Research Project

Resource Efficient LLM Fine-tuning and Serving

Abstract

Large Language Models (LLMs) have achieved great success in many real-world applications. However, fine-tuning and serving LLMs require much memory and computing resources. This project aims to develop cutting-edge techniques to improve the resource efficiency of LLM fine-tuning and serving.

Project members

Zeyi WEN

Assistant Professor

Project Period

2023-Present

Research Area

Data-driven AI & Machine Learning、High-Performance Systems for Data Analytics

Keywords

Efficiency, Fine-tuning, Large Language Models, Model Serving