Data & Infrastructure

AWS Inferentia

Amazon-designed AI inference accelerator chip. Inf2 instances offer cost/performance advantages over GPUs for certain inference workloads on Bedrock and self-managed EC2. Not a full training replacement but a mature inference option in the AWS stack.

Related terms

H100 / H200
NVIDIA data-center GPUs based on Hopper architecture. H100 (2022) and H200 (2024) are the workhorses of frontier-model training and inference through 2026. Predecessors to Blackwell (B100/B200) which shipped in volume 2024-2025.

Next steps

Take the assessment— See where you stand

Where this fits

AWS Inferentia is part of the Data & Infrastructure vocabulary used in the Generative AI Maturity Framework. See the full glossary for the complete set of 149 defined terms, or take the free maturity assessment to see where your organisation stands.

Related terms

Related on this site

Framework dimensions

Free tools

Whitepapers

Next steps

Where this fits