Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exiting

Item #:

079017-0381

Details

DOI: https://doi.org/10.52202/079017-0381
Author(s): Kai Han, Fangcheng Liu, Zhenhua Liu, Yunsheng Ni, Duyu Tang, Yehui Tang, Yunhe Wang
Pages: 11946-11965 (20 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 37
Date/Location: Held 10-15 December 2024, Vancouver, Canada.
Series: Advances in Neural Information Processing Systems 37
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)

DOI: https://doi.org/10.52202/079017-0381
Author(s): Kai Han, Fangcheng Liu, Zhenhua Liu, Yunsheng Ni, Duyu Tang, Yehui Tang, Yunhe Wang
Pages: 11946-11965 (20 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 37
Date/Location: Held 10-15 December 2024, Vancouver, Canada.
Series: Advances in Neural Information Processing Systems 37
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)