HAQ: Hardware-Aware Automated Quantization With Mixed Precision

HAQ: Hardware-Aware Automated Quantization With Mixed Precision

Model quantization is a widely used technique to compress and accelerate deep neural network (DNN) inference. Emergent DNN hardware accelerators begin to support mixed precision (1-8 bits) to further improve the computation efficiency, which raises a great challenge to find the optimal bitwidth for...

Fuld beskrivelse

Bibliografiske detaljer
Main Authors: Wang, Kuan, Liu, Zhijian, Lin, Yujun, Lin, Ji, Han, Song
Andre forfattere: Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Format: Article
Sprog:English
Udgivet: Institute of Electrical and Electronics Engineers (IEEE) 2021
Online adgang:https://hdl.handle.net/1721.1/129522

Internet

https://hdl.handle.net/1721.1/129522

Lignende værker