@article{learningtokeepapromisescalinglanguage, title = {Learning to Keep a Promise: Scaling Language Model Decoding Parallelism with Learned Asynchronous Decoding}, author = {Tian Jin and Ellie Y. Cheng and Zack Ankner and Nikunj Saunshi and Blake M. Elias and Amir Yazdanbakhsh and Jonathan Ragan-Kelley and Suvinay Subramanian and Michael Carbin}, year = {2025}, eprint = {2502.11517}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2502.11517v2}, }