Efficiency Unleashed: Inference Acceleration for LLM-based Recommender Systems with Speculative Decoding.

@inproceedings{xi-2025-efficiency, author = {Yunjia Xi and Jiahao Zhao and Menghui Zhu and Hangyu Wang and Shaoxuan Xu and Weiwen Liu and Bo Chen and Jianghao Lin and Fengqi Zhu and Ruiming Tang and Jiahao Zhao and Menghui Zhu and Jingyang Ou and Weinan Zhang and Shaoxuan Xu and Weiwen Liu and Sirius Chen and Zhewei Wei and Yong Yu and Yuling Shi and Fengqi Zhu and Ruiming Tang and Sirius Chen and Zhewei Wei and Jingyang Ou and Weinan Zhang and Yong Yu and Yuling Shi}, editor = {Nicola Ferro and Maria Maistro and Gabriella Pasi and Omar Alonso and Andrew Trotman and Suzan Verberne}, title = {{Efficiency Unleashed: Inference Acceleration for LLM-based Recommender Systems with Speculative Decoding}}, booktitle = {{Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2025, Padua, Italy, July 13-18, 2025}}, pages = {1891--1901}, publisher = {ACM}, year = {2025}, url = {https://doi.org/10.1145/3726302.3729961}, doi = {https://doi.org/10.1145/3726302.3729961} }