AI RESEARCH
DisCEdge: Distributed Context Management for Large Language Models at the Edge
arXiv CS.LG
•
ArXi:2511.22599v2 Announce Type: replace-cross Deploying Large Language Model (LLM) services at the edge benefits latency-sensitive and privacy-aware applications. However, the stateless nature of LLMs makes managing user context (e.g., sessions, preferences) across geo-distributed edge nodes challenging. Existing solutions, such as client-side context storage, We propose DisCEdge, a distributed context management system that s and replicates user context in tokenized form across edge nodes.