Low-Precision Quantization Techniques for Hardware-Implementation-Friendly BERT Models

Xinpei Zhang, Yi Ding, Mingfei Yu, Shin-ichi O'Uchi, Masahiro Fujita. Low-Precision Quantization Techniques for Hardware-Implementation-Friendly BERT Models. In 23rd International Symposium on Quality Electronic Design, ISQED 2022, Santa Clara, CA, USA, April 6-7, 2022. pages 1-6, IEEE, 2022. [doi]

Abstract

Abstract is missing.