@article{dovetailacpugpuheterogeneousspeculative, title = {Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference}, author = {Libo Zhang and Zhaoning Zhang and Baizhou Xu and Songzhu Mei and Dongsheng Li}, year = {2024}, eprint = {2412.18934}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2412.18934v1}, }