@article{duodecodinghardwareawareheterogeneous, title = {DuoDecoding: Hardware-aware Heterogeneous Speculative Decoding with Dynamic Multi-Sequence Drafting}, author = {Kai Lv and Honglin Guo and Qipeng Guo and Xipeng Qiu}, year = {2025}, eprint = {2503.00784}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.00784v1}, }