@article{magicpyramidacceleratinginferencewith, title = {Magic Pyramid: Accelerating Inference with Early Exiting and Token Pruning}, author = {Xuanli He and Iman Keivanloo and Yi Xu and Xiang He and Belinda Zeng and Santosh Rajagopalan and Trishul Chilimbi}, year = {2021}, eprint = {2111.00230}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2111.00230v1}, }