Block Pruning For Faster Transformers.

François Lagunas Ella Charlaix Victor Sanh Alexander M. Rush

Published in: CoRR (2021)

Keyphrases

search space
pruning method
variable size
pruning methods
block size
vector quantization
pruning power
pruning algorithm
memory efficient
highly efficient
data sets
optical flow
multi agent
artificial intelligence
machine learning
neural network
databases