2 papers
cs.CL2024
Temperature-Centric Investigation of Speculative Decoding with Knowledge Distillation
Siru Ouyang, Shuohang Wang, Minhao Jiang +4
Speculative decoding stands as a pivotal technique to expedite inference in autoregressive (large) language models. This method employs a smaller draft model to speculate a block o…
cs.CL2024
ParallelSpec: Parallel Drafter for Efficient Speculative Decoding
Zilin Xiao, Hongming Zhang, Tao Ge +3
Speculative decoding has proven to be an efficient solution to large language model (LLM) inference, where the small drafter predicts future tokens at a low cost, and the target mo…