@article{adecodingaccelerationframeworkfor,
  title = {Efficiency Unleashed: Inference Acceleration for LLM-based Recommender Systems with Speculative Decoding},
  author = {Yunjia Xi and Hangyu Wang and Bo Chen and Jianghao Lin and Menghui Zhu and Weiwen Liu and Ruiming Tang and Zhewei Wei and Weinan Zhang and Yong Yu},
  year = {2024},
  eprint = {2408.05676},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2408.05676v2},
}