Lee, Gibbeum

1. Predictive Pipelined Decoding: A Compute-Latency Trade-off for Exact LLM Decoding
   2023/07/12 by Yang, Seongjun, Lee, Gibbeum, Cho, Jaewoong +2 · 3 citations
   #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG)