@article{fastercascadesviaspeculativedecoding, title = {Faster Cascades via Speculative Decoding}, author = {Harikrishna Narasimhan and Wittawat Jitkrittum and Ankit Singh Rawat and Seungyeon Kim and Neha Gupta and Aditya Krishna Menon and Sanjiv Kumar}, year = {2024}, eprint = {2405.19261}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2405.19261v2}, }