2 papers
cs.LG2025
Splitwise: Collaborative Edge-Cloud Inference for LLMs via Lyapunov-Assisted DRL
Abolfazl Younesi, Abbas Shabrang Maryan, Elyas Oustad +3
Deploying large language models (LLMs) on edge devices is challenging due to their limited memory and power resources. Cloud-only inference reduces device burden but introduces hig…
cs.AR2025
MOFCO: Mobility- and Migration-Aware Task Offloading in Three-Layer Fog Computing Environments
Soheil Mahdizadeh, Elyas Oustad, Mohsen Ansari
Task offloading in three-layer fog computing environments presents a critical challenge due to user equipment (UE) mobility, which frequently triggers costly service migrations and…