@inproceedings{yi-etal-2024-towards, title = "Towards Fast Multilingual {LLM} Inference: Speculative Decoding and Specialized Drafters", author = "Yi, Euiin and Kim, Taehyeon and Jeung, Hongseok and Chang, Du-Seong and Yun, Se-Young", editor = "Al-Onaizan, Yaser and Bansal, Mohit and Chen, Yun-Nung", booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing", month = nov, year = "2024", address = "Miami, Florida, USA", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/Add-Cong-Liu-Florida-Atlantic-University-author-id/2024.emnlp-main.602/", doi = "10.18653/v1/2024.emnlp-main.602", pages = "10789--10802" }