FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling
Weilin Zhao, Tengyu Pan, Xu Han, Yudi Zhang, Sun Ao, Yuxiang Huang, Kaihuo Zhang, Weilun Zhao, Yuxuan Li, Jie Zhou, Hao Zhou, Jianyong Wang, Maosong Sun, Zhiyuan Liu. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
Authors
- Jie Zhou (ORCID: https://orcid.org/0000-0003-4383-2280)
- Hao Zhou (ORCID: https://orcid.org/0000-0002-0173-0393)
- Yuxiang Huang (ORCID: https://orcid.org/0000-0003-1329-8814)
- Tao Pan (ORCID: https://orcid.org/0000-0003-4346-6428)
- Maosong Sun (ORCID: https://orcid.org/0000-0002-6011-6115)
- Xu Han (ORCID: https://orcid.org/0000-0002-2742-5354)
- Kaihuo Zhang
- Weilin Zhao (ORCID: https://orcid.org/0000-0001-8016-1952)
- Zhiyuan Liu (ORCID: https://orcid.org/0000-0002-6331-0810)
- Yuxuan Li (ORCID: https://orcid.org/0009-0006-3155-1886)
- Ao Sun (ORCID: https://orcid.org/0009-0007-5369-624X)
- Jianyong Wang (ORCID: https://orcid.org/0000-0003-1689-2384)
- Weilun Zhao
- Yudi Zhang (ORCID: https://orcid.org/0009-0002-4820-1103)
Publication Details
- Published
- 2025-01-01
- DOI
- https://doi.org/10.18653/v1/2025.acl-long.198
- Primary Topic
- Natural Language Processing Techniques
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Science Foundation
- Tsinghua University