Commits · 178d03fbd64e18999647b349623cd1489f816c8c · OpenDAS / vllm_cscc

"vscode:/vscode.git/clone" did not exist on "e4791438eda469d4263e2ce2ab0236f61f3c6ebc"

06 Aug, 2025 11 commits

[gpt-oss] Add Tool/ConversationContext classes and harmony_utils (#22340) · 178d03fb

Woosuk Kwon authored Aug 06, 2025


Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Co-authored-by: LiuXiaoxuanPKU <lilyliupku@gmail.com>
Co-authored-by: simon-mo <xmo@berkeley.edu>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>
Co-authored-by: Hongxia Yang <62075498+hongxiayang@users.noreply.github.com>
Co-authored-by: Minseok Lee <47620120+minseokl@users.noreply.github.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>

178d03fb

[gpt-oss] flashinfer attention sink init (#22330) · 90ec0069

Yongye Zhu authored Aug 05, 2025


Signed-off-by: simon-mo <xmo@berkeley.edu>
Co-authored-by: LiuXiaoxuanPKU <lilyliupku@gmail.com>
Co-authored-by: simon-mo <xmo@berkeley.edu>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Co-authored-by: Hongxia Yang <62075498+hongxiayang@users.noreply.github.com>
Co-authored-by: Minseok Lee <47620120+minseokl@users.noreply.github.com>

90ec0069

[GptOss] Add GptOss reasoning parser to support structure output (#22322) · a47e6ffe

Chen Zhang authored Aug 05, 2025


Signed-off-by: Chen Zhang <zhangch99@outlook.com>
Co-authored-by: LiuXiaoxuanPKU <lilyliupku@gmail.com>
Co-authored-by: simon-mo <xmo@berkeley.edu>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Co-authored-by: Hongxia Yang <62075498+hongxiayang@users.noreply.github.com>
Co-authored-by: Minseok Lee <47620120+minseokl@users.noreply.github.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>

a47e6ffe

[ROCm] Add attention sink to use_rocm_custom_paged_attention (#22329) · 98a3a810

Woosuk Kwon authored Aug 05, 2025


Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Co-authored-by: LiuXiaoxuanPKU <lilyliupku@gmail.com>
Co-authored-by: simon-mo <xmo@berkeley.edu>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>
Co-authored-by: Hongxia Yang <62075498+hongxiayang@users.noreply.github.com>
Co-authored-by: Minseok Lee <47620120+minseokl@users.noreply.github.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>

98a3a810

Add GPT-OSS model code and config [1/N] (#22327) · de98252f
Woosuk Kwon authored Aug 05, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
de98252f

Update transformers to `v4.55` (#21931) · 796bae07

Harry Mellor authored Aug 06, 2025


Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Isotr0py <2037008807@qq.com>
Signed-off-by: isotr0py <2037008807@qq.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

796bae07

Add attention sink in attention backends (#22320) · 6e209243

Woosuk Kwon authored Aug 05, 2025


Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Co-authored-by: LiuXiaoxuanPKU <lilyliupku@gmail.com>
Co-authored-by: simon-mo <xmo@berkeley.edu>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>
Co-authored-by: Hongxia Yang <62075498+hongxiayang@users.noreply.github.com>
Co-authored-by: Minseok Lee <47620120+minseokl@users.noreply.github.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>

6e209243

[Bugfix] Skip dead and non-GPU nodes for Ray DP engine allocation (#22275) · 302962e8
Rui Qiao authored Aug 05, 2025
```
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
```
302962e8
[Perf] Parallelize fill_bitmask to accelerate high-throughput guided decoding (#21862) · 7e6544c7
Benjamin Chislett authored Aug 05, 2025
```
Signed-off-by: Benjamin Chislett <benjamin.chislett@centml.ai>
```
7e6544c7
[Bugfix] Fix MoE BNB version (#22260) · 8e6c7e87
Jee Jee Li authored Aug 06, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
8e6c7e87
[Bugfix] Fix 3D input passed into cutlass_scaled_mm (#22278) · 6a515304
Michael Goin authored Aug 05, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
6a515304

05 Aug, 2025 23 commits
- [V1] port xformers backend to v1 (#21342) · 469b3ffa
  Giancarlo Delfin authored Aug 05, 2025
```
Signed-off-by: Giancarlo Delfin <gdelfin@meta.com>
```
  469b3ffa
- [Refactor] Remove Unused Environment Variable `VLLM_NO_DEPRECATION_WARNING` (#22199) · ae87ddd0
  Wentao Ye authored Aug 05, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  ae87ddd0
- [Misc] correct static type check for GroupCoordinator (#21946) · 74333ae2
  Ning Xie authored Aug 05, 2025
```
Signed-off-by: Andy Xie <andy.xning@gmail.com>
```
  74333ae2
- [NVIDIA] Support Flashinfer TRT-LLM Prefill Attention Kernel (#22095) · 83156c7b
  elvischenv authored Aug 05, 2025
```
Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
```
  83156c7b
- [Feature] Non-contiguous Support for FP8 Quantization (#21961) · 4771df7b
  Wentao Ye authored Aug 05, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
```
  4771df7b
- Migrate KimiVLImagePixelInputs to TensorSchema (#21769) · 05fae021
  Benji Beck authored Aug 05, 2025
```
Signed-off-by: Benji Beck <benjibeck@meta.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
```
  05fae021
- [Model] Pooling model activation supports per request control by PoolingParams (#20538) · 586f2867
  wang.yuqi authored Aug 05, 2025
```
Signed-off-by: wang.yuqi <noooop@126.com>
```
  586f2867
- [Core] Factor out common logic for MM budget calculation (#22228) · 811ac13d
  Cyrus Leung authored Aug 05, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  811ac13d
- [UX] Fail if an invalid attention backend is specified (#22217) · e79a12fc
  Michael Goin authored Aug 05, 2025
```
Signed-off-by: mgoin <michael@neuralmagic.com>
```
  e79a12fc
- [Bugfix] Misaligned params in TreeAttentionImpl (#22226) · cdfd6871
  Cyrus Leung authored Aug 05, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  cdfd6871
- Optimize configuration access with LRU cache in custom ops (#22204) · 4b3e4474
  ZiTian.Zhao authored Aug 05, 2025
```
Signed-off-by: zitian zhao <zitian.zhao@tencentmusic.com>
```
  4b3e4474
- [Misc] log more detailed message for ensure_model_parallel_initialized (#22144) · bd3db7f4
  Ning Xie authored Aug 05, 2025
```
Signed-off-by: Andy Xie <andy.xning@gmail.com>
```
  bd3db7f4
- [Doc] add backend to doc string of initialize_model_parallel (#22142) · 29b97c09
  Ning Xie authored Aug 05, 2025
```
Signed-off-by: Andy Xie <andy.xning@gmail.com>
```
  29b97c09
- [Misc] Remove pass_config from CompilationConfig dump_json excluded (#21911) · 7b455cf1
  elvischenv authored Aug 05, 2025
```
Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
```
  7b455cf1
- fix: kimi_k2 return empty tool call list (#22149) · 8a6e108e
  tlipoca9 authored Aug 05, 2025
```
Signed-off-by: tlipoca9 <tlipoca9@gmail.com>
```
  8a6e108e
- [Log] DeepGEMM Update Log for Unaligned Problem Size (#22208) · d7b28f34
  Wentao Ye authored Aug 04, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  d7b28f34
- self.gate dtype update for GLM-4.5 (#22203) · 6fa41e0c
  Yuxuan Zhang authored Aug 05, 2025
```
Signed-off-by: zRzRzRzRzRzRzR <2448370773@qq.com>
```
  6fa41e0c
- [ROCm][Bugfix] Compilation passes fix (#22202) · 031ca762
  Gregory Shtrasberg authored Aug 04, 2025
```
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
```
  031ca762
- [FEAT] Refactor ROPE into module (#22192) · 6ad6b8e1
  TJian authored Aug 04, 2025
```
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
```
  6ad6b8e1
- [V0 deprecation][P/D] Deprecate v0 `KVConnectorBase` code (1/2) (#21785) · f4f4e7ef
  lkchen authored Aug 04, 2025
```
Signed-off-by: Linkun Chen <github@lkchen.net>
```
  f4f4e7ef
- Revert "[Bugfix] V1 Fix the cursor leakage issue during request scheduling." (#22223) · 71758176
  Woosuk Kwon authored Aug 04, 2025
  
  71758176
- [Bugfix] V1 Fix the cursor leakage issue during request scheduling. (#21173) · 2dffac46
  PiteXChen authored Aug 05, 2025
```
Signed-off-by: CLFutureX <775523362@qq.com>
```
  2dffac46
- [NVIDIA] Auto detect modelopt quant and fix DSR1-FP4 weight loading (#22073) · bdcb42e4
  Po-Han Huang (NVIDIA) authored Aug 05, 2025
  
  bdcb42e4
04 Aug, 2025 6 commits
- [Responses API] Ignore `store=True` and process the request by default (#22185) · 9af654cc
  Woosuk Kwon authored Aug 04, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  9af654cc
- Fix Arcee model weight loading: Add custom load_weights (#21725) · a5fff3bd
  Raghav Ravishankar authored Aug 04, 2025
```
Signed-off-by: alyosha-swamy <raghav@arcee.ai>
```
  a5fff3bd
- [Sampler] Support returning all logprobs or logits (#21792) · 54de71d0
  22quinn authored Aug 04, 2025
```
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
```
  54de71d0
- [Bugfix] Fix failing GGUF models test (#22174) · fed5849d
  Isotr0py authored Aug 04, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  fed5849d
- [feat] move WEIGHT_SCALE_SUPPORTED into raise block to accelerate RLHF weight loading (#21164) · c1b4eb04
  Weixiao Huang authored Aug 04, 2025
```
Signed-off-by: huangweixiao <huangweixiao@msh.team>
```
  c1b4eb04
- [Misc] Modify the organization of GLM series (#22171) · a7b8788d
  Jee Jee Li authored Aug 04, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  a7b8788d