Building Fast, Cost-Efficient, Sovereign Inference Platforms on AWS with Intel CPUs
AWS Events via YouTube
-
46
-
- Write review
Stuck in Tutorial Hell? Learn Backend Dev the Right Way
Learn AI, Data Science & Business — Earn Certificates That Get You Hired
Overview
Google, IBM & Meta Certificates — All 10,000+ Courses at 40% Off
One annual plan covers every course and certificate on Coursera. 40% off for a limited time.
Get Full Access
Learn how to build fast, cost-efficient, and sovereign generative AI inference platforms on AWS using Intel CPUs in this conference talk from AWS re:Invent 2025. Discover how to overcome common misconceptions around cost, performance, and infrastructure that often slow GenAI adoption by exploring real-world use cases and open-source alternatives that provide better data privacy control and lower total costs. Explore Intel's optimized CPU-first innovations and instances that enable scalable, cost-effective GenAI inference pipelines on AWS services including SageMaker and EC2. Gain insights into how Intel is helping customers unlock the full potential of generative AI, whether you're a startup developer or enterprise architect looking to deploy AI solutions with improved sovereignty and cost efficiency.
Syllabus
AWS re:Invent 2025 -Building Fast, Cost-Efficient, Sovereign Inference Platforms on AWS w/Intel CPUs
Taught by
AWS Events