.png){kind=icon}
Return
Game-Based LLM Inference Task Offloading for Edge Computing System
.png){kind=icon}
PRE
AI
DOI：10.1109/TGCN.2026.3676823.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Large Language Models (LLMs), with their powerful capabilities, are fundamentally transforming society. Cloud-based LLM deployment has drawbacks, including latency, lack of offline functionality, and high long-term costs. Edge computing-based LLM solutions address these issues by offloading inference tasks to edge servers. This paper formulates and optimizes an LLM inference framework that jointly accounts for inference time and predictive quality. Specifically, to address the natural tendency of selfish users for personal utility maximization, we develop a Game-theoretic Offloading Algorithm (GOALIT) to optimize LLM inference offloading. The approach enables distributed users to iteratively adjust their strategies and converge to a Nash equilibrium. Compared to the optimal tree-based search (OT-GAH), the proposed approach yields a 27% increase in token throughput and shortens inference latency by 20%, while maintaining lower perplexity under dynamic system loads. These findings confirm the effectiveness of our approach in resource-constrained edge environments.
Keywords:
Edge computing
LLM inference task offloading
quantization
game theory
Journal
I
IF:
6.7
Papers:
1.4K
Citations:
4.3K
Organization
Cited Papers
ShareSaveShareSaveShareSaveAIGC-Driven Real-Time Interactive 4-D Traffic Scene Generation in Vehicular Networks.png)
IEEE Network
IEEE NetworkIF6.3
PREAI
ShareSave
View more