Commits · 686f5e321096f3a843a23a89fa4a3f28e586c26f · kecinstone / 2024pra-vllm

16 Nov, 2023 1 commit
- Return usage for openai streaming requests (#1663) · 686f5e32
  Iskren Ivov Chernev authored Nov 17, 2023
  
  686f5e32
01 Nov, 2023 1 commit
- Add `/health` Endpoint for both Servers (#1540) · 7e90a2d1
  Fluder-Paradyne authored Nov 01, 2023
  
  7e90a2d1
30 Oct, 2023 1 commit
- Add support for `spaces_between_special_tokens` · 7013a801
  Dan Lord authored Oct 30, 2023
  
  7013a801
07 Oct, 2023 1 commit
- API server support ipv4 / ipv6 dualstack (#1288) · 09ff7f10
  Yunfeng Bai authored Oct 07, 2023
```
Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>
```
  09ff7f10
03 Oct, 2023 1 commit
- Use monotonic time where appropriate (#1249) · acbed3ef
  Antoni Baum authored Oct 02, 2023
  
  acbed3ef
28 Sep, 2023 2 commits
- Provide default max model length (#1224) · f936657e
  Woosuk Kwon authored Sep 28, 2023
  
  f936657e
- Add `skip_special_tokens` sampling params (#1186) · 20f7cc4c
  Dan Lord authored Sep 27, 2023
  
  20f7cc4c
24 Sep, 2023 1 commit
- Align `max_tokens` behavior with openai (#852) · bbbf8656
  Wen Sun authored Sep 24, 2023
  
  bbbf8656
21 Sep, 2023 2 commits
- feat: support stop_token_ids parameter. (#1097) · f98b745a
  Ricardo Lu authored Sep 22, 2023
  
  f98b745a
- clean api code, remove redundant background task. (#1102) · 2d1e86f1
  Roy authored Sep 22, 2023
  
  2d1e86f1
15 Sep, 2023 1 commit
- Only fail if logit_bias has actual values (#1045) · b5f93d06
  Lukas Kreussel authored Sep 15, 2023
  
  b5f93d06
08 Sep, 2023 1 commit
- Start background task in `AsyncLLMEngine.generate` (#988) · 08043847
  Antoni Baum authored Sep 08, 2023
```
Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>
```
  08043847
07 Sep, 2023 1 commit

Make `AsyncLLMEngine` more robust & fix batched abort (#969) · c07ece5c

Antoni Baum authored Sep 07, 2023


Signed-off-by: Antoni Baum <antoni.baum@protonmail.com>
Co-authored-by: Avnish Narayan <38871737+avnishn@users.noreply.github.com>

c07ece5c

05 Sep, 2023 1 commit
- Initialize AsyncLLMEngine bg loop correctly (#943) · 16967258
  Antoni Baum authored Sep 04, 2023
  
  16967258
30 Aug, 2023 1 commit
- Enable request body OpenAPI spec for OpenAI endpoints (#865) · becd7a56
  lplcor authored Aug 29, 2023
  
  becd7a56
11 Aug, 2023 1 commit
- Supports tokens and arrays of tokens as inputs to the OpenAI completion API (#715) · e06f504a
  WanMok authored Aug 11, 2023
  
  e06f504a
09 Aug, 2023 1 commit
- Check the max prompt length for the OpenAI completions API (#472) · 66c54aa9
  Nicolas Basile authored Aug 08, 2023
  
  66c54aa9
02 Aug, 2023 1 commit
- [BUG FIX] upgrade fschat version to 0.2.23 (#650) · e8ddc08e
  YHPeter authored Aug 02, 2023
```
Co-authored-by: hao.yu <hao.yu@cn-c017.server.mila.quebec>
```
  e8ddc08e
26 Jul, 2023 2 commits
- [Fix] Add model sequence length into model config (#575) · 58a072be
  Zhuohan Li authored Jul 25, 2023
  
  58a072be
- [Fix] Add chat completion Example and simplify dependencies (#576) · 82ad323d
  Zhuohan Li authored Jul 25, 2023
  
  82ad323d
20 Jul, 2023 1 commit
- fix: enable trust-remote-code in api server & benchmark. (#509) · 8c4b2592
  Ricardo Lu authored Jul 20, 2023
  
  8c4b2592
07 Jul, 2023 1 commit
- fix: only response [DONE] once when streaming response. (#378) · b396cb49
  Ricardo Lu authored Jul 07, 2023
  
  b396cb49
05 Jul, 2023 1 commit
- [Server] use fastchat.model.model_adapter.get_conversation_template method to... · 3d64cf01
  akxxsb authored Jul 05, 2023
```
[Server] use fastchat.model.model_adapter.get_conversation_template method to get model template (#357)
```
  3d64cf01
04 Jul, 2023 1 commit
- [Server] Add option to specify chat template for chat endpoint (#345) · 98fe8cb5
  Zhuohan Li authored Jul 03, 2023
  
  98fe8cb5
03 Jul, 2023 5 commits
- [Quality] Add CI for formatting (#343) · 42e0c1df
  Zhuohan Li authored Jul 03, 2023
  
  42e0c1df
- [Quality] Add code formatter and linter (#326) · d6fa1be3
  Zhuohan Li authored Jul 03, 2023
  
  d6fa1be3
- [Fix] Better error message for batched prompts (#342) · 0ffded81
  Zhuohan Li authored Jul 03, 2023
  
  0ffded81
- Allow send list of str for the Prompt on openai demo endpoint /v1/completions (#323) · 0bd2a573
  Michele Catalano authored Jul 03, 2023
```
* allow str or List[str] for prompt

* Update vllm/entrypoints/openai/api_server.py
Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>

---------
Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>
```
  0bd2a573
- feat: add ChatCompletion endpoint in OpenAI demo server. (#330) · 49b26e2c
  Ricardo Lu authored Jul 03, 2023
  
  49b26e2c
28 Jun, 2023 2 commits
- [Tokenizer] Add tokenizer mode (#298) · 998d9d15
  Woosuk Kwon authored Jun 28, 2023
  
  998d9d15
- [Tokenizer] Add an option to specify tokenizer (#284) · 4338cc47
  Woosuk Kwon authored Jun 28, 2023
  
  4338cc47
17 Jun, 2023 2 commits
- Change the name to vLLM (#150) · 0b98ba15
  Woosuk Kwon authored Jun 17, 2023
  
  0b98ba15
- Rename servers to engines (#152) · e5464ee4
  Zhuohan Li authored Jun 17, 2023
  
  e5464ee4
16 Jun, 2023 1 commit
- Rename servers and change port numbers to reduce confusion (#149) · eedb46bf
  Zhuohan Li authored Jun 17, 2023
  
  eedb46bf
10 Jun, 2023 1 commit
- Non-streaming simple fastapi server (#144) · 5020e1e8
  Zhuohan Li authored Jun 11, 2023
  
  5020e1e8
07 Jun, 2023 1 commit
- Add docstrings for LLMServer and related classes and examples (#142) · 42983742
  Zhuohan Li authored Jun 07, 2023
  
  42983742
05 Jun, 2023 1 commit
- Fix various issues of async servers (#135) · 1a956e13
  Zhuohan Li authored Jun 05, 2023
  
  1a956e13
24 May, 2023 1 commit
- OpenAI Compatible Frontend (#116) · 057daef7
  Zhuohan Li authored May 23, 2023
  
  057daef7