VFF - The signal in the noise
VFF - The signal in the noise
News

AWS Bedrock adds cross-region inference for EU compliance

AWS Machine Learning Blog
Read original
Share
AWS Bedrock adds cross-region inference for EU compliance

AWS has introduced cross-Region Inference (CRIS) on Amazon Bedrock, a managed capability that automatically routes AI model inference requests across multiple AWS regions within defined geographic boundaries. The feature allows European customers to access generative AI models and compute capacity while maintaining compliance with data protection regulations like GDPR. CRIS includes both global profiles that route to any supported AWS commercial region and EU-specific profiles designed for customers with regional data processing requirements.

TL;DR

  • AWS Bedrock now offers cross-Region Inference (CRIS) to route model requests across multiple regions automatically
  • System-defined inference profiles support both global routing and EU geographic scope for regulatory compliance
  • Data transmitted during cross-region inference is encrypted and remains within AWS secure network
  • Feature helps customers build more resilient AI applications by optimizing capacity and reducing latency

Why It Matters

As demand for generative AI compute capacity outpaces supply, enterprises need mechanisms to access models reliably while meeting regional data protection requirements. CRIS addresses this by enabling automatic failover and load distribution across regions without requiring manual intervention, while EU-scoped profiles help customers navigate GDPR and other local data residency obligations.

Business Impact

Organizations can now build more resilient generative AI applications that automatically handle capacity constraints and regional model availability issues. European enterprises gain a compliant path to access global AI capacity without manually managing cross-region routing or risking regulatory violations.

Key Implications

  • EU customers can leverage AWS global infrastructure for AI workloads while maintaining data residency and GDPR compliance through geographic-scoped inference profiles
  • Automatic request routing reduces engineering overhead for managing multi-region deployments and improves application resilience during peak demand periods
  • Encrypted cross-region data transmission within AWS network provides security assurance for sensitive workloads while enabling geographic flexibility

What to Watch

Monitor how European enterprises adopt EU-scoped inference profiles and whether this approach becomes a template for other regulated regions. Track AWS model availability and pricing across regions to understand how CRIS affects cost optimization strategies for customers managing multi-region deployments.

Share
InfrastructureGovernance & PolicyGenerative AIAWS

Subscribe to the newsletter

The latest stories and analysis, delivered to your inbox.

Free. No spam. Unsubscribe any time.

Related stories

Nvidia Sends GPUs to the Moon
InfrastructureTrendingNews

Nvidia Sends GPUs to the Moon

Nvidia is deploying GPUs to lunar missions, extending the company's hardware reach beyond Earth-based data centers and AI applications. The move signals Nvidia's strategy to position its processors as essential infrastructure across multiple domains, including space exploration. Details on specific missions, timelines, and technical specifications are limited in available reporting.

by Tim Fernholz· TechCrunch AI
Etched hits $10.3B valuation with GPU-free AI inference chips
InfrastructureTrendingNews

Etched hits $10.3B valuation with GPU-free AI inference chips

Etched, a startup founded by three Harvard dropouts, has raised funding at a $10.3 billion valuation by developing chips and memory components designed to accelerate AI model inference without requiring GPUs. The company claims its hardware can speed up inference across any AI model. The funding round attracted backing from major investors, signaling confidence in the alternative chip approach to AI acceleration.

by Julie Bort· TechCrunch AI
Google Cloud's AI Boom Comes With a Cash Burn Problem
InfrastructureTrendingNews

Google Cloud's AI Boom Comes With a Cash Burn Problem

Google Cloud's revenue surged 82% in Q2 2026, driven by AI service demand and chip sales, lifting Alphabet's overall top-line growth to 24%. However, the company burned cash in the quarter as capital expenditures of $45 billion exceeded operating cash flow of $39 billion, a rare occurrence for Google. The cash burn and mounting AI infrastructure costs triggered a 4% stock sell-off in after-hours trading.

by Martin Peers· The Information
NVIDIA Deploys AI Supercomputer at Naval Postgraduate School
InfrastructureTrendingNews

NVIDIA Deploys AI Supercomputer at Naval Postgraduate School

NVIDIA commissioned a DGX GB300 supercomputer at the Naval Postgraduate School in Monterey, California, giving the military graduate institution's 1,500 students and 600 faculty access to large-scale AI computing for applications including weather prediction, cybersecurity, and disaster response planning. The system, deployed during the school's Converge @ NPS event, anchors an NVIDIA AI Technology Center on campus and expands an existing collaboration that includes instructor toolkits through NVIDIA's Deep Learning Institute. The move aims to train military leaders to work effectively in AI-enabled environments while conducting applied research in domains like ocean modeling and digital twin development.

by NVIDIA Writers· NVIDIA Blog (AI)