This course was developed by members of AWS Technical Field Communities (TFC), an AWS community of technical experts. The content is intended to complement our standard training curriculum and augment your AWS learning journey. We are aware some courses have accessibility limitations and are working to address. If you require accommodation, please contact AWS Training and Certification Customer Support.
In this course, learners will explore Amazon EC2 G7e instances powered by NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs and how they accelerate generative AI inference on Amazon SageMaker AI. The course covers G7e capabilities, ideal use cases, deployment steps, and performance benchmarks comparing G6e and G7e instances. Learners will also discover how combining G7e with EAGLE speculative decoding delivers compounding cost and throughput improvements, achieving up to 75 percent cost reduction over previous-generation baselines.
