, 2025
  
  7349d526