In this workshop we will learn about setting up and running large language models (LLMs) using llama-cpp-python on a high-performance computing (HPC) cluster.

Participants will learn:

• how to configure the environment
• how to install the necessary libraries
• how to download and run quantized models
• how to leverage multiple GPUs for faster inference

Instructors:

Dr. Rachel DuBose, rldubose@ua.edu

Dakeya Chambers, dachambers@ua.edu

Before using AI tools, be sure to review UA OIT’s guidelines for use of AI and the UA AI Minimum Security Standard: https://oit.ua.edu/software/artificial-intelligence/ai-approved-list/

Registration is required. You register for this event here: https://ua.libcal.com/event/16022961