A Fast Post-Training Pruning Framework for Transformers.

Woosuk Kwon Sehoon Kim Michael W. Mahoney Joseph Hassoun Kurt Keutzer Amir Gholami

Published in: NeurIPS (2022)

Keyphrases

main contribution
machine learning
artificial intelligence
case study
key features
framework enables
neural network
real world
training set
search space
theoretical framework
design principles