paperIEEE Xplore·1 Nov 2026·Xinghan Wang, Xiaoxiong Zhong, Weihong Yang, Fangming Liu, Weizhe Zhang
Mix-or-Split: Latency-Aware Scheduling for Edge–Cloud LLM Inference
Mix-or-Split schedules LLM inference across devices, edge and cloud using a fine-grained latency model.
Extract
IEEE Transactions on Parallel and Distributed Systems