Commits · 56ed7609a9d61ac43e89d62e0e9494ceea9a450d · OpenDAS / vllm_cscc

"vllm/config/model.py" did not exist on "e93f4cc9e37484009f74e15d3111a1f335c532a5"

24 Oct, 2025 2 commits

[MISC] `cudagraph_capture_sizes` related improvements (#26016) · 284cc922

fhl2000 authored Oct 24, 2025

Signed-off-by: fhl <2410591650@qq.com>
Signed-off-by: fhl2000 <63384265+fhl2000@users.noreply.github.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

284cc922

Fix pooling adapters for Transformers backend (#27338) · 1f9460c4
Harry Mellor authored Oct 24, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
1f9460c4

23 Oct, 2025 1 commit

[Feature] Pydantic validation for speculative.py (#27156) · faee3ccd

Navya Srivastava authored Oct 23, 2025


Signed-off-by: Navya Srivastava <navya.srivastava1707@gmail.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

faee3ccd

22 Oct, 2025 2 commits

[Feature] publisher default set zmq in kv_event config (#26915) · 8669c69a

rongfu.leng authored Oct 23, 2025


Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

8669c69a

[Frontend] Require flag for loading text and image embeds (#27204) · 58fab50d

Russell Bryant authored Oct 22, 2025


Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>

58fab50d

21 Oct, 2025 2 commits
- [V0 Deprecation] Remove V0 executors (#27142) · 647214f3
  Nick Hill authored Oct 21, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  647214f3
- [MM][Core] Decouple ViT backend from LM backend (#27061) · c3a2c6ac
  Roger Wang authored Oct 21, 2025
```
Signed-off-by: Roger Wang <hey@rogerw.io>
```
  c3a2c6ac
20 Oct, 2025 1 commit

[LoRA] LoRA cuda graph specialization (#25914) · b63f2143

Andy Lo authored Oct 20, 2025


Signed-off-by: Andy Lo <andy@mistral.ai>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>

b63f2143

19 Oct, 2025 2 commits
- Fix typo in ValueError message: use `kv_role` instead of `kv_disagg_role` (#27166) · 8a81d776
  Yongtao Huang authored Oct 20, 2025
```
Signed-off-by: Yongtao Huang <yongtaoh2022@gmail.com>
```
  8a81d776
- [Chore] Separate out `vllm.utils.network_utils` (#27164) · 7a6c8c3f
  iAmir97 authored Oct 19, 2025
```
Signed-off-by: iAmir97 <Amir.balwel@embeddedllm.com>
Co-authored-by: iAmir97 <Amir.balwel@embeddedllm.com>
```
  7a6c8c3f
18 Oct, 2025 3 commits

[Chore] Clean up pytorch helper functions in `vllm.utils` (#26908) · 6ac5e06f
Isotr0py authored Oct 19, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: isotr0py <2037008807@qq.com>
```
6ac5e06f

[Chore] Separate out `vllm.utils.mem_utils` (#27143) · 1d165d6d

iAmir97 authored Oct 18, 2025

Signed-off-by: iAmir97 <Amir.balwel@embeddedllm.com>
Signed-off-by: iAmir97 <71513472+iAmir97@users.noreply.github.com>
Co-authored-by: iAmir97 <Amir.balwel@embeddedllm.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

1d165d6d

[GPT-OSS] Structure_Tag support for gpt-oss tool-call in cot (#25515) · 7c572544

Hanchenli authored Oct 17, 2025


Signed-off-by: Hanchenli <lihanc2002@gmail.com>
Signed-off-by: Hanchenli <61769611+Hanchenli@users.noreply.github.com>
Signed-off-by: Wei Wei <wwei6@meta.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Wei Wei <wwei6@meta.com>
Co-authored-by: Wei Wei <weiweinpu@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

7c572544

17 Oct, 2025 3 commits
- [Bugfix] Use PIECEWISE cudagraphs on Blackwell if max_model_len > 131072 (#27114) · 950cf9e5
  Michael Goin authored Oct 17, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  950cf9e5
- [Docs] Replace `rst` style double-backtick with `md` single-backtick (#27091) · 6c9fdbf7
  Harry Mellor authored Oct 17, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  6c9fdbf7
- [Chore] Separate out `vllm.utils.importlib` (#27022) · 4d4d6bad
  Cyrus Leung authored Oct 17, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  4d4d6bad
16 Oct, 2025 5 commits
- Refactor Transformers backend to use mixins (#26906) · fb5e10d3
  Harry Mellor authored Oct 16, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  fb5e10d3
- [small][batch invariance] Rename the env and internal flags to simplify usage (#26855) · b2f78cba
  Bram Wasti authored Oct 16, 2025
```
Signed-off-by: Bram Wasti <bwasti@meta.com>
```
  b2f78cba
- Support block size of 256 used by Intel HPU (#26883) · ac3ed5a8
  Mandy Li authored Oct 16, 2025
```
Signed-off-by: mandy-li <mandy.j.li@intel.com>
```
  ac3ed5a8
- Deepseek-v3 Batch Invariant on 8xH100 (#26609) · 7d8975de
  Bram Wasti authored Oct 15, 2025
```
Signed-off-by: Bram Wasti <bwasti@meta.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
```
  7d8975de
- [BUG] Allow runai_streamer_sharded in config check (#26958) · 582f2c6b
  ahao-anyscale authored Oct 15, 2025
```
Signed-off-by: ahao-anyscale <ahao@anyscale.com>
```
  582f2c6b
15 Oct, 2025 4 commits

[Feature]: Use pydantic validation in observability.py config (#26637) · 14f84563

Sam/Samuel authored Oct 16, 2025

Signed-off-by: Samuel Wu <cernunnos1710@gmail.com>
Signed-off-by: Sam/Samuel <57896620+cern1710@users.noreply.github.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

14f84563

[Misc] rename torch_dtype to dtype (#26695) · 8f4b313c
wangxiyuan authored Oct 15, 2025
```
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
```
8f4b313c
[Platform] allow platform to init dp group (#22243) · db1764e4
wangxiyuan authored Oct 15, 2025
```
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
```
db1764e4

[Frontend][torch.compile] CompilationConfig Overhaul (#20283): name change ... · 96b9aa5a

Morrison Turnansky authored Oct 14, 2025


[Frontend][torch.compile] CompilationConfig Overhaul (#20283): name change  compilation level to compilation mode, deprecation compilation level (#26355)
Signed-off-by: morrison-turnansky <mturnans@redhat.com>
Signed-off-by: Morrison Turnansky <mturnans@redhat.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>

96b9aa5a

14 Oct, 2025 8 commits
- [torch.compile] Fix tests for torch==2.9 inductor partition (#26116) · 2dcd12d3
  Luka Govedič authored Oct 14, 2025
```
Signed-off-by: ProExpertProg <lgovedic@redhat.com>
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
```
  2dcd12d3
- use combo kernel to fuse qk-norm and qk-rope (#26682) · ca683a2a
  Boyuan Feng authored Oct 14, 2025
```
Signed-off-by: Boyuan Feng <boyuan@meta.com>
```
  ca683a2a
- [DCP] Support Decode Context Parallel (DCP) for GQA with FlashAttention (#24864) · ea97940d
  Jaya Yuan authored Oct 14, 2025
```
Signed-off-by: yuanyongjie.yyj <yuanyongjie.yyj@antgroup.com>
Signed-off-by: FENP <32334296+FENP@users.noreply.github.com>
Signed-off-by: Jaya Yuan <yuanyongjie.yyj@antgroup.com>
```
  ea97940d
- [Feature] Change vllm.py with pydantic validation (#26726) · c715ba37
  Vladislav Bronzov authored Oct 14, 2025
```
Signed-off-by: Vladislav <vladislav.bronzov@gmail.com>
Signed-off-by: Vladislav Bronzov <58587565+VladOS95-cyber@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  c715ba37
- [Chore] Remove `SupportsV0Only` interface and update supported models docs (#26783) · 9c4cb683
  Cyrus Leung authored Oct 14, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  9c4cb683
- [NIXL][HeteroTP] Enable KV transfer from HND prefill to NHD decode (#26556) · 7e6edb14
  Chendi.Xue authored Oct 14, 2025
```
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
```
  7e6edb14
- scheduler.py: Update the name of the default scheduler. (#26758) · 481545b3
  Ryan Li authored Oct 14, 2025
```
Signed-off-by: Ryan Li <ryanli@ryanli.org>
```
  481545b3
- [UX] Replace VLLM_ALL2ALL_BACKEND with --all2all-backend (#26732) · 3e051bda
  Michael Goin authored Oct 13, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  3e051bda
13 Oct, 2025 4 commits

[FrontEnd] UNREVERT CompilationConfig overhaul (#20283): deprecate... · e3fdb627

Morrison Turnansky authored Oct 13, 2025


[FrontEnd] UNREVERT CompilationConfig overhaul (#20283): deprecate use_inductor in favor of backend, simplify custom_ops  (#26502)
Signed-off-by: morrison-turnansky <mturnans@redhat.com>
Signed-off-by: Morrison Turnansky <mturnans@redhat.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Jiangyun Zhu <riverclouds.zhu@qq.com>