SkipDecode: Autoregressive Skip Decoding with Batching and Caching for Efficient LLM InferenceLuciano Del Corro,Allie Del Giorno,Sahaj Agarwal,Bin Yu,Ahmed Hassan Awadallah,Subhabrata MukherjeeICLR 2024(2024)引用 25|浏览17关键词Adaptive Computation,Efficient Inference,Generative ModelsAI 理解论文溯源树样例生成溯源树,研究论文发展脉络Chat Paper正在生成论文摘要