Commits · c8bde93367fb252eca1e9a6ae78650caa4a9a951 · OpenDAS / vllm_cscc

24 Sep, 2025 1 commit
- [BUG] Allows for RunAI Streamer and Torch.compile cache to be used together (#24922) · c8bde933
  ahao-anyscale authored Sep 23, 2025
```
Signed-off-by: ahao-anyscale <ahao@anyscale.com>
```
  c8bde933
23 Sep, 2025 4 commits

[Speculators][Speculative Decoding] Fix gpt-oss eagle3 accuracy issue (#25406) · d5944d51
jiahanc authored Sep 23, 2025
```
Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
```
d5944d51
[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

[Performance] Move apply_w8a8_block_fp8_linear to an op class (#24666) · 63400259

ElizaWszola authored Sep 23, 2025


Signed-off-by: ElizaWszola <ewszola@redhat.com>
Signed-off-by: ElizaWszola <elizaw.9289@gmail.com>
Signed-off-by: Luka Govedič <lgovedic@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: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Luka Govedič <lgovedic@redhat.com>

63400259

[Core/DBO][2/N] Dual-Batch Overlap add DeepEP High Throughput support and Prefill support (#24845) · cc1dc7ed

Lucas Wilkinson authored Sep 23, 2025


Signed-off-by: Sage Moore <sage@neuralmagic.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Sage Moore <sage@neuralmagic.com>
Co-authored-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>

cc1dc7ed

22 Sep, 2025 4 commits

[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

[DP] support torchrun external launcher with Data Parallelism (#24899) · 922979bf

Lucia Fang authored Sep 22, 2025


Signed-off-by: Lu Fang <fanglu@fb.com>
Signed-off-by: Zhuohan Li <zhuohan123@gmail.com>
Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>

922979bf

refactor: abstract graph mode support into platform interface (#25161) · b6f01bd9
Yizhou authored Sep 22, 2025
```
Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>
```
b6f01bd9
Enable Eagle3 speculative decoding for GPT-OSS model (#25246) · 21467f9a
Eldar Kurtić authored Sep 22, 2025
```
Signed-off-by: Eldar Kurtic <8884008+eldarkurtic@users.noreply.github.com>
```
21467f9a

21 Sep, 2025 3 commits
- Remove V0 attention backends (#25351) · bc6e542d
  Woosuk Kwon authored Sep 21, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  bc6e542d
- feat: Enable engine-level arguments with speculators models (#25250) · c438b295
  Rahul Tuli authored Sep 21, 2025
```
Signed-off-by: Rahul Tuli <rtuli@redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>
```
  c438b295
- [V0 Deprecation] Remove async_output_proc, preemption mode, delay factor (#25334) · 0ff8ebb2
  Woosuk Kwon authored Sep 21, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  0ff8ebb2
20 Sep, 2025 2 commits

[Optimization] Avoid repeated model architecture conversion for pooling models (#25261) · c60e6137
Cyrus Leung authored Sep 20, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
c60e6137

[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

19 Sep, 2025 4 commits
- Enable modelopt gemma3 nvfp4/fp8, make workflow more robust (#22771) · 431535b5
  Zhiyu authored Sep 19, 2025
```
Signed-off-by: Zhiyu Cheng <zhiyuc@nvidia.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
  431535b5
- [Frontend] Pass API server count to each process (#23717) · 6c117cff
  Cyrus Leung authored Sep 20, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  6c117cff
- Move `ModelConfig` from `config/__init__.py` to `config/model.py` (#25252) · aed16879
  Harry Mellor authored Sep 19, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  aed16879
- Move `PoolerConfig` from `config/__init__.py` to `config/pooler.py` (#25181) · 058525b9
  Harry Mellor authored Sep 19, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  058525b9
18 Sep, 2025 7 commits
- [Bug] Fix torch Compilation Cache Hit Error (#25093) · d2a30a2d
  Wentao Ye authored Sep 18, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  d2a30a2d
- [spec decode] Fix MTP inference path for MiMo-7B model (#25136) · c4cb0af9
  qizixi authored Sep 18, 2025
```
Signed-off-by: zixi-qi <qizixi@meta.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
  c4cb0af9
- Fix `validate-config` pre-commit check (#25157) · 3ed1ec4a
  Harry Mellor authored Sep 18, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  3ed1ec4a
- Move `StructuredOutputsConfig` from `config/__init__.py` to `config/structured_outputs.py` (#25153) · 8ed039d5
  Harry Mellor authored Sep 18, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  8ed039d5
- [Chore] Cleanup guided namespace, move to structured outputs config (#22772) · 29283e89
  Aaron Pham authored Sep 18, 2025
```
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  29283e89
- [Bugfix] when use s3 model cannot use default load_format (#24435) · 350c94de
  rongfu.leng authored Sep 18, 2025
```
Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>
Co-authored-by: 22quinn <33176974+22quinn@users.noreply.github.com>
```
  350c94de
- [Spec Decode] Efficient padded speculation (#24539) · b7433ca1
  Benjamin Chislett authored Sep 18, 2025
```
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
```
  b7433ca1
17 Sep, 2025 2 commits
- [BUG] Exclude .pth files when pulling remote files (#25092) · f20c3b09
  ahao-anyscale authored Sep 17, 2025
```
Signed-off-by: ahao-anyscale <ahao@anyscale.com>
```
  f20c3b09
- [UX] Remove "quantization is not fully optimized yet" log (#25012) · 67532a1a
  Michael Goin authored Sep 16, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  67532a1a
16 Sep, 2025 4 commits

[Core/DBO][1/N] Add Dual-Batch Overlap mechanism to VLLM (#23693) · 56793995

Sage Moore authored Sep 16, 2025


Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Sage Moore <sage@neuralmagic.com>
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Co-authored-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>

56793995

Move `SpeculativeConfig` from `config/__init__.py` to `config/speculative.py` (#24904) · 0faf3cc3
Harry Mellor authored Sep 16, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
0faf3cc3

[Feat][EPLB] A novel static EPLB placement strategy for MoE models. (#23745) · 7ea5c73a

Chen Bruce authored Sep 16, 2025


Signed-off-by: bruceszchen <bruceszchen@tencent.com>
Signed-off-by: Chen Bruce <bruceszchen@tencent.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: Chen Bruce <cszwwdz@vip.qq.com>
Co-authored-by: lemon412 <lemon412@foxmail.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

7ea5c73a

Remove V0 Encoder-Decoder Support (#24907) · 759ef49b
Woosuk Kwon authored Sep 15, 2025
```
Signed-off-by: Woosuk Kwon <woosuk@thinkingmachines.ai>
```
759ef49b

15 Sep, 2025 1 commit

Move `MultiModalConfig` from `config/__init__.py` to `config/multimodal.py` (#24659) · c4afdb69

Harry Mellor authored Sep 15, 2025


Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

c4afdb69

12 Sep, 2025 2 commits
- [Core] Shared memory based object store for Multimodal data caching and IPC (#20452) · a5b84f1c
  dongluw authored Sep 12, 2025
```
Signed-off-by: donglu <donglu@cohere.com>
```
  a5b84f1c
- [CI] Add ci_envs for convenient local testing (#24630) · d21a36f5
  wang.yuqi authored Sep 12, 2025
```
Signed-off-by: wang.yuqi <noooop@126.com>
```
  d21a36f5
11 Sep, 2025 6 commits
- [Doc] Clarify cudagraph capture size logic and default behavior in scheduler (#18698) · 7a30fa87
  Zazzle516 authored Sep 12, 2025
```
Signed-off-by: Zazzle516 <2405677060@qq.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  7a30fa87
- [HybridKVCache][Platform] Add support_hybrid_kv_cache for platform (#24646) · 4f6593b0
  Mengqing Cao authored Sep 11, 2025
```
Signed-off-by: MengqingCao <cmq0113@163.com>
```
  4f6593b0
- Allow users to specify kv cache memory size (#21489) · 94e6b2d5
  Boyuan Feng authored Sep 11, 2025
```
Signed-off-by: Boyuan Feng <boyuan@meta.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  94e6b2d5
- Move `LoRAConfig` from `config/__init__.py` to `config/lora.py` (#24644) · 5f5271f1
  Harry Mellor authored Sep 11, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  5f5271f1
- Fix typing for `safetensors_load_strategy` (#24641) · d6249d06
  Harry Mellor authored Sep 11, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  d6249d06
- [CI Failure] fix models/language/pooling/test_auto_prefix_cache_support.py (#24636) · 25bb9e8c
  wang.yuqi authored Sep 11, 2025
```
Signed-off-by: wang.yuqi <noooop@126.com>
```
  25bb9e8c