Large Language Models (LLMs) Inference Offloading and Resource Allocation in Cloud-Edge Networks: An Active Inference Approach.
Jingcheng FangYing HeF. Richard YuJianqiang LiVictor C. M. LeungPublished in: VTC Fall (2023)
Keyphrases
- resource allocation
- language model
- language modeling
- information retrieval
- probabilistic model
- document retrieval
- resource management
- allocation strategies
- optimal resource allocation
- allocation problems
- speech recognition
- statistical language models
- bayesian networks
- dynamic resource allocation
- allocate resources
- resource allocation problems
- language modelling
- combinatorial auctions
- context sensitive
- n gram
- multi agent systems
- question answering
- resource allocation decisions
- distributed resource allocation
- resource allocation and scheduling