Preprint
Aug 2026
Spatial Prefix Caching for Wireless Edge LLM Inference: A Stochastic-Geometry and Queueing Framework
A stochastic-geometry and queueing framework for this spatial communication--caching--computation tradeoff and shows that the latency-optimal node need not be the nearest node, that TTFT can be non-monotonic in cached-prefix depth because of GPU-memory coupling.
Leo T. Yang, Zhouyong Liu
· 1 citation