A Low-Latency and Scalable Vector Engine with Operation Fusion for Transformers.

Mincheol Cha Keehyuk Lee Xuan Truong Nguyen Hyuk-Jae Lee

Published in: AICAS (2024)

Keyphrases

low latency
high bandwidth
continuous query processing
high speed
massive scale
highly efficient
high throughput
real time
virtual machine
stream processing
multi dimensional
context aware
computational complexity
query processing
low cost
spatio temporal databases