@inproceedings {216077, author = {Minjia Zhang and Samyam Rajbhandari and Wenhan Wang and Yuxiong He}, title = {{DeepCPU}: Serving {RNN-based} Deep Learning Models 10x Faster}, booktitle = {2018 USENIX Annual Technical Conference (USENIX ATC 18)}, year = {2018}, isbn = {978-1-939133-01-4}, address = {Boston, MA}, pages = {951--965}, url = {https://www.usenix.org/conference/atc18/presentation/zhang-minjia}, publisher = {USENIX Association}, month = jul }