[AWS GenAI Loft] Unlocking Inferentia & Trainium Accelerators for Inference & Training
AI
GenAI Loft | Paris
Day:
-
Time:
-
Type:
HYBRID
Language:
English
Level(s):
300 - Advanced
We're always seeking ways to push the performance boundaries of AI and machine learning workloads. In this session, we'll take a closer look at two powerful AWS-built AI accelerators - Inferentia and Trainium - and explore how they can enhance the performance and efficiency of your AI training and inference workloads.
Join us as we share our experiences, lessons learned, and real-world use cases to help you better understand how these AI accelerators can fit into your tech stack.
Agenda
8:30 AM UTC
AWS AI Chips 101: Your guide to adopting Amazon Inferentia and Trainium
Maurits de Groot & Dmitri Laptev | Solutions Architect & Senior Solutions Architect at AWS
We're always seeking ways to push the performance boundaries of AI and machine learning workloads. In this session, we'll take a closer look at two powerful AWS-built AI accelerators - Inferentia and Trainium - and explore how they can enhance the performance and efficiency of your ML workloads.
9:30 AM UTC
Coffee Break
9:45 AM UTC
Train your AI workloads on AWS custom AI accelerators: The keys to maximize price-performance
Syl Taylor & Roy Allela | Specialist Solutions Architect & Sr AI/ML Specialist Architect at AWS
To stay ahead in the rapidly-evolving world of AI, it's essential to understand how to evaluate latest compute options. But "performance" can mean different things depending on your business goals. Join us to explore key metrics for assessing compute performance, and learn how to ensure your AI infrastructure drives maximum value for your needs.
11:00 AM UTC
Lunch
12:00 PM UTC
Office Hours