SWAT: Scalable and Efficient Window Attention-based Transformers Acceleration on FPGAs.

Zhenyu Bai Pranav Dangi Huize Li Tulika Mitra

Published in: CoRR (2024)

Keyphrases

highly scalable
neural network
computer vision
video sequences
computational complexity
lightweight
sliding window
highly efficient
databases
social networks
e learning
website
computationally efficient
self organizing maps
computationally expensive