SparKV: Overhead-Aware KV Cache Loading for Efficient On-Device LLM Inference

arXiv:2604.21231 · cs.NI, cs.AI, cs.PF · Submitted 2026-04-23 · Read on arXiv

cs.NI, cs.AI, cs.PF

Submitted: 2026-04-23

Updated: 2026-10-08

Terminology

• Edge Devices — 1× in this paper · explained in 2 episodes
• KV cache — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Robustness — 1× in this paper · explained in 5 episodes

Related papers

• HiFiNet: Hierarchical Fault Identification in Wireless Sensor Networks via Edge-Based Classification and Graph Aggregation
• Embodied AI in 6G Networks: From Intelligent Connectivity to Physical Intelligence
• Lightweight GenAI for Network Traffic Generation: Fidelity, Augmentation, and Classification
• EdgePoW: Adaptive Ingress-Aware Defense with Non-Interactive PoW Against Volumetric SYN Floods
• Digital Twin for Pre-Deployment Validation of AI-Driven Safety-Critical Industrial Edge Control Loops
• SoK: Where Do Flow Labels Come From? Auditing Label Provenance in Encrypted Traffic Benchmarks