Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Explore strategies for scaling generative AI workloads through strategic model selection in this 30-minute conference talk from AWS Summit London 2025. Discover how to optimize your AI implementations by choosing the most efficient models for your specific use cases, balancing performance requirements with computational costs. Learn best practices for deploying and managing generative AI at scale on AWS infrastructure, including considerations for model size, inference speed, and resource allocation. Gain insights into AWS services and tools that support efficient generative AI workloads, and understand how to make informed decisions when selecting between different AI models to maximize both performance and cost-effectiveness in production environments.
