GOBO: Quantizing Attention-Based NLP Models for Low Latency and Energy Efficient Inference.

Ali Hadi Zadeh Isak Edo Omar Mohamed Awad Andreas Moshovos

Published in: MICRO (2020)

Keyphrases

efficient inference
low latency
real time
probabilistic model
human pose estimation
hidden variables
high speed
structured prediction
machine learning
parameter estimation
conditional random fields
highly efficient
gaussian processes
fully connected