PerLLM: Personalized Inference Scheduling with Edge-Cloud Collaboration for Diverse LLM Services.
Zheming YangYuanhao YangChang ZhaoQi GuoWenkai HeWen JiPublished in: CoRR (2024)
Keyphrases
- cloud computing
- personalized information
- context aware
- service providers
- voice and data services
- web services
- geographically dispersed
- cloud services
- repositories of learning objects
- scheduling problem
- service oriented
- personalized services
- user specific
- utility computing
- cloud platform
- ubiquitous computing
- service composition
- computing infrastructure
- exchange information
- end users
- middleware architecture
- resource allocation
- information services
- user centric
- grid environment
- e learning
- bayesian networks
- service discovery
- private cloud
- personal preferences
- information sharing
- computing paradigm
- user communities
- resource utilization
- virtual enterprise
- computing resources
- parallel machines
- edge detection
- scheduling algorithm
- data center
- user profiles
- team members