Optimizing Generative AI Workloads for Sustainability and Cost - AIM253
AWS Events via YouTube
-
34
-
- Write review
40% Off Career-Building Certificates
Power BI Fundamentals - Create visualizations and dashboards from scratch
Overview
Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Explore practical strategies for building efficient and cost-effective generative AI solutions in this 20-minute conference talk from AWS re:Invent 2025. Discover how to optimize generative AI workloads using AWS services including SageMaker and Bedrock while implementing sustainability best practices. Learn essential optimization techniques such as quantization and pruning to improve model efficiency, and master cost-saving infrastructure approaches including spot instances and intelligent storage tiering. Gain insights into leveraging AWS's native capabilities to develop high-performance AI solutions that balance environmental responsibility with budget constraints, enabling you to create more sustainable and economical generative AI implementations.
Syllabus
AWS re:Invent 2025 - Optimizing generative AI workloads for sustainability and cost (AIM253)
Taught by
AWS Events