ChunkLLM: A Lightweight Pluggable Framework for Accelerating LLMs Inference 文章

ArXiv CS.CL2026-05-26NEWSen作者: Haojie Ouyang, Jianwei Lv, Lei Ren, Chen Wei, Xiaojie Wang, Fangxiang Feng

ChunkLLM: A Lightweight Pluggable Framework for Accelerating LLMs Inference · 相关技术