SpecHub: Provable Acceleration to Multi-Draft Speculative Decoding Ryan Sun author Tianyi Zhou author Xun Chen author Lichao Sun author 2024-11 text Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing Yaser Al-Onaizan editor Mohit Bansal editor Yun-Nung Chen editor Association for Computational Linguistics Miami, Florida, USA conference publication sun-etal-2024-spechub 10.18653/v1/2024.emnlp-main.1148 https://aclanthology.org/2024.emnlp-main.1148/ 2024-11 20620 20641