@article{quakespeedingupmodelinferenceusingquick, title = {QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities}, author = {Sai Kiran Narayanaswami and Gopalakrishnan Srinivasan and Balaraman Ravindran}, year = {2024}, eprint = {2412.00408}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2412.00408v1}, }