Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation.
Heming Xia, Tao Ge, Peiyi Wang, Si-Qing Chen, Furu Wei, Zhifang Sui
Browse the full EMNLP paper archive.
Heming Xia, Tao Ge, Peiyi Wang, Si-Qing Chen, Furu Wei, Zhifang Sui
Browse the full EMNLP paper archive.