NN-LUT: neural approximation of non-linear operations for efficient transformer inference

Joonsang Yu, Junki Park, Seongmin Park, Minsoo Kim, Sihwa Lee, Dong-hyun Lee, Jungwook Choi. NN-LUT: neural approximation of non-linear operations for efficient transformer inference. In Rob Oshana, editor, DAC '22: 59th ACM/IEEE Design Automation Conference, San Francisco, California, USA, July 10 - 14, 2022. pages 577-582, ACM, 2022. [doi]

Abstract

Abstract is missing.