Commits · 749be00a98eef8eab262cc3119893c00dbca22e9 · OpenDAS / vllm_cscc

30 Aug, 2025 3 commits
- [LoRA] Much faster startup when LoRA is enabled (#23777) · 038e9be4
  Andy Lo authored Aug 30, 2025
```
Signed-off-by: Andy Lo <andy@mistral.ai>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
```
  038e9be4
- [Refactor] refactor freezing_value/cuda_event initialize outside try finally (#23758) · e80bca30
  Ning Xie authored Aug 30, 2025
```
Signed-off-by: Andy Xie <andy.xning@gmail.com>
```
  e80bca30
- [Core] Cleanup TPU model runner for MM (#23894) · f1bddbd8
  Cyrus Leung authored Aug 30, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  f1bddbd8
29 Aug, 2025 3 commits
- [BugFix] Async scheduling and PP compatibility with DP (#23770) · d90d8eb6
  Nick Hill authored Aug 29, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  d90d8eb6
- [Performance] V1 Classify Models E2E Performance Optimization (#23541) · d9e00dbd
  wang.yuqi authored Aug 29, 2025
```
Signed-off-by: wang.yuqi <noooop@126.com>
```
  d9e00dbd
- [CPU] Enable data parallel for CPU backend (#23903) · ad39106b
  Li, Jiang authored Aug 29, 2025
```
Signed-off-by: jiang1.li <jiang1.li@intel.com>
```
  ad39106b
28 Aug, 2025 2 commits
- [V1] Enable prefill optimization for Gemma3n (#22628) · cb293f6a
  Yong Hoon Shin authored Aug 28, 2025
```
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
```
  cb293f6a
- [Doc]: fix typos in Python scripts (#23828) · d3da2eea
  Didier Durand authored Aug 28, 2025
```
Signed-off-by: Didier Durand <durand.didier@gmail.com>
```
  d3da2eea
27 Aug, 2025 6 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
- [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
- [Model] Merge `SupportsMultiModalWithRawInput` with `SupportsMultiModal` (#23749) · 52883ed0
  Cyrus Leung authored Aug 28, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  52883ed0
- [Misc] Move CpuGpuBuffer to vllm/v1/utils.py (#23728) · 04ff1e43
  Woosuk Kwon authored Aug 27, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  04ff1e43
- [XPU]fix cuda event used in XPU model runner (#23708) · 64466778
  Kunshang Ji authored Aug 27, 2025
```
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
```
  64466778
- [Core] Use key-only cache for `BaseMultiModalProcessor` (#23018) · 69244e67
  Cyrus Leung authored Aug 27, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  69244e67
26 Aug, 2025 4 commits

[Bugfix] Fix cuda event usage with CPU model runner (#23643) · 9b018700
Li, Jiang authored Aug 27, 2025
```
Signed-off-by: jiang1.li <jiang1.li@intel.com>
```
9b018700
Support FlashAttention Backend for Hybrid SSM Models (#23299) · 2b4fc9bd
Chen Zhang authored Aug 26, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
2b4fc9bd

[Disagg][Perf] Use CUDA event sync instead of blocking `tolist` to avoid... · b395b3b0

Zijing Liu authored Aug 25, 2025


[Disagg][Perf] Use CUDA event sync instead of blocking `tolist` to avoid unintentional copy ops blocking across different CUDA streams, improving disagg TTIT/TTFT (#22760)
Signed-off-by: Zijing Liu <liuzijing2014@gmail.com>
Signed-off-by: Zijing Liu <liuzijing2014@users.noreply.github.com>

b395b3b0

Update Flashinfer to 0.2.14.post1 (#23537) · ae067888

weiliang authored Aug 26, 2025


Signed-off-by: Siyuan Fu <siyuanf@nvidia.com>
Signed-off-by: siyuanf <siyuanf@nvidia.com>
Signed-off-by: Weiliang Liu <weiliangl@nvidia.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Siyuan Fu <siyuanf@nvidia.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

ae067888

25 Aug, 2025 5 commits

[XPU] Delay BF16 check to worker init for spawn compatibility (#22979) · 8a044754
Chaojun Zhang authored Aug 26, 2025
```
Signed-off-by: chzhang <chaojun.zhang@intel.com>
```
8a044754
[test][RL] Add sleep level 2 test and fix reload with sleep mode (#23521) · 2a167b2e
22quinn authored Aug 25, 2025
```
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
```
2a167b2e

[Refactor] Refactor persistent buffers with CpuGpuBuffer (#23515) · 0ff902f3

Woosuk Kwon authored Aug 25, 2025


Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

0ff902f3

[Attention] Unify mamba and attention backend selection (#23171) · 5c4b6e66
Ayush Satyam authored Aug 25, 2025
```
Signed-off-by: Ayush Satyam <ayushsatyam146@gmail.com>
```
5c4b6e66

[Core][Multimodal] Track encode cache entries by mm_hash and enable embedding... · d765cf01

Chenguang Zheng authored Aug 25, 2025


[Core][Multimodal] Track encode cache entries by mm_hash and enable embedding sharing between requests (#22711)
Signed-off-by: knlnguyen1802 <knlnguyen1802@gmail.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: knlnguyen1802 <knlnguyen1802@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>

d765cf01

24 Aug, 2025 1 commit
- [Misc] Remove unused slot_mapping buffer (#23502) · ad788684
  Woosuk Kwon authored Aug 24, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  ad788684
23 Aug, 2025 1 commit
- [BugFix] Fix batch updates for pooling models (#23398) · c80c53a3
  Nick Hill authored Aug 22, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  c80c53a3
22 Aug, 2025 3 commits
- [Misc] local import code clean (#23420) · 325aa3de
  Ning Xie authored Aug 22, 2025
```
Signed-off-by: Andy Xie <andy.xning@gmail.com>
```
  325aa3de
- [Misc] Move M-RoPE init logic to _init_mrope_positions (#23422) · 808d2e9a
  Woosuk Kwon authored Aug 22, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  808d2e9a
- [Attention] Refactor AttentionMetadata Preparation for Encoder-only Models (#23154) · 17373dcd
  Chen Zhang authored Aug 21, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  17373dcd
21 Aug, 2025 4 commits
- [Misc] Misc code cleanup/simplification (#23304) · 603fbbbc
  Nick Hill authored Aug 21, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  603fbbbc
- [Performance] V1 Pooling Models E2E Performance Optimization (#23162) · d70a1662
  wang.yuqi authored Aug 21, 2025
```
Signed-off-by: wang.yuqi <noooop@126.com>
```
  d70a1662
- [Refactor] Simplify code for MM budget (#23310) · 0c6e40bb
  Cyrus Leung authored Aug 21, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  0c6e40bb
- [Optimization] Make new_block_ids None if empty (#23262) · b029de99
  Woosuk Kwon authored Aug 20, 2025
```
Signed-off-by: Woosuk Kwon <woosuk@thinkingmachines.ai>
```
  b029de99
20 Aug, 2025 2 commits

[Feature] use --eplb_config to set eplb param (#20562) · 4fbda0b2

rongfu.leng authored Aug 21, 2025


Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: rongfu.leng <lenronfu@gmail.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

4fbda0b2

[Misc] Add max_seq_len to CommonAttentionMetadata (#23216) · d6d13bd4
Woosuk Kwon authored Aug 20, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
d6d13bd4

19 Aug, 2025 5 commits
- [Misc] Fix seq_lens for graph capture (#23175) · 40f26734
  Woosuk Kwon authored Aug 19, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  40f26734
- [Misc] Avoid accessing req_ids inside a loop (#23159) · 21bcc826
  Woosuk Kwon authored Aug 19, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  21bcc826
- [Hardware][IBM Z]Enable v1 for s390x and s390x dockerfile fixes (#22725) · 78dba404
  Nikhil Suryawanshi authored Aug 19, 2025
```
Signed-off-by: Nikhil Suryawanshi <suryawanshin74@gmail.com>
```
  78dba404
- [TPU] make ptxla not imported when using tpu_commons (#23081) · e9d6a3db
  Chengji Yao authored Aug 18, 2025
```
Signed-off-by: Chengji Yao <chengjiyao@gmail.com>
Signed-off-by: Chengji Yao <chengjiyao@google.com>
Co-authored-by: Chengji Yao <chengjiyao@gmail.com>
```
  e9d6a3db
- [Spec Decode] Make `propose_draft_token_ids` non-blocking for lower TTFT (#23041) · c9b38be8
  Woosuk Kwon authored Aug 18, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  c9b38be8
18 Aug, 2025 1 commit
- [Misc] Minor refactoring for prepare_inputs (#23116) · 0dd3f4f5
  Woosuk Kwon authored Aug 18, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  0dd3f4f5