LookupFFN: Making Transformers Compute-lite for CPU inference.

Zhanpeng Zeng Michael Davies Pranav Pulijala Karthikeyan Sankaralingam Vikas Singh

Published in: CoRR (2024)

Keyphrases

probabilistic inference
bayesian inference
inference process
real time
inference engine
computer vision
pairwise
inference mechanism
genetic algorithm
website
bayesian networks
personal computer
probabilistic reasoning
efficient computation
gpu implementation