Login / Signup

NeuPIMs: NPU-PIM Heterogeneous Acceleration for Batched LLM Inferencing.

Guseul HeoSangyeop LeeJaehong ChoHyunmin ChoiSanghyeon LeeHyungkyu HamGwangsun KimDivya MahajanJongse Park
Published in: ASPLOS (3) (2024)
Keyphrases
  • knowledge representation
  • heterogeneous networks
  • data sets
  • real world
  • database
  • machine learning
  • genetic algorithm
  • inference engine
  • semantically rich