WiP: Efficient LLM Prefilling with Mobile NPU.

Daliang Xu Hao Zhang Liming Yang Ruiqi Liu Mengwei Xu Xuanzhe Liu

Published in: EdgeFM@MobiSys (2024)

Keyphrases

neural network
social networks
mobile phone
lightweight
highly efficient
machine learning
information systems
case study
database systems
relational databases
mobile devices
evolutionary algorithm
data management
cost effective
mobile users