@article{190600532, title = {Efficient 8-Bit Quantization of Transformer Neural Machine Language Translation Model}, author = {Aishwarya Bhandare and Vamsi Sripathi and Deepthi Karkada and Vivek Menon and Sun Choi and Kushal Datta and Vikram Saletore}, year = {2019}, eprint = {1906.00532}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/1906.00532v2}, }