Stitching Weight-Shared Deep Neural Networks for Efficient Multitask Inference on GPU

Zeyu Wang, Xiaoxi He, Zimu Zhou, Xu Wang 0018, Qiang Ma 0007, Xin Miao, Zhuo Liu, Lothar Thiele, Zheng Yang 0002. Stitching Weight-Shared Deep Neural Networks for Efficient Multitask Inference on GPU. In 19th Annual IEEE International Conference on Sensing, Communication, and Networking, SECON 2022, Stockholm, Sweden, September 20-23, 2022. pages 145-153, IEEE, 2022. [doi]

Abstract

Abstract is missing.