AWS
Amazon Web Services releases and Terraform AWS provider.
- AWS What's New aiawsengineer ·
SageMaker HyperPod Slurm clusters now support minimum capacity
Amazon SageMaker HyperPod for Slurm clusters now supports specifying minimum instance requirements (MinCount) with continuous provisioning. This allows users to guarantee a baseline number of nodes before training jobs start, improving reliability for distributed workloads and meeting SLA targets. Engineers and architects running large-scale AI/ML training jobs on SageMaker HyperPod will benefit from this enhanced control over cluster availability.
feature - AWS What's New aiawsengineer ·
Amazon Aurora MySQL integrates with Kiro Powers for AI development assistance
Amazon Aurora MySQL now integrates with Kiro Powers, a repository of AI agent tools, enabling developers to build applications faster using natural language commands for both data and control plane operations. This integration provides instant expertise for Aurora MySQL operations and schema design, abstracting complex syntax and offering dynamic, task-specific guidance. The feature is available via one-click installation and affects developers building or managing Aurora MySQL-backed applications.
feature - AWS What's New aiinfraawsengineer ·
Amazon EC2 X8i instances expand to more AWS regions
Amazon EC2 X8i instances, powered by custom Intel Xeon 6 processors, are now available in Asia Pacific (Singapore), Asia Pacific (Sydney), and AWS GovCloud (US-West) regions. These SAP-certified instances offer significantly higher performance, memory capacity, and bandwidth compared to X2i instances, benefiting memory-intensive workloads like SAP HANA, large databases, and AI inference. The expanded availability allows more customers to leverage these powerful compute options.
feature - AWS What's New aiawsengineer ·
Amazon SageMaker Unified Studio Enhances Domain Management
Amazon SageMaker Unified Studio now offers expanded domain management for both Identity Center and IAM-based domains, allowing administrators to manage projects, workforce identity, and networking properties outside the AWS console. This unification simplifies administration for teams working with diverse SageMaker environments, improving consistency and enabling cross-account data sharing.
feature - AWS What's New aiawsengineermedia ·
SageMaker Inference now supports OpenAI-compatible APIs
Amazon SageMaker Inference now supports OpenAI-compatible APIs, enabling direct integration with tools like OpenAI SDK, LangChain, and Strands Agents by simply changing an endpoint URL. This new feature removes the need for custom integration code or SDK wrappers, allowing users to leverage existing SDK calls and framework integrations with SageMaker endpoints while retaining control over GPU instances, VPC data, and auto-scaling. The update is available in multiple AWS regions.
feature - 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 - Google Cloud release notes aisecurityawsgcpgapreviewsecurity-advisoryengineer ·
Google Cloud updates: BigQuery, Cloud Workstations, COS, Gemini
Google Cloud's latest updates include a billing label change for BigQuery Data Transfer Service, enhanced workstation authorization URLs in Cloud Workstations, and an LTS refresh for Container Optimized OS with numerous security fixes. Gemini Enterprise sees GA for its Box data store integration and an Early Access program for the Gemini Distillation Service is launching. These changes affect BigQuery users, Cloud Workstations administrators, COS users, and those leveraging Gemini Enterprise.
patch security feature announcement - OpenAI News aiawsengineer ·
OpenAI Models, Codex, and Managed Agents Available on AWS
OpenAI's GPT models, Codex, and Managed Agents are now accessible on AWS. This integration allows enterprises to develop and deploy AI applications securely within their existing AWS infrastructure.
announcement - Databricks Java SDK Releases sdkaiawsazuregcpdatabricksengineer ·
Databricks SDK Java v0.105.0: AI agent detection, breaking API changes
Databricks SDK Java version 0.105.0 introduces automatic detection of AI coding agents in user-agent strings and updates the logging abstraction. This release also includes several breaking changes to API method paths, requiring users to update their integrations. The SDK now better supports various AI environments and simplifies logging configurations.
breaking feature patch