Commits · 432ec9926ebd3ce826f0d49df0a2a5ae3cc81ec0 · OpenDAS / vllm_cscc

31 May, 2025 1 commit
- create util function for batched arange (#18937) · 7782464a
  Yu Guo authored May 30, 2025
  
  7782464a
29 May, 2025 1 commit
- [V1] Allocate kv_cache with stride order for V1 (#18775) · 32ce3cf7
  Nicolò Lucchesi authored May 29, 2025
```
Signed-off-by: nicklucche <nlucches@redhat.com>
```
  32ce3cf7
28 May, 2025 2 commits
- [Core] Enable CUDA graphs for DP + All2All kernels (#18724) · 7951d787
  Varun Sundar Rabindranath authored May 28, 2025
```
Signed-off-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
```
  7951d787
- [Chore][Spec Decode] Update check NoneType instead of assigning variables (#18836) · a09c7ca9
  Aaron Pham authored May 28, 2025
```
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
```
  a09c7ca9
27 May, 2025 1 commit
- [Core] Automatically cast multi-modal input dtype (#18756) · 696259ca
  Cyrus Leung authored May 27, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  696259ca
24 May, 2025 2 commits
- [V1][Spec Decode] Support multi-layer eagle draft model (#18030) · c1e4a405
  qizixi authored May 24, 2025
```
Signed-off-by: qizixi <qizixi@meta.com>
```
  c1e4a405
- [V1][Spec Decode] Small refactors to improve eagle bookkeeping performance (#18424) · d55e446d
  qizixi authored May 23, 2025
```
Signed-off-by: qizixi <qizixi@meta.com>
```
  d55e446d
23 May, 2025 3 commits

[V1] Support Deepseek MTP (#18435) · 2628a69e

Jiayi Yao authored May 23, 2025


Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
Signed-off-by: YaoJiayi <120040070@link.cuhk.edu.cn>
Co-authored-by: Rui Qiao <ruisearch42@gmail.com>

2628a69e

[v1] Redo "Support multiple KV cache groups in GPU model runner (#17945)" (#18593) · 6550114c
Chen Zhang authored May 24, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
6550114c

[Frontend] [Core] Add Tensorizer support for V1, LoRA adapter serialization... · c32e249a

Sanger Steel authored May 22, 2025


[Frontend] [Core] Add Tensorizer support for V1, LoRA adapter serialization and deserialization (#17926)
Signed-off-by: Sanger Steel <sangersteel@gmail.com>

c32e249a

22 May, 2025 1 commit
- [Bugfix] Use random hidden states in dummy sampler run (#18543) · 4e04eceb
  Bowen Wang authored May 22, 2025
```
Signed-off-by: Bowen Wang <abmfy@icloud.com>
```
  4e04eceb
21 May, 2025 1 commit
- Revert "[v1] Support multiple KV cache groups in GPU model runner (#17945) (#18459) · bb0a3112
  Mark McLoughlin authored May 21, 2025
```
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
```
  bb0a3112
17 May, 2025 1 commit
- Support sequence parallelism combined with pipeline parallelism (#18243) · 9ab2c02f
  cascade authored May 17, 2025
```
Signed-off-by: cascade812 <cascade812@outlook.com>
```
  9ab2c02f
16 May, 2025 2 commits
- [Feature] Support Pipeline Parallism in torchrun SPMD offline inference for V1 (#17827) · 3d2779c2
  Lucia Fang authored May 15, 2025
```
Signed-off-by: Lucia Fang <fanglu@fb.com>
```
  3d2779c2
- [Model] vLLM v1 supports Medusa (#17956) · f4937a51
  Sky Lee authored May 16, 2025
```
Signed-off-by: lisiqi23 <lisiqi23@xiaomi.com>
Signed-off-by: skylee-01 <497627264@qq.com>
Co-authored-by: lisiqi23 <lisiqi23@xiaomi.com>
```
  f4937a51
15 May, 2025 1 commit
- [v1] Support multiple KV cache groups in GPU model runner (#17945) · e60f550b
  Chen Zhang authored May 15, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  e60f550b
14 May, 2025 2 commits
- [core][distributed] add ep group and all2all interface (#18077) · 6266c57b
  youkaichao authored May 14, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  6266c57b
- [Misc] Remove unused numpy tensor (#18084) · 6e27c6d8
  Roger Wang authored May 13, 2025
```
Signed-off-by: Roger Wang <hey@rogerw.me>
```
  6e27c6d8
13 May, 2025 1 commit
- [Bugfix][V1] Only get input embeddings w/ multi-modal models if first PP (#17916) · 8dd0671b
  Jin Huang authored May 13, 2025
```
Signed-off-by: Jin Huang <jinhun@amazon.com>
Co-authored-by: Jin Huang <jinhun@amazon.com>
```
  8dd0671b
12 May, 2025 1 commit

[P/D] NIXL Integration (#17751) · d1911020

Robert Shaw authored May 12, 2025


Signed-off-by: ApostaC <yihua98@uchicago.edu>
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Signed-off-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
Signed-off-by: Robert Shaw <rshaw@neuralmagic.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: Brent Salisbury <bsalisbu@redhat.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: ApostaC <yihua98@uchicago.edu>
Co-authored-by: Robert Shaw <rshaw@neuralmagic.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Tyler Michael Smith <tysmith@redhat.com>
Co-authored-by: Brent Salisbury <bsalisbu@redhat.com>

d1911020

10 May, 2025 1 commit
- [v1] Pass BlockTable and KVCacheSpec to AttentionMetadataBuilders (#17483) · 950751a9
  Chen Zhang authored May 11, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  950751a9
08 May, 2025 1 commit

[Core] Support full cuda graph in v1 (#16072) · 7ea2adb8

Chanh Nguyen authored May 07, 2025


Signed-off-by: Chanh Nguyen <cnguyen@linkedin.com>
Co-authored-by: Chanh Nguyen <cnguyen@linkedin.com>

7ea2adb8

06 May, 2025 2 commits
- [v1] AttentionMetadata for each layer (#17394) · cba31c47
  Chen Zhang authored May 06, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  cba31c47
- [V1][PP] Support PP for MultiprocExecutor (#14219) · a6fed020
  Li, Jiang authored May 06, 2025
```
Signed-off-by: jiang1.li <jiang1.li@intel.com>
Signed-off-by: jiang.li <jiang1.li@intel.com>
```
  a6fed020
30 Apr, 2025 1 commit
- [V1][Feature] Enable Speculative Decoding with Structured Outputs (#14702) · 34120f5a
  Benjamin Chislett authored Apr 29, 2025
```
Signed-off-by: Benjamin Chislett <benjamin.chislett@centml.ai>
Signed-off-by: Benjamin Chislett <chislett.ben@gmail.com>
```
  34120f5a
29 Apr, 2025 2 commits
- [V1][Spec Decode] Apply torch.compile & cudagraph to EAGLE (#17211) · 70788bdb
  Bryan Lu authored Apr 29, 2025
```
Signed-off-by: Bryan Lu <yuzhelu@amazon.com>
```
  70788bdb
- [V1] Remove num_input_tokens from attn_metadata (#17193) · 24e6ad3f
  Chen Zhang authored Apr 30, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  24e6ad3f
27 Apr, 2025 2 commits

[Feature] support sequence parallelism using compilation pass (#16155) · 690fe019

cascade authored Apr 27, 2025


Signed-off-by: cascade812 <cascade812@outlook.com>
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>

690fe019

[Bugfix] Get a specific type of layer from forward context (#17222) · 838cedad
Chen Zhang authored Apr 27, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
838cedad

26 Apr, 2025 2 commits
- [Core] Remove prompt string from engine core data structures (#17214) · df6f3ce8
  Nick Hill authored Apr 25, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  df6f3ce8
- [Minor][Spec Decode] Add use_eagle to SpeculativeConfig (#17213) · 1cf0719e
  Woosuk Kwon authored Apr 25, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  1cf0719e
25 Apr, 2025 1 commit

[V1][Spec Decode] EAGLE-3 Support (#16937) · a0e619e6

Benjamin Chislett authored Apr 25, 2025


Signed-off-by: Bryan Lu <yuzhelu@amazon.com>
Signed-off-by: Benjamin Chislett <benjamin.chislett@centml.ai>
Co-authored-by: Bryan Lu <yuzhelu@amazon.com>

a0e619e6

24 Apr, 2025 1 commit
- [Chore] Remove Sampler from Model Code (#17084) · b411418f
  Woosuk Kwon authored Apr 24, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  b411418f
23 Apr, 2025 2 commits
- [V1][Spec Decode] Always use argmax for sampling draft tokens (#16899) · 41fb013d
  Woosuk Kwon authored Apr 23, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  41fb013d
- [BugFix][V1] Fix int32 token index overflow when preparing input ids (#16806) · 32d4b669
  Yong Hoon Shin authored Apr 23, 2025
  
  32d4b669
22 Apr, 2025 2 commits
- [Perf] Optimize `_update_states` for GPU model runner (#16910) · a114bf20
  SnowCharm authored Apr 22, 2025
```
Signed-off-by: snowcharm <snowcharmqq@gmail.com>
```
  a114bf20
- [V1] V1 FlashInfer Attention (#16684) · 986537f1
  Michael Goin authored Apr 21, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Aurick Qiao <qiao@aurick.net>
```
  986537f1
21 Apr, 2025 1 commit
- [V1][Spec Decode] Handle draft tokens beyond max_model_len (#16087) · 3a0fba5c
  Woosuk Kwon authored Apr 21, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  3a0fba5c
19 Apr, 2025 1 commit

[Model][VLM] Add Qwen2.5-Omni model support (thinker only) (#15130) · 2c1bd848

Yang Fan authored Apr 19, 2025


Signed-off-by: fyabc <suyang.fy@alibaba-inc.com>
Signed-off-by: Roger Wang <ywang@roblox.com>
Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com>
Co-authored-by: Roger Wang <ywang@roblox.com>
Co-authored-by: Xiong Wang <wangxiongts@163.com>

2c1bd848

17 Apr, 2025 1 commit

[P/D][V1] KV Connector API V1 (#15960) · 3408e471

Yihua Cheng authored Apr 17, 2025


Signed-off-by: ApostaC <yihua98@uchicago.edu>
Signed-off-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
Signed-off-by: remi <remi@mistral.ai>
Co-authored-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Rémi Delacourt <54138269+Flechman@users.noreply.github.com>
Co-authored-by: Tyler Michael Smith <tysmith@redhat.com>

3408e471