Commits · 0640f227c9a5fb1e7193792eb36ff48d152af099 · OpenDAS / vllm_cscc · GitLab

04 Sep, 2024 1 commit
- [Frontend] Multimodal support in offline chat (#8098) · 855c262a
  Cyrus Leung authored Sep 04, 2024
  
  855c262a
02 Sep, 2024 2 commits
- [Core][Bugfix] Accept GGUF model without .gguf extension (#8056) · 4ca65a97
  Isotr0py authored Sep 02, 2024
  
  4ca65a97
- [Model] Add Granite model (#7436) · f8d60145
  Shawn Tan authored Sep 01, 2024
```
Co-authored-by: Nick Hill <nickhill@us.ibm.com>
```
  f8d60145
31 Aug, 2024 1 commit
- [Bugfix] Fix ModelScope models in v0.5.5 (#8037) · 4f5d8446
  Nicolò Lucchesi authored Aug 31, 2024
  
  4f5d8446
30 Aug, 2024 1 commit
- [MODEL] add Exaone model support (#7819) · dc13e993
  Yohan Na authored Aug 30, 2024
  
  dc13e993
27 Aug, 2024 1 commit
- [Model] Add Mistral Tokenization to improve robustness and chat encoding (#7739) · 6fc4e6e0
  Patrick von Platen authored Aug 27, 2024
  
  6fc4e6e0
22 Aug, 2024 2 commits
- [Speculative Decoding] EAGLE Implementation with Top-1 proposer (#6830) · a3fce56b
  Abhinav Goyal authored Aug 22, 2024
  
  a3fce56b
- [Model] Fix Phi-3.5-vision-instruct 'num_crops' issue (#7710) · df1a2113
  zifeitong authored Aug 21, 2024
  
  df1a2113
21 Aug, 2024 1 commit
- [Model] Add UltravoxModel and UltravoxConfig (#7615) · 1ca0d4f8
  Peter Salas authored Aug 21, 2024
  
  1ca0d4f8
16 Aug, 2024 1 commit
- [Model] Align nemotron config with final HF state and fix lm-eval-small (#7611) · 44f26a94
  Michael Goin authored Aug 16, 2024
  
  44f26a94
13 Aug, 2024 1 commit
- [mypy] Misc. typing improvements (#7417) · 9ba85bc1
  Cyrus Leung authored Aug 13, 2024
  
  9ba85bc1
07 Aug, 2024 1 commit
- [Frontend] Gracefully handle missing chat template and fix CI failure (#7238) · 66d617e3
  Cyrus Leung authored Aug 07, 2024
```
Co-authored-by: Roger Wang <ywang@roblox.com>
```
  66d617e3
05 Aug, 2024 1 commit
- [Core] Support loading GGUF model (#5191) · 360bd67c
  Isotr0py authored Aug 06, 2024
```
Co-authored-by: Michael Goin <michael@neuralmagic.com>
```
  360bd67c
03 Aug, 2024 1 commit

[ Frontend ] Multiprocessing for OpenAI Server with `zeromq` (#6883) · ed812a73

Robert Shaw authored Aug 02, 2024


Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
Co-authored-by: Joe Runde <Joseph.Runde@ibm.com>
Co-authored-by: Joe Runde <joe@joerun.de>
Co-authored-by: Nick Hill <nickhill@us.ibm.com>
Co-authored-by: Simon Mo <simon.mo@hey.com>

ed812a73

02 Aug, 2024 2 commits
- [ci][distributed] try to fix pp test (#7054) · 25235779
  youkaichao authored Aug 01, 2024
  
  25235779
- [Performance] Optimize `get_seqs` (#7051) · 6ce01f30
  Woosuk Kwon authored Aug 01, 2024
  
  6ce01f30
31 Jul, 2024 1 commit
- [mypy] Enable following imports for some directories (#6681) · da1f7cc1
  Cyrus Leung authored Jul 31, 2024
  
  da1f7cc1
29 Jul, 2024 1 commit
- [Model] Initialize support for InternVL2 series models (#6514) · 7cbd9ec7
  Isotr0py authored Jul 29, 2024
```
Co-authored-by: Roger Wang <ywang@roblox.com>
```
  7cbd9ec7
26 Jul, 2024 1 commit
- [Model] Support Nemotron models (Nemotron-3, Nemotron-4, Minitron) (#6611) · 07278c37
  Michael Goin authored Jul 26, 2024
  
  07278c37
23 Jul, 2024 2 commits
- Bump `transformers` version for Llama 3.1 hotfix and patch Chameleon (#6690) · 1bedf210
  Roger Wang authored Jul 23, 2024
  
  1bedf210
- [VLM][Model] Support image input for Chameleon (#6633) · 22fa2e35
  Roger Wang authored Jul 22, 2024
  
  22fa2e35
22 Jul, 2024 2 commits
- [Core] Support dynamically loading Lora adapter from HuggingFace (#6234) · 42c7f66a
  Jiaxin Shan authored Jul 22, 2024
```
Co-authored-by: Antoni Baum <antoni.baum@protonmail.com>
```
  42c7f66a
- [Model] Initial Support for Chameleon (#5770) · c9eef37f
  Roger Wang authored Jul 21, 2024
  
  c9eef37f
20 Jul, 2024 1 commit
- [Core] Allow specifying custom Executor (#6557) · 7bd82002
  Antoni Baum authored Jul 19, 2024
  
  7bd82002
18 Jul, 2024 1 commit
- [BugFix][Frontend] Use LoRA tokenizer in OpenAI APIs (#6227) · e2fbaee7
  Nick Hill authored Jul 18, 2024
```
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
```
  e2fbaee7
11 Jul, 2024 1 commit
- [ BugFix ] Prompt Logprobs Detokenization (#6223) · 7ed6a4f0
  Robert Shaw authored Jul 11, 2024
```
Co-authored-by: Zifei Tong <zifeitong@gmail.com>
```
  7ed6a4f0
10 Jul, 2024 1 commit
- [Speculative Decoding] Medusa Implementation with Top-1 proposer (#4978) · 2416b26e
  Abhinav Goyal authored Jul 10, 2024
  
  2416b26e
03 Jul, 2024 1 commit

[Core] Dynamic image size support for VLMs (#5276) · 9831aec4

Cyrus Leung authored Jul 03, 2024


Signed-off-by: Xiaowei Jiang <xwjiang2010@gmail.com>
Co-authored-by: Xiaowei Jiang <xwjiang2010@gmail.com>
Co-authored-by: ywang96 <ywang@roblox.com>
Co-authored-by: xwjiang2010 <87673679+xwjiang2010@users.noreply.github.com>
Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com>

9831aec4

02 Jul, 2024 1 commit

[VLM] Remove `image_input_type` from VLM config (#5852) · 98d6682c

xwjiang2010 authored Jul 02, 2024


Signed-off-by: Xiaowei Jiang <xwjiang2010@gmail.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Roger Wang <ywang@roblox.com>

98d6682c

01 Jul, 2024 2 commits
- [Model] Changes to MLPSpeculator to support tie_weights and input_scale (#5965) · 54600709
  Thomas Parnell authored Jul 02, 2024
```
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Co-authored-by: Joshua Rosenkranz <jmrosenk@us.ibm.com>
```
  54600709
- [Bugfix] Use RayActorError for older versions of Ray in RayTokenizerGroupPool (#6039) · dec6fc6f
  Antoni Baum authored Jul 01, 2024
  
  dec6fc6f
29 Jun, 2024 1 commit
- [Bugfix] Support `eos_token_id` from `config.json` (#5954) · 51e971d3
  Cyrus Leung authored Jun 29, 2024
  
  51e971d3
28 Jun, 2024 1 commit
- [Core] Registry for processing model inputs (#5214) · 5cbe8d15
  Cyrus Leung authored Jun 28, 2024
```
Co-authored-by: ywang96 <ywang@roblox.com>
```
  5cbe8d15
27 Jun, 2024 1 commit
- [BugFix] Fix `MLPSpeculator` handling of `num_speculative_tokens` (#5876) · 691e29ec
  Nick Hill authored Jun 27, 2024
  
  691e29ec
25 Jun, 2024 1 commit
- [Core] Add fault tolerance for `RayTokenizerGroupPool` (#5748) · 67882dbb
  Antoni Baum authored Jun 25, 2024
  
  67882dbb
21 Jun, 2024 1 commit

[Model] MLPSpeculator speculative decoding support (#4947) · b12518d3

Joshua Rosenkranz authored Jun 20, 2024


Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Co-authored-by: Thomas Parnell <tpa@zurich.ibm.com>
Co-authored-by: Nick Hill <nickhill@us.ibm.com>
Co-authored-by: Davis Wertheimer <Davis.Wertheimer@ibm.com>

b12518d3

15 Jun, 2024 1 commit
- [mypy] Enable type checking for test directory (#5017) · 0e9164b4
  Cyrus Leung authored Jun 15, 2024
  
  0e9164b4
11 Jun, 2024 2 commits
- [Frontend] Customizable RoPE theta (#5197) · dcbf4286
  sasha0552 authored Jun 11, 2024
  
  dcbf4286
- [Misc] Various simplifications and typing fixes (#5368) · a0086298
  Nick Hill authored Jun 10, 2024
  
  a0086298
06 Jun, 2024 1 commit
- Bugfix: fix broken of download models from modelscope (#5233) · 4efff036
  liuyhwangyh authored Jun 07, 2024
```
Co-authored-by: mulin.lyh <mulin.lyh@taobao.com>
```
  4efff036