Ouroboros: Generating Longer Drafts Phrase by Phrase for Faster Speculative Decoding

Weilin Zhao, Yuxiang Huang, Xu Han, Wang Xu, Chaojun Xiao, Xinrong Zhang, Yewei Fang, Kaihuo Zhang, Zhiyuan Liu, Maosong Sun


Abstract
Speculative decoding is a widely used method that accelerates the generation process of large language models (LLMs) with no compromise in model performance. It achieves this goal by using an existing smaller model for drafting and then employing the target LLM to verify the draft in a low-cost parallel manner. Under such a drafting-verification framework, drafting efficiency has become a bottleneck in the final speedup of speculative decoding. Therefore, generating longer drafts at less cost can lead to better decoding speedup. To achieve this, we introduce Ouroboros, which can generate draft phrases to parallelize the drafting process and meanwhile lengthen drafts in a training-free manner. The experimental results on various typical text generation tasks show that Ouroboros can achieve speedups of up to 2.4× over speculative decoding and 3.9× over vanilla decoding, without fine-tuning draft and target models. Code available at https://github.com/thunlp/Ouroboros.
Anthology ID:
2024.emnlp-main.742
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
13378–13393
Language:
URL:
https://aclanthology.org/2024.emnlp-main.742
DOI:
Bibkey:
Cite (ACL):
Weilin Zhao, Yuxiang Huang, Xu Han, Wang Xu, Chaojun Xiao, Xinrong Zhang, Yewei Fang, Kaihuo Zhang, Zhiyuan Liu, and Maosong Sun. 2024. Ouroboros: Generating Longer Drafts Phrase by Phrase for Faster Speculative Decoding. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 13378–13393, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Ouroboros: Generating Longer Drafts Phrase by Phrase for Faster Speculative Decoding (Zhao et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.742.pdf
Software:
 2024.emnlp-main.742.software.zip