AWS
Amazon Web Services releases and Terraform AWS provider.
- AWS What's New awsazuregapreviewengineer ·
AWS Interconnect offers free 500 Mbps tier for multicloud connections
AWS has launched a free 500 Mbps tier for its Interconnect service, enabling easier private connections between AWS and other public clouds. This offering simplifies multicloud adoption and testing, providing a fully managed, resilient connection at no charge from the AWS side. It benefits customers evaluating or operating workloads across multiple cloud providers, with a free CloudWatch Network Synthetic Monitor included.
feature - AWS What's New aiawspreviewengineer ·
Amazon Bedrock adds Service Quotas support for bedrock-mantle endpoint
Amazon Bedrock now supports AWS Service Quotas for its bedrock-mantle endpoint, providing customers with visibility into inference quotas for OpenAI and Anthropic APIs. This allows for consistent tracking of limits across AWS services and helps customers proactively plan for production workloads.
feature - AWS What's New mlinfraawspreviewengineer ·
AWS Neuron 2.30.0 Enhances Trainium3 Capabilities and Developer Tools
AWS Neuron 2.30.0 is now generally available, featuring NKI 0.4.0 with new AWS Trainium3 hardware support and 22 new NKI Library kernels. This release benefits ML developers by improving model porting and validation with expanded Neuron Agentic Development skills and introduces the Neuron DRA Driver for Kubernetes. Key updates include hardware-specific instructions, FP8 support, and performance enhancements for custom kernel development and deployment on Trainium and Inferentia instances.
feature patch - AWS What's New aiawspreviewengineer ·
Amazon Bedrock adds request-level usage attribution for InvokeModel APIs
Amazon Bedrock now supports request-level usage attribution for InvokeModel and InvokeModelWithResponseStream APIs. This feature provides granular visibility into model inference usage across an organization, aiding in cost optimization and internal reporting. It extends existing attribution capabilities, offering a consistent tagging mechanism for inference calls.
feature - AWS What's New aiawspreviewengineer ·
SageMaker HyperPod adds inference data capture to S3
Amazon SageMaker HyperPod now supports data capture for inference workloads, automatically logging request/response payloads to S3. This new capability provides visibility into production generative AI model behavior for drift detection, troubleshooting, and dataset building, eliminating the need for custom logging pipelines.
feature