EdgeBERT: Sentence-Level Energy Optimizations for Latency-Aware Multi-Task NLP Inference

Thierry Tambe, Coleman Hooper, Lillian Pentecost, Tianyu Jia, En-Yu Yang, Marco Donato, Victor Sanh, Paul N. Whatmough, Alexander M. Rush, David Brooks 0001, Gu-Yeon Wei. EdgeBERT: Sentence-Level Energy Optimizations for Latency-Aware Multi-Task NLP Inference. In MICRO '21: 54th Annual IEEE/ACM International Symposium on Microarchitecture, Virtual Event, Greece, October 18-22, 2021. pages 830-844, ACM, 2021. [doi]

Authors

Thierry Tambe

This author has not been identified. Look up 'Thierry Tambe' in Google

Coleman Hooper

This author has not been identified. Look up 'Coleman Hooper' in Google

Lillian Pentecost

This author has not been identified. Look up 'Lillian Pentecost' in Google

Tianyu Jia

This author has not been identified. Look up 'Tianyu Jia' in Google

En-Yu Yang

This author has not been identified. Look up 'En-Yu Yang' in Google

Marco Donato

This author has not been identified. Look up 'Marco Donato' in Google

Victor Sanh

This author has not been identified. Look up 'Victor Sanh' in Google

Paul N. Whatmough

This author has not been identified. Look up 'Paul N. Whatmough' in Google

Alexander M. Rush

This author has not been identified. Look up 'Alexander M. Rush' in Google

David Brooks 0001

This author has not been identified. Look up 'David Brooks 0001' in Google

Gu-Yeon Wei

This author has not been identified. Look up 'Gu-Yeon Wei' in Google