Commits · d4e547bb7e06ab05c56a567b9a9f33b6c893dc66 · OpenDAS / vllm_cscc

04 Nov, 2025 2 commits
- Revert "[PERF] Decouple projections from GDN custom op" (#28080) · d4e547bb
  Vadim Gimpelson authored Nov 05, 2025
```
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
```
  d4e547bb
- [PERF] Decouple projections from GDN custom op (#27512) · 5fd8f02e
  Vadim Gimpelson authored Nov 04, 2025
```
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
```
  5fd8f02e
03 Nov, 2025 1 commit

[BUG] Make 'binary' default option for saving torch compile artifacts when... · cac4c10e

ahao-anyscale authored Nov 03, 2025


[BUG] Make 'binary' default option for saving torch compile artifacts when using standalone_compile (#27616)
Signed-off-by: ahao-anyscale <ahao@anyscale.com>

cac4c10e

30 Oct, 2025 1 commit

[Model] Introduce Kimi Linear to vLLM (#27809) · 4e68cc9b

Zhiyuan Li authored Oct 30, 2025


Signed-off-by: lizhiyuan <lizhiyuan@moonshot.cn>
Signed-off-by: Zhiyuan Li <uniartisan2017@gmail.com>

4e68cc9b

28 Oct, 2025 1 commit

[Misc][qwen2_5_vl][torch.compile] Enable `supports_torch_compile` on generic... · 94666612

Lucas Kabela authored Oct 28, 2025


[Misc][qwen2_5_vl][torch.compile] Enable `supports_torch_compile` on generic nn.Module and demonstrate speedup on Qwen Vision model (#23207)
Signed-off-by: Lucas Kabela <lucaskabela@meta.com>
Signed-off-by: Lucas Kabela <lucasakabela@gmail.com>

94666612

24 Oct, 2025 1 commit

[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

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

18 Oct, 2025 1 commit
- [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
17 Oct, 2025 1 commit
- [Chore] Separate out `vllm.utils.importlib` (#27022) · 4d4d6bad
  Cyrus Leung authored Oct 17, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  4d4d6bad
15 Oct, 2025 1 commit

[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 2 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
13 Oct, 2025 1 commit

[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>

e3fdb627

12 Oct, 2025 1 commit
- Update `Optional[x]` -> `x | None` and `Union[x, y]` to `x | y` (#26633) · 8fcaaf6a
  Harry Mellor authored Oct 12, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  8fcaaf6a
11 Oct, 2025 1 commit
- [compile] Fix inductor partition config (#26645) · 01653a91
  Angela Yi authored Oct 11, 2025
```
Signed-off-by: angelayi <yiangela7@gmail.com>
```
  01653a91
10 Oct, 2025 2 commits

[torch.compile] Make inductor partition rules respect splitting_ops #25691 (#25845) · cddce79f

baonudesifeizhai authored Oct 10, 2025

Signed-off-by: baonudesifeizhai <baonudesifeizhai@gmail.com>
Signed-off-by: baonudesifeizhai <85092850+baonudesifeizhai@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>

cddce79f

[Spec-Decode] Support piecewise cudagraphs for Eagle head (#25109) · 29255cfc

Lucas Wilkinson authored Oct 10, 2025


Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Benjamin Chislett <chislett.ben@gmail.com>

29255cfc

09 Oct, 2025 2 commits

Revert #26113 "[Frontend] CompilationConfig overhaul (#20283): deprecate... · 5728da11

Jiangyun Zhu authored Oct 09, 2025


Revert  #26113 "[Frontend] CompilationConfig overhaul (#20283): deprecate use_inductor in favor of backend, simplify custom_ops" (#26472)
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>

5728da11

Separate MLAAttention class from Attention (#25103) · e614ab78

Naveenraj Kamalakannan authored Oct 08, 2025

Signed-off-by: Naveenraj Kamalakannan <therealnaveenkamal@gmail.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>

e614ab78

07 Oct, 2025 1 commit

[Frontend] CompilationConfig overhaul (#20283): deprecate use_inductor in... · 0c824fc4

Morrison Turnansky authored Oct 07, 2025


[Frontend] CompilationConfig overhaul (#20283): deprecate use_inductor in favor of backend, simplify custom_ops (#26113)
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>

0c824fc4

05 Oct, 2025 1 commit
- Convert formatting to use `ruff` instead of `yapf` + `isort` (#26247) · d6953beb
  Harry Mellor authored Oct 05, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  d6953beb
30 Sep, 2025 1 commit

[New Model] DeepSeek-V3.2 (Rebased to Main) (#25896) · fa7e254a

Yongye Zhu authored Sep 30, 2025


Signed-off-by: Chen Zhang <zhangch99@outlook.com>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: NickLucche <nlucches@redhat.com>
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Signed-off-by: Barry Kang <43644113+Barry-Delaney@users.noreply.github.com>
Signed-off-by: Lucia Fang <fanglu@meta.com>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Lucia Fang <116399278+luccafong@users.noreply.github.com>
Co-authored-by: Lucia Fang <fanglu@meta.com>
Co-authored-by: NickLucche <nlucches@redhat.com>
Co-authored-by: Siyuan Fu <siyuanf@nvidia.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Xiaozhu Meng <mxz297@gmail.com>
Co-authored-by: Barry Kang <43644113+Barry-Delaney@users.noreply.github.com>

fa7e254a

29 Sep, 2025 1 commit
- [torch.compile] serialize cudagraph_mode as its enum name instead of value (#25868) · 43227236
  Jiangyun Zhu authored Sep 29, 2025
```
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
```
  43227236
27 Sep, 2025 1 commit

[torch.compile]: Add VLLM_DEBUG_DUMP_PATH environment variable (#25651) · c0ec8183

Jiangyun Zhu authored Sep 28, 2025


Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Signed-off-by: Jiangyun Zhu <riverclouds.zhu@qq.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>

c0ec8183

26 Sep, 2025 1 commit

[V1] address post issues related to #20059 (part 1) (#23046) · f075693d

fhl2000 authored Sep 27, 2025


Signed-off-by: fhl2000 <63384265+fhl2000@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>

f075693d

25 Sep, 2025 1 commit
- [V0 deprecation] Clean up V0 fallback in compilation config (#25675) · 71b25b0d
  Isotr0py authored Sep 26, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  71b25b0d
23 Sep, 2025 1 commit
- [Perf] Change default CUDAGraphMode from PIECEWISE to FULL_AND_PIECEWISE (#25444) · 24fab45d
  Michael Goin authored Sep 23, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  24fab45d
22 Sep, 2025 1 commit

[torch.compile] Cleanup compilation tests and custom passes, add debug utils,... · d5e0fca2

Luka Govedič authored Sep 22, 2025


[torch.compile] Cleanup compilation tests and custom passes, add debug utils, fix DCE bug (#23091), fix test (#24376), and prep for custom op matching (#24604) (#24542)
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Signed-off-by: luka <lgovedic@redhat.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>

d5e0fca2

20 Sep, 2025 1 commit

[torch.compile] CUDAGraph Inductor partition integration (#24281) · 8945b001

Boyuan Feng authored Sep 19, 2025


Signed-off-by: Boyuan Feng <boyuan@meta.com>
Signed-off-by: Boyuan Feng <fby.1994@gmail.com>
Signed-off-by: boyuanfeng <boyuan@meta.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>

8945b001

18 Sep, 2025 1 commit
- [Bug] Fix torch Compilation Cache Hit Error (#25093) · d2a30a2d
  Wentao Ye authored Sep 18, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  d2a30a2d
11 Sep, 2025 1 commit
- Add the support for the qwen3 next model (a hybrid attention model). (#24526) · e93f4cc9
  Tao He authored Sep 11, 2025
```
Signed-off-by: Tao He <linzhu.ht@alibaba-inc.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
```
  e93f4cc9
09 Sep, 2025 1 commit
- [Compilation][WideEP] Enable Piecewise CUDAGraph for DeepEPHT (#24123) · a55cf41a
  Wentao Ye authored Sep 09, 2025
  
  a55cf41a
03 Sep, 2025 2 commits

[V1] v1 engine + full CUDA graph support for PLaMo2 (#23998) · fa4311d8

nopperl authored Sep 04, 2025


Signed-off-by: Hemmi Shinichi <shemmi@preferred.jp>
Signed-off-by: nopperl <54780682+nopperl@users.noreply.github.com>
Co-authored-by: Hemmi Shinichi <shemmi@preferred.jp>
Co-authored-by: Thomas Parnell <tom.parnell@gmail.com>

fa4311d8

fix some typos (#24071) · 1bd007f2
co63oc authored Sep 03, 2025
```
Signed-off-by: co63oc <co63oc@users.noreply.github.com>
```
1bd007f2

27 Aug, 2025 1 commit
- [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
26 Aug, 2025 1 commit
- Fix nits from #20059 (#23548) · b00e69f8
  Harry Mellor authored Aug 26, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  b00e69f8
21 Aug, 2025 2 commits
- [Model] Add LFM2 architecture (#22845) · 2e2000f3
  Paul Pak authored Aug 21, 2025
```
Signed-off-by: Paul Pak <paulpak58@gmail.com>
```
  2e2000f3
- [V1][Mamba1] - Full CUDA and Piecewise CUDA Graphs Support (#23035) · 3663870c
  Asaf Joseph Gardin authored Aug 21, 2025
```
Signed-off-by: asafg <asafg@ai21.com>
Signed-off-by: asafg <39553475+Josephasafg@users.noreply.github.com>
Co-authored-by: asafg <asafg@ai21.com>
```
  3663870c
15 Aug, 2025 1 commit

[Core] Allow full cudagraph with separate attention routines and orthogonal to... · 74f441f4

fhl2000 authored Aug 15, 2025


[Core] Allow full cudagraph with separate attention routines and orthogonal to compilation, add support for FA2 and FlashInfer (#20059)
Signed-off-by: fhl <2410591650@qq.com>
Signed-off-by: fhl2000 <63384265+fhl2000@users.noreply.github.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>

74f441f4

09 Aug, 2025 1 commit
- Move `ParallelConfig` from `config/__init__.py` to `config/parallel.py` (#22565) · 2d18256e
  Harry Mellor authored Aug 09, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  2d18256e