@article{hadeshardwareaccelerateddecodingfor, title = {HADES: Hardware Accelerated Decoding for Efficient Speculation in Large Language Models}, author = {Ze Yang and Yihong Jin and Xinhe Xu}, year = {2024}, eprint = {2412.19925}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2412.19925v2}, }