Commits · dc5ce861bf0e10fc002384859b93b1eebbd70933 · OpenDAS / vllm_cscc

03 Dec, 2024 2 commits
- [torch.compile] remove compilation_context and simplify code (#10838) · dc5ce861
  youkaichao authored Dec 02, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  dc5ce861
- [core][distributed] add pynccl broadcast (#10843) · 21fe7b48
  youkaichao authored Dec 02, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  21fe7b48
02 Dec, 2024 4 commits

[Misc][LoRA] Move the implementation of lora bias to punica.py (#10829) · b45f0d79
Jee Jee Li authored Dec 03, 2024
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
b45f0d79

[Model]: add some tests for aria model (#10770) · ef31eabc

zhou fan authored Dec 02, 2024


Signed-off-by: xffxff <1247714429@qq.com>
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <2037008807@qq.com>

ef31eabc

[Kernel] Use `out` arg in flash_attn_varlen_func (#10811) · 073a4bd1
Woosuk Kwon authored Dec 01, 2024
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
073a4bd1

[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
- [Model] Clean up MiniCPMV (#10751) · fa6ecb9a
  Cyrus Leung authored Nov 29, 2024
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  fa6ecb9a
28 Nov, 2024 3 commits
- [Model] Added GLM-4 series hf format model support vllm==0.6.4 (#10561) · 5fc5ce0f
  sixgod authored Nov 28, 2024
```
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
  5fc5ce0f
- [V1] Do not allocate beyond the max_model_len (#10730) · a79b1224
  Woosuk Kwon authored Nov 28, 2024
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  a79b1224
- [Bug][CLI] Allow users to disable prefix caching explicitly (#10724) · d9b4b3f0
  Ricky Xu authored Nov 27, 2024
```
Signed-off-by: rickyx <rickyx@anyscale.com>
```
  d9b4b3f0
27 Nov, 2024 6 commits
- [Frontend] don't block event loop in tokenization (preprocess) in OpenAI compatible server (#10635) · 395b1c74
  tomeras91 authored Nov 27, 2024
```
Signed-off-by: Tomer Asida <tomera@ai21.com>
```
  395b1c74
- [Bugfix][Mamba] Fix Multistep on Mamba-like models (#10705) · 197b4484
  Mor Zusman authored Nov 27, 2024
```
Signed-off-by: mzusman <mor.zusmann@gmail.com>
```
  197b4484
- [ci] fix slow tests (#10698) · 308cc5e2
  youkaichao authored Nov 27, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  308cc5e2
- [Model] Support telechat2 (#10311) · 1209261e
  shunxing12345 authored Nov 27, 2024
```
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: xiangw2 <xiangw2@chinatelecom.cn>
Co-authored-by: Isotr0py <2037008807@qq.com>
```
  1209261e
- [Bugfix][SpecDecode] apply sampling parameters to target probabilities for... · 1bf905dd
  jeongin601 authored Nov 27, 2024
```
[Bugfix][SpecDecode] apply sampling parameters to target probabilities for consistency in rejection sampling. (#10198)
Signed-off-by: jeongin601 <0200angela@gmail.com>
Signed-off-by: jeong_in.bae <jeong_in.bae@navercorp.com>
```
  1bf905dd
- 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 4 commits
- [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
- [ci] add vllm_test_utils (#10659) · 334d64d1
  youkaichao authored Nov 26, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  334d64d1
- custom allreduce + torch.compile (#10121) · 9a88f897
  Sage Moore authored Nov 26, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
```
  9a88f897
- [v1] EngineArgs for better config handling for v1 (#10382) · 519e8e41
  Ricky Xu authored Nov 25, 2024
```
Signed-off-by: rickyx <rickyx@anyscale.com>
```
  519e8e41
25 Nov, 2024 9 commits
- [Model] Add OLMo November 2024 model (#10503) · 9db713a1
  Shane A authored Nov 25, 2024
  
  9db713a1
- [Model]: Add support for Aria model (#10514) · b1d92053
  zhou fan authored Nov 26, 2024
```
Signed-off-by: xffxff <1247714429@qq.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
```
  b1d92053
- [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
- [Bug]: Authorization ignored when root_path is set (#10606) · d04b13a3
  Chauncey authored Nov 26, 2024
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
  d04b13a3
- [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
- [torch.compile] support encoder based models (#10613) · 571841b7
  youkaichao authored Nov 24, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  571841b7
- 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
24 Nov, 2024 1 commit

[Bugfix] Fix LoRA weight sharding (#10450) · 1700c543

Jee Jee Li authored Nov 24, 2024


Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>

1700c543

23 Nov, 2024 6 commits
- [2/N] handling placeholders in merged multi-modal processor (#10485) · c8acd805
  Cyrus Leung authored Nov 23, 2024
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  c8acd805
- Prefix Cache Aware Scheduling [1/n] (#10128) · 4634a89d
  Ricky Xu authored Nov 22, 2024
```
Signed-off-by: rickyx <rickyx@anyscale.com>
```
  4634a89d
- [Bugfix] Internal Server Error when tool_choice is incorrect. (#10567) · 7d8ffb34
  Varun Vinayak Shenoy authored Nov 22, 2024
```
Signed-off-by: Varun Shenoy <varun.vinayak.shenoy@oracle.com>
```
  7d8ffb34
- [core] gemma2 full context length support (#10584) · 4aba6e3d
  youkaichao authored Nov 22, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  4aba6e3d
- [Misc] Add pynccl wrappers for all_gather and reduce_scatter (#9432) · 978b3974
  Tyler Michael Smith authored Nov 22, 2024
  
  978b3974
- [Bugfix][Frontend] Update Llama Chat Templates to also support Non-Tool use (#10164) · 9195dbdb
  Travis Johnson authored Nov 22, 2024
```
Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com>
```
  9195dbdb
22 Nov, 2024 2 commits
- [v1] Refactor KVCacheManager for more hash input than token ids (#10507) · 97814fbf
  Ricky Xu authored Nov 22, 2024
```
Signed-off-by: rickyx <rickyx@anyscale.com>
Signed-off-by: Cody Yu <hao.yu.cody@gmail.com>
Co-authored-by: Cody Yu <hao.yu.cody@gmail.com>
```
  97814fbf
- [torch.compile] support all attention backends (#10558) · eebad39f
  youkaichao authored Nov 22, 2024
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  eebad39f