Login / Signup

Splitwise: Efficient Generative LLM Inference Using Phase Splitting.

Pratyush PatelEsha ChoukseChaojie ZhangAashaka ShahÍñigo GoiriSaeed MalekiRicardo Bianchini
Published in: ISCA (2024)
Keyphrases
  • artificial intelligence
  • efficient learning
  • database
  • data mining
  • computationally efficient
  • highly efficient
  • neural network
  • information retrieval
  • information systems
  • generative model