Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation

Heming Xia, Tao Ge 0001, Peiyi Wang, Si-Qing Chen, Furu Wei, Zhifang Sui. Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation. In Houda Bouamor, Juan Pino 0001, Kalika Bali, editors, Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore, December 6-10, 2023. pages 3909-3925, Association for Computational Linguistics, 2023. [doi]

Abstract

Abstract is missing.