Efficient Multi-Task LLM Generative Serving in Heterogeneous Clusters


Grant Data
Project Title
Efficient Multi-Task LLM Generative Serving in Heterogeneous Clusters
Principal Investigator
Professor Wu, Chuan   (Principal Investigator (PI))
Duration
36
Start Date
2024-12-01
Amount
1198059
Conference Title
Efficient Multi-Task LLM Generative Serving in Heterogeneous Clusters
Keywords
Large language models, Generative serving, Multi-task inference, Heterogeneous cluster, Request batching & scheduling
Discipline
NetworkOthers - Computing Science and Information Technology
Panel
Engineering (E)
HKU Project Code
17205824
Grant Type
General Research Fund (GRF) 2024/25
Funding Year
2024
Status
On-going
Objectives
Refer to ES