Fast-dLLM++: Fr\'{e}chet Profile Decoding for Faster Diffusion LLM Inference 文章

ArXiv CS.CL2026-06-03NEWSen作者: Siva Rajesh Kasa, Yasong Dai, Sumit Negi, Hongdong Li
查看原文 →
关系图谱

Fast-dLLM++: Fr\'{e}chet Profile Decoding for Faster Diffusion LLM Inference · 相关技术

相关技术

Fr\'{e}chet profile decodingFréchet profile decodingconfidence-guided parallel decodingKV cachingFast-dLLMDiffusion large language models