@misc{indiciae6ac03bb8d7d1, title = {Ps and Qs: Quantization-Aware Pruning for Efficient Low Latency Neural Network Inference}, author = {Hawks, Benjamin and Duarte, Javier and Fraser, Nicholas J. and Pappalardo, Alessandro and Tran, Nhan and Umuroglu, Yaman}, year = {2021}, doi = {10.3389/frai.2021.676564}, url = {https://www.osti.gov/biblio/1824191}, note = {Source identifier: 1824191} }