Large Language Models for the Rest of Us - Infrastructure and Deployment

Learn about the infrastructure challenges and deployment solutions for Large Language Models (LLMs) in this 36-minute tech talk delivered by Aqueduct Co-founder and CTO Chenggang Wu at an ML Meetup in San Francisco. Gain insights into the complexities of running LLMs in cloud environments, watch a practical demonstration of LLM deployment on cloud infrastructure, and discover how Aqueduct's platform streamlines the process of moving LLM-powered workflows from prototype to production. Master the essential knowledge needed to overcome the technical barriers that typically limit LLM implementation to major tech companies.