@article{eagle2fasterinferenceoflanguagemodels, title = {EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees}, author = {Yuhui Li and Fangyun Wei and Chao Zhang and Hongyang Zhang}, year = {2024}, eprint = {2406.16858}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.16858v2}, }