@article{
venkatesha2025fast,
title={Fast and Cost-effective Speculative Edge-Cloud Decoding with Early Exits},
author={Yeshwanth Venkatesha and Souvik Kundu and Priyadarshini Panda},
journal={Transactions on Machine Learning Research},
issn={2835-8856},
year={2025},
url={https://openreview.net/forum?id=PTIUjARnbc},
note={}
}