Commits · 62ec38ea4148bb8147f346f7e01cab6b8a2ec7b6 · xdb4_94051 / vllm

"...resnet50_onnxruntime_migraphx.git" did not exist on "58ced0d7af264fdae7b2dd85e8394c38a4da4931"

28 May, 2023 2 commits
- Add throughput benchmarking script (#133) · 211318d4
  Woosuk Kwon authored May 28, 2023
  
  211318d4
- Enable LLaMA fast tokenizer (#132) · 337871c6
  Woosuk Kwon authored May 28, 2023
  
  337871c6
24 May, 2023 4 commits
- OpenAI Compatible Frontend (#116) · 057daef7
  Zhuohan Li authored May 23, 2023
  
  057daef7
- Incrementally decode output tokens (#121) · e8671783
  Woosuk Kwon authored May 23, 2023
  
  e8671783
- Print warnings/errors for large swap space (#123) · aedba6d5
  Woosuk Kwon authored May 23, 2023
  
  aedba6d5
- Add contributing guideline and mypy config (#122) · a283ec2e
  Woosuk Kwon authored May 23, 2023
  
  a283ec2e
22 May, 2023 1 commit
- Introduce LLM class for offline inference (#115) · 655a5e48
  Woosuk Kwon authored May 21, 2023
  
  655a5e48
21 May, 2023 1 commit
- Implement stop strings and best_of (#114) · f746ced0
  Woosuk Kwon authored May 21, 2023
  
  f746ced0
20 May, 2023 1 commit
- Refactor system architecture (#109) · c3442c1f
  Woosuk Kwon authored May 20, 2023
  
  c3442c1f