Commits · f756799b84f5558c82c7a049069f845b31573e9e · norm / vllm

19 May, 2023 1 commit
- Use runtime profiling to replace manual memory analyzers (#81) · f756799b
  Zhuohan Li authored May 19, 2023
  
  f756799b
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 1 commit
- Avoid sorting waiting queue & Minor code cleaning (#93) · ae356774
  Woosuk Kwon authored May 10, 2023
  
  ae356774
09 May, 2023 2 commits
- Use slow tokenizer for LLaMA (#84) · 85eb6318
  Woosuk Kwon authored May 09, 2023
  
  85eb6318
- Refactor system architecture (#82) · 7c041ab5
  Woosuk Kwon authored May 09, 2023
  
  7c041ab5