AutoChunk: Automated Activation Chunk for Memory-Efficient Deep Learning Inference

Open Webpage

Xuanlei Zhao, Shenggan Cheng, Guangyang Lu, Haotian Zhou, Bin Jia, Yang You

Published: 01 Jan 2024, Last Modified: 13 Nov 2024ICLR 2024EveryoneRevisionsBibTeXCC BY-SA 4.0