16 April 2024 13:45 - 14:15
Unlocking AI efficiency - how to speed up your apps and spend less
Join OctoML’s VP of Customer Success, Anna Connolly, and Solutions Architect Bassem Yacoube as they discuss how organizations can optimize their AI workloads for maximum efficiency.
The cost of production AI can skyrocket as an app or service gains user traction. Fortunately, organizations can stave off unexpected (and unsustainable) cost increases by optimizing ML models and identifying low-cost hardware.
Anna and Bassem will share real-world examples from Microsoft Xbox and generative AI startup Wombo, who successfully optimized their computer vision workloads to run fast on multiple types of hardware.
Learn from their experiences and insights on how to make your AI workloads more efficient, ultimately driving better performance and cost-effectiveness in your AI deployments.