Commits · d263bd9df7b2f5586910e5d006a11ff11ba7c310 · OpenDAS / vllm_cscc

15 Dec, 2024 1 commit
- [Core] Support disaggregated prefill with Mooncake Transfer Engine (#10884) · d263bd9d
  shangmingc authored Dec 16, 2024
```
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
```
  d263bd9d
14 Dec, 2024 1 commit
- [Frontend] Add `logits_processors` as an extra completion argument (#11150) · 9c3dadd1
  Brad Hilton authored Dec 14, 2024
```
Signed-off-by: Brad Hilton <brad.hilton.nw@gmail.com>
```
  9c3dadd1
13 Dec, 2024 1 commit
- [core] clean up cudagraph batchsize padding logic (#10996) · be39e3cd
  youkaichao authored Dec 12, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  be39e3cd
12 Dec, 2024 1 commit

[V1] VLM preprocessor hashing (#11020) · 4e116833

Alexander Matveev authored Dec 11, 2024


Signed-off-by: Roger Wang <ywang@roblox.com>
Signed-off-by: Alexander Matveev <alexm@neuralmagic.com>
Co-authored-by: Michael Goin <michael@neuralmagic.com>
Co-authored-by: Roger Wang <ywang@roblox.com>

4e116833

11 Dec, 2024 5 commits
- [torch.compile] use depyf to dump torch.compile internals (#10972) · 91642db9
  youkaichao authored Dec 11, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  91642db9
- [Doc] Update docs to refer to pooling models (#11093) · cad5c0a6
  Cyrus Leung authored Dec 11, 2024
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  cad5c0a6
- [Misc] Split up pooling tasks (#10820) · 8f10d5e3
  Cyrus Leung authored Dec 11, 2024
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  8f10d5e3
- [Model] PP support for Mamba-like models (#10992) · ffa48c91
  Mor Zusman authored Dec 11, 2024
```
Signed-off-by: mzusman <mor.zusmann@gmail.com>
```
  ffa48c91
- [Misc] LoRA + Chunked Prefill (#9057) · d5c5154f
  Aurick Qiao authored Dec 10, 2024
  
  d5c5154f
09 Dec, 2024 3 commits
- [v1] fix use compile sizes (#11000) · 1a2f8fb8
  youkaichao authored Dec 09, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  1a2f8fb8
- [Platform] Move `async output` check to platform (#10768) · aea2fc38
  wangxiyuan authored Dec 10, 2024
```
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
```
  aea2fc38
- [misc] clean up and unify logging (#10999) · 46004e83
  youkaichao authored Dec 08, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  46004e83
08 Dec, 2024 2 commits
- [torch.compile][misc] fix comments (#10993) · 43b05fa3
  youkaichao authored Dec 08, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  43b05fa3
- [torch.compile] allow candidate compile sizes (#10984) · fd57d2b5
  youkaichao authored Dec 08, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  fd57d2b5
07 Dec, 2024 2 commits
- [core][executor] simplify instance id (#10976) · 1b62745b
  youkaichao authored Dec 07, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  1b62745b
- [Model] Composite weight loading for multimodal Qwen2 (#10944) · bf0e382e
  Cyrus Leung authored Dec 07, 2024
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  bf0e382e
06 Dec, 2024 2 commits
- [misc] fix typo (#10960) · c05cfb67
  youkaichao authored Dec 06, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  c05cfb67
- [torch.compile] add logging for compilation time (#10941) · b031a455
  youkaichao authored Dec 06, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  b031a455
05 Dec, 2024 1 commit
- [Doc] Create a new "Usage" section (#10827) · aa39a8e1
  Cyrus Leung authored Dec 05, 2024
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  aa39a8e1
04 Dec, 2024 1 commit
- Drop ROCm load format check (#10767) · b5b647b0
  wangxiyuan authored Dec 04, 2024
```
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
```
  b5b647b0
03 Dec, 2024 2 commits
- [Core][Performance] Add XGrammar support for guided decoding and set it as default (#10785) · 9323a315
  Aaron Pham authored Dec 03, 2024
```
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
Signed-off-by: mgoin <michael@neuralmagic.com>
Co-authored-by: mgoin <michael@neuralmagic.com>
```
  9323a315
- [torch.compile] remove compilation_context and simplify code (#10838) · dc5ce861
  youkaichao authored Dec 02, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  dc5ce861
02 Dec, 2024 3 commits

[misc] use out argument for flash attention (#10822) · a4c4daf3
youkaichao authored Dec 02, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
a4c4daf3
[doc]Update config docstring (#10732) · 995a1485
wangxiyuan authored Dec 02, 2024
```
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
```
995a1485

[Core] Implement disagg prefill by StatelessProcessGroup (#10502) · 0590ec3f

Kuntai Du authored Dec 01, 2024



This PR provides initial support for single-node disaggregated prefill in 1P1D scenario.
Signed-off-by: KuntaiDu <kuntai@uchicago.edu>
Co-authored-by: ApostaC <yihua98@uchicago.edu>
Co-authored-by: YaoJiayi <120040070@link.cuhk.edu.cn>

0590ec3f

01 Dec, 2024 2 commits
- [Misc] Rename embedding classes to pooling (#10801) · d2f058e7
  Cyrus Leung authored Dec 01, 2024
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  d2f058e7
- [Model] Replace embedding models with pooling adapter (#10769) · 13370712
  Cyrus Leung authored Dec 01, 2024
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  13370712
29 Nov, 2024 1 commit
- [platform] Add verify_quantization in platform. (#10757) · 661175bc
  wangxiyuan authored Nov 29, 2024
```
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
```
  661175bc
27 Nov, 2024 2 commits
- [torch.compile] fix shape specialization (#10722) · c411def2
  youkaichao authored Nov 27, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  c411def2
- Remove hard-dependencies of Speculative decode to CUDA workers (#10587) · 0a71900b
  Chendi.Xue authored Nov 26, 2024
```
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
```
  0a71900b
26 Nov, 2024 1 commit

[Bugfix] Fix for Spec model TP + Chunked Prefill (#10232) · db66e018

Murali Andoorveedu authored Nov 26, 2024


Signed-off-by: andoorve <37849411+andoorve@users.noreply.github.com>
Signed-off-by: Sourashis Roy <sroy@roblox.com>
Co-authored-by: Sourashis Roy <sroy@roblox.com>

db66e018

25 Nov, 2024 6 commits
- [Bugfix] Fix chunked prefill with model dtype float32 on Turing Devices (#9850) · c27df94e
  Wallas Henrique authored Nov 25, 2024
```
Signed-off-by: Wallas Santos <wallashss@ibm.com>
Co-authored-by: Michael Goin <michael@neuralmagic.com>
```
  c27df94e
- [Model] Support `is_causal` HF config field for Qwen2 model (#10621) · ed46f143
  Cyrus Leung authored Nov 25, 2024
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  ed46f143
- [misc] move functions to config.py (#10624) · 05d1f8c9
  youkaichao authored Nov 25, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  05d1f8c9
- [misc] add torch.compile compatibility check (#10618) · 25d806e9
  youkaichao authored Nov 24, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  25d806e9
- [Refactor][MISC] del redundant code in ParallelConfig.postinit (#10614) · 7ea3cd7c
  Mengqing Cao authored Nov 25, 2024
```
Signed-off-by: MengqingCao <cmq0113@163.com>
```
  7ea3cd7c
- Support Cross encoder models (#10400) · 214efc2c
  Maximilien de Bayser authored Nov 24, 2024
```
Signed-off-by: Max de Bayser <maxdebayser@gmail.com>
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Signed-off-by: Flavia Beo <flavia.beo@ibm.com>
Co-authored-by: Flavia Beo <flavia.beo@ibm.com>
```
  214efc2c
23 Nov, 2024 3 commits
- [AMD] Add support for GGUF quantization on ROCm (#10254) · 7c25fe45
  kliuae authored Nov 23, 2024
  
  7c25fe45
- Update default max_num_batch_tokens for chunked prefill to 2048 (#10544) · 02a43f82
  Michael Goin authored Nov 23, 2024
  
  02a43f82
- [core] gemma2 full context length support (#10584) · 4aba6e3d
  youkaichao authored Nov 22, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  4aba6e3d