@article{relayattentionforefficientlargelanguage, title = {RelayAttention for Efficient Large Language Model Serving with Long System Prompts}, author = {Lei Zhu and Xinjiang Wang and Wayne Zhang and Rynson W. H. Lau}, year = {2024}, eprint = {2402.14808}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2402.14808v3}, }