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...

Celý popis

Podrobná bibliografie
Hlavní autoři: Wang, Kuan, Liu, Zhijian, Lin, Yujun, Lin, Ji, Han, Song
Další autoři: Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Médium: Článek
Jazyk:English
Vydáno: Institute of Electrical and Electronics Engineers (IEEE) 2021
On-line přístup:https://hdl.handle.net/1721.1/129522

Internet

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

Podobné jednotky