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

@inproceedings{xi-2025-efficiency, 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}, 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} }