Commits · 7297fa6f7c4ce6413ee005025b312c4c9d4f5f0b · norm / vllm

20 May, 2023 1 commit
- Remove unused parts in Megatron-LM code and add copyright notice (#110) · 7297fa6f
  Zhuohan Li authored May 20, 2023
  
  7297fa6f
19 May, 2023 2 commits
- Fix timeout error in the FastAPI frontend (#34) · b7955ef1
  Zhuohan Li authored May 19, 2023
  
  b7955ef1
- Use runtime profiling to replace manual memory analyzers (#81) · f756799b
  Zhuohan Li authored May 19, 2023
  
  f756799b
18 May, 2023 1 commit
- Use pytest format for unit tests (#107) · 825d8892
  Woosuk Kwon authored May 17, 2023
  
  825d8892
15 May, 2023 4 commits
- Add docstrings to some modules and classes (#100) · b322fd16
  Woosuk Kwon authored May 14, 2023
  
  b322fd16
- Add copyright headers to source files adapted from FT (#104) · 667ba399
  Woosuk Kwon authored May 14, 2023
  
  667ba399
- Add copyright headers for HF models (#103) · 707ec647
  Woosuk Kwon authored May 14, 2023
  
  707ec647
- Add Apache-2.0 license (#102) · 89988ec8
  Woosuk Kwon authored May 14, 2023
  
  89988ec8
13 May, 2023 1 commit
- Minor code cleaning for SamplingParams (#99) · 6208d622
  Woosuk Kwon authored May 12, 2023
  
  6208d622
11 May, 2023 2 commits
- Enhance SamplingParams (#96) · 42f1042e
  Woosuk Kwon authored May 11, 2023
  
  42f1042e
- Implement presence and frequency penalties (#95) · 55f8b0a5
  Woosuk Kwon authored May 10, 2023
  
  55f8b0a5
10 May, 2023 4 commits
- Support top-k sampling (#94) · 9f88db35
  Woosuk Kwon authored May 10, 2023
  
  9f88db35
- Avoid sorting waiting queue & Minor code cleaning (#93) · ae356774
  Woosuk Kwon authored May 10, 2023
  
  ae356774
- Log system stats (#90) · e3319577
  Woosuk Kwon authored May 10, 2023
  
  e3319577
- Rename variables and methods (#91) · 8d66a7b6
  Woosuk Kwon authored May 10, 2023
  
  8d66a7b6
09 May, 2023 5 commits
- Update sample prompts in `simple_server.py` (#89) · ce26e57f
  Woosuk Kwon authored May 09, 2023
  
  ce26e57f
- Use slow tokenizer for LLaMA (#84) · 85eb6318
  Woosuk Kwon authored May 09, 2023
  
  85eb6318
- Enhance model loader (#83) · add055e1
  Woosuk Kwon authored May 09, 2023
  
  add055e1
- Refactor system architecture (#82) · 7c041ab5
  Woosuk Kwon authored May 09, 2023
  
  7c041ab5
- Add a system logger (#85) · 8917782a
  Woosuk Kwon authored May 08, 2023
  
  8917782a
07 May, 2023 1 commit
- Specify python package dependencies in requirements.txt (#78) · 7addca59
  Woosuk Kwon authored May 07, 2023
  
  7addca59
06 May, 2023 1 commit
- [Minor] Fix a dtype bug (#79) · c84e9242
  Woosuk Kwon authored May 06, 2023
  
  c84e9242
05 May, 2023 1 commit
- Replace FlashAttention with xformers (#70) · c9d5b6d4
  Woosuk Kwon authored May 05, 2023
  
  c9d5b6d4
04 May, 2023 3 commits
- Use dtype from model config & Add Dolly V2 (#63) · 189ae231
  Woosuk Kwon authored May 04, 2023
  
  189ae231
- Add support for GPT-2 (#60) · e548c148
  Woosuk Kwon authored May 04, 2023
  
  e548c148
- Fix a bug in attention kernel (#68) · 130d5fd8
  Woosuk Kwon authored May 04, 2023
  
  130d5fd8
03 May, 2023 3 commits
- Support bfloat16 data type (#54) · e070829a
  Woosuk Kwon authored May 03, 2023
  
  e070829a
- Refactor attention kernels (#53) · 436e523b
  Woosuk Kwon authored May 03, 2023
  
  436e523b
- New weight loader without np copy (#52) · 27f1410d
  Zhuohan Li authored May 03, 2023
  
  27f1410d
30 Apr, 2023 1 commit
- Add an option to launch cacheflow without ray (#51) · 4858f3bb
  Zhuohan Li authored Apr 30, 2023
  
  4858f3bb
28 Apr, 2023 1 commit
- Add support for GPT-NeoX (Pythia) (#50) · a96d63c2
  Woosuk Kwon authored Apr 28, 2023
  
  a96d63c2
17 Apr, 2023 1 commit
- Change plotting script · aa50b17c
  Woosuk Kwon authored Apr 17, 2023
  
  aa50b17c
15 Apr, 2023 1 commit
- Support various block sizes & Change default block size to 16 (#38) · 0f4b3219
  Woosuk Kwon authored Apr 15, 2023
  
  0f4b3219
12 Apr, 2023 1 commit
- Collect system stats in scheduler & Add scripts for experiments (#30) · 84eee24e
  Woosuk Kwon authored Apr 12, 2023
  
  84eee24e
11 Apr, 2023 1 commit
- Memcpy kernel for flash attention (#29) · e3cec88a
  Siyuan (Ryans) Zhuang authored Apr 10, 2023
```
* optimize

* add benchmark

* add assert

* add test
```
  e3cec88a
10 Apr, 2023 1 commit
- Support block size 32 (#35) · b9926f7f
  Woosuk Kwon authored Apr 09, 2023
  
  b9926f7f
09 Apr, 2023 1 commit
- Add an option to use dummy model weights (#33) · ee88a7e5
  Woosuk Kwon authored Apr 08, 2023
  
  ee88a7e5
08 Apr, 2023 2 commits
- Add query stride to multi_query_cached_kv_attention & Add kernel benchmark script (#27) · c267b1a0
  Woosuk Kwon authored Apr 08, 2023
```
* Add query stride to multi_query_cached_kv_attention

* Add kernel benchmark script
```
  c267b1a0
- Implement block copy kernel to optimize beam search (#32) · 0f40557a
  Woosuk Kwon authored Apr 07, 2023
  
  0f40557a
06 Apr, 2023 1 commit
- Fix potential bugs in FastAPI frontend and add comments (#28) · a490aafa
  Zhuohan Li authored Apr 06, 2023
  
  a490aafa