@article{deepspeedinferenceenablingefficient, title = {DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale}, author = {Reza Yazdani Aminabadi and Samyam Rajbhandari and Minjia Zhang and Ammar Ahmad Awan and Cheng Li and Du Li and Elton Zheng and Jeff Rasley and Shaden Smith and Olatunji Ruwase and Yuxiong He}, year = {2022}, eprint = {2207.00032}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2207.00032v1}, }