Smart-DNN+: A Memory-efficient Neural Networks Compression Framework for the Model Inference

Donglei Wu, Weihao Yang, Xiangyu Zou, Wen Xia, Shiyi Li, Zhenbo Hu, Weizhe Zhang, Binxing Fang. Smart-DNN+: A Memory-efficient Neural Networks Compression Framework for the Model Inference. TACO, 20(4), December 2023. [doi]

Abstract

Abstract is missing.