@article{adaeagleoptimizingspeculativedecodingvia, title = {AdaEAGLE: Optimizing Speculative Decoding via Explicit Modeling of Adaptive Draft Structures}, author = {Situo Zhang and Hankun Wang and Da Ma and Zichen Zhu and Lu Chen and Kunyao Lan and Kai Yu}, year = {2024}, eprint = {2412.18910}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2412.18910v1}, }