Kategorie: Amazon AWS

AWS Compute Optimizer now supports unused NAT Gateway recommendations

Today, AWS announces that AWS Compute Optimizer now supports idle resource recommendations for NAT Gateways. With this new recommendation type, you will be able to identify NAT Gateways that are unused, resulting in cost savings. With the new unused NAT Gateway recommendation, you will be able to identify NAT Gateways that show no traffic activity over a 32-day analysis period. Compute Optimizer analyzes CloudWatch metrics including active connection count, incoming packets from source, and incoming packets from destination to validate if NAT Gateways are truly unused. To avoid recommending critical backup resources, Compute Optimizer also examines if the NAT Gateway resource is associated in any AWS Route Tables. You can view the total savings potential of these unused NAT Gateways and access detailed utilization metrics to verify unused conditions before taking action. This new feature is available in all AWS Regions where AWS Compute Optimizer is available except the AWS GovCloud (US) and the China Regions. To learn more about the new feature updates, please visit Compute Optimizer’s product page and user guide.
Quelle: aws.amazon.com

Amazon SageMaker HyperPod now supports custom Kubernetes labels and taints

Amazon SageMaker HyperPod now supports custom Kubernetes labels and taints, enabling customers to control pod scheduling and integrate seamlessly with existing Kubernetes infrastructure. Customers deploying AI workloads on HyperPod clusters orcehstrated with EKS need precise control over workload placement to prevent expensive GPU resources from being consumed by system pods and non-AI workloads, while ensuring compatibility with custom device plugins such as EFA and NVIDIA GPU operators. Previously, customers had to manually apply labels and taints using kubectl and reapply them after every node replacement, scaling, or patching operation, creating significant operational overhead. This capability allows you to configure labels and taints at the instance group level through the CreateCluster and UpdateCluster APIs, providing a managed approach to defining and maintaining scheduling policies across the entire node lifecycle. Using the new KubernetesConfig parameter, you can specify up to 50 labels and 50 taints per instance group. Labels enable resource organization and pod targeting through node selectors, while taints repel pods without matching tolerations to protect specialized nodes. For example, you can apply NoSchedule taints to GPU instance groups to ensure only AI training jobs with explicit tolerations consume high-cost compute resources, or add custom labels that enable device plugin pods to schedule correctly. HyperPod automatically applies these configurations during node creation and maintains them across replacement, scaling, and patching operations, eliminating manual intervention and reducing operational overhead. This feature is available in all AWS Regions where Amazon SageMaker HyperPod is available. To learn more about custom labels and taints, see the user guide.
Quelle: aws.amazon.com

SageMaker HyperPod now supports Managed tiered KV cache and intelligent routing

Amazon SageMaker HyperPod now supports Managed Tiered KV Cache and Intelligent Routing for large language model (LLM) inference, enabling customers to optimize inference performance for long-context prompts and multi-turn conversations. Customers deploying production LLM applications need fast response times while processing lengthy documents or maintaining conversation context, but traditional inference approaches require recalculating attention mechanisms for all previous tokens with each new token generation, creating computational overhead and escalating costs. Managed Tiered KV Cache addresses this challenge by intelligently caching and reusing computed values, while Intelligent Routing directs requests to optimal instances. These capabilities deliver up to 40% latency reduction, 25% throughput improvement, and 25% cost savings compared to baseline configurations. The Managed Tiered KV Cache feature uses a two-tier architecture combining local CPU memory (L1) with disaggregated cluster-wide storage (L2). AWS-native disaggregated tiered storage is the recommended backend, providing scalable terabyte-scale capacity and automatic tiering from CPU memory to local SSD for optimal memory and storage utilization. We also offer Redis as an alternative L2 cache option. The architecture enables efficient reuse of previously computed key-value pairs across requests. The newly introduced Intelligent Routing maximizes cache utilization through three configurable strategies: prefix-aware routing for common prompt patterns, KV-aware routing for maximum cache efficiency with real-time cache tracking, and round-robin for stateless workloads. These features work seamlessly together. Intelligent routing directs requests to instances with relevant cached data, reducing time to first token in document analysis and maintaining natural conversation flow in multi-turn dialogues. Built-in observability integration with Amazon Managed Grafana provides metrics for monitoring performance. You can enable these features through InferenceEndpointConfig or SageMaker JumpStart when deploying models via the HyperPod Inference Operator on EKS-orchestrated clusters. These features are available in all regions where SageMaker HyperPod is available. To learn more, see the user guide.
Quelle: aws.amazon.com

Amazon SageMaker AI now supports EAGLE speculative decoding

Amazon SageMaker AI now supports EAGLE (Extrapolation Algorithm for Greater Language-model Efficiency) speculative decoding to improve large language model inference throughput by up to 2.5x. This capability enables models to predict and validate multiple tokens simultaneously rather than one at a time, improving response times for AI applications. As customers deploy AI applications to production, they need capabilities to serve models with low latency and high throughput to deliver responsive user experiences. Data scientists and ML engineers lack efficient methods to accelerate token generation without sacrificing output quality or requiring complex model re-architecture, making it hard to meet performance expectations under real-world traffic. Teams spend significant time optimizing infrastructure rather than improving their AI applications. With EAGLE speculative decoding, SageMaker AI enables customers to accelerate inference throughput by allowing models to generate and verify multiple tokens in parallel rather than one at a time, maintaining the same output quality while dramatically increasing throughput. SageMaker AI automatically selects between EAGLE 2 and EAGLE 3 based on your model architecture, and provides built-in optimization jobs that use either curated datasets or your own application data to train specialized prediction heads. You can then deploy optimized models through your existing SageMaker AI inference workflow without infrastructure changes, enabling you to deliver faster AI applications with predictable performance. You can use EAGLE speculative decoding in the following AWS Regions: US East (N. Virginia), US West (Oregon), US East (Ohio), Asia Pacific (Tokyo), Europe (Ireland), Asia Pacific (Singapore), and Europe (Frankfurt) To learn more about EAGLE speculative decoding, visit AWS News Blog here, and SageMaker AI documentation here.
Quelle: aws.amazon.com

AWS Lambda adds support for Node.js 24

AWS Lambda now supports creating serverless applications using Node.js 24. Developers can use Node.js 24 as both a managed runtime and a container base image, and AWS will automatically apply updates to the managed runtime and base image as they become available. Node.js 24 is the latest long-term support release of Node.js and is expected to be supported for security and bug fixes until April 2028. With this release, Lambda has simplified the developer experience, focusing on the modern async/await programming pattern and no longer supports callback-based function handlers. You can use Node.js 24 with Lambda@Edge (in supported Regions), allowing you to customize low-latency content delivered through Amazon CloudFront. Powertools for AWS Lambda (TypeScript), a developer toolkit to implement serverless best practices and increase developer velocity, also supports Node.js 24. You can use the full range of AWS deployment tools, including the Lambda console, AWS CLI, AWS Serverless Application Model (AWS SAM), AWS CDK, and AWS CloudFormation to deploy and manage serverless applications written in Node.js 24. The Node.js 24 runtime is available in all Regions, including the AWS GovCloud (US) Regions and China Regions. For more information, including guidance on upgrading existing Lambda functions, see our blog post. For more information about AWS Lambda, visit our product page. 
Quelle: aws.amazon.com

Manage Amazon SageMaker HyperPod clusters with the new Amazon SageMaker AI MCP Server

The Amazon SageMaker AI MCP Server now supports tools that help you setup and manage HyperPod clusters. Amazon SageMaker HyperPod removes the undifferentiated heavy lifting involved in building generative AI models by quickly scaling model development tasks such as training, fine-tuning, or deployment across a cluster of AI accelerators. The SageMaker AI MCP Server now empowers AI coding assistants to provision and operate AI/ML clusters for model training and deployment. MCP servers in AWS provide a standard interface to enhance AI-assisted application development by equipping AI code assistants with real-time, contextual understanding of various AWS services. The SageMaker AI MCP server comes with tools that streamline end-to-end AI/ML cluster operations using the AI assistant of your choice—from initial setup through ongoing management. It enables AI agents to reliably setup HyperPod clusters orchestrated by Amazon EKS or Slurm complete with pre-requisites, powered by CloudFormation templates that optimize networking, storage, and compute resources. Clusters created via this MCP server are fully optimized for high-performance distributed training and inference workloads, leveraging best practice architectures to maximize throughput and minimize latency at scale. Additionally, it provides comprehensive tools for cluster and node management—including scaling operations, applying software patches, and performing various maintenance tasks. When used in conjunction with AWS API MCP Server, AWS Knowledge MCP Server, and Amazon EKS MCP Server you gain complete coverage for all SageMaker HyperPod APIs and you can effectively troubleshoot common issues, such as diagnosing why a cluster node became inaccessible. For cluster administrators, these tools streamline daily operations. For data scientists, they enable you to set up AI/ML clusters at scale without requiring infrastructure expertise, allowing you to focus on what matters most—training and deploying models. You can manage your AI/ML clusters through the SageMaker AI MCP server in all regions where SageMaker HyperPod is available. To get started, visit the AWS MCP Servers documentation.
Quelle: aws.amazon.com

Introducing AWS Network Firewall Proxy in preview

AWS introduces Network Firewall Proxy in public preview. You can use it to exert centralized controls against data exfiltration and malware injection. You can set up your Network Firewall Proxy in explicit mode in just a few clicks and filter the traffic going out from your applications and the response that these applications receive. Network Firewall Proxy enables customers to efficiently manage and secure web and inter-network traffic. It protects your organization against atempts to spoof the domain name or the server name index (SNI) and offers flexibility to set fine-grained access controls. You can use Network Firewall Proxy to restrict access from your applications to trusted domains or IP addresses, or block unintended response from external servers. You can also turn on TLS inspection and set granular filtering controls on HTTP header attributes. Your Network Firewall Proxy offers comprehensive logs for monitoring your applications. You can enable them and send to Amazon S3 and AWS CloudWatch for detailed analyses and audit. Try out AWS Network Firewall Proxy in your test environment today in US East (Ohio) region. Proxy is available for free during public preview. For more information check AWS Network Firewall proxy documentation.
Quelle: aws.amazon.com

Amazon OpenSearch Service introduces Agentic Search

Amazon OpenSearch Service launches Agentic Search, transforming how users interact with their data through intelligent, agent-driven search. Agentic Search introduces an intelligent agent-driven system that understands user intent, orchestrates the right set of tools, generates OpenSearch DSL (domain-specific language) queries, and provides transparent summaries of its decision-making process through a simple ‘agentic’ query clause and natural language search terms. Agentic Search automates OpenSearch query planning and execution, eliminating the need for complex search syntax. Users can ask questions in natural language like “Find red cars under $30,000″ or “Show last quarter’s sales trends.” The agent interprets intent, applies optimal search strategies, and delivers results while explaining its reasoning process. The feature provides two agent types: conversational agents, which handle complex interactions with the ability to store conversations in memory, and flow agents for efficient query processing. The built-in QueryPlanningTool uses large language models (LLMs) to create DSL queries, making search accessible regardless of technical expertise. Users can manage Agentic Search through APIs or OpenSearch Dashboards to configure and modify agents. Agentic Search’s advanced settings allow you to connect with external MCP servers and use custom search templates. Support for agentic search is available for OpenSearch Service version 3.3 and later in all AWS Commercial and AWS GovCloud (US) Regions where OpenSearch Service is available. See here for a full listing of our Regions. Build agents and run agentic searches using the new Agentic Search use case available in the AI Search Flows plugin. To learn more about Agentic Search, visit the OpenSearch technical documentation.
Quelle: aws.amazon.com

AWS Glue Data Quality now supports pre-processing queries

Today, AWS announces the general availability of preprocessing queries for AWS Glue Data Quality, enabling you to transform your data before running data quality checks through AWS Glue Data Catalog APIs. This feature allows you to create derived columns, filter data based on specific conditions, perform calculations, and validate relationships between columns directly within your data quality evaluation process.
Preprocessing queries provide enhanced flexibility for complex data quality scenarios that require data transformation before validation. You can create derived metrics like calculating total fees from tax and shipping columns, limiting number of columns that are considered for data quality recommendations or filter datasets to focus quality checks on specific data subsets. This capability eliminates the need for separate data pre-processing steps, streamlining your data quality workflows.
AWS Glue Data Quality preprocessing queries are available through AWS Glue Data Catalog APIs – start-data-quality-rule-recommendation-run and start-data-quality-ruleset-evaluation-run, in all commercial AWS Regions where AWS Glue Data Quality is available. To learn more about preprocessing queries, see the Glue Data Quality documentation. 
Quelle: aws.amazon.com

Amazon Quick Suite introduces scheduling for Quick Flows

Amazon Quick Flows now supports scheduling, enabling you to automate repetitive workflows without requiring manual intervention. You can now configure Quick Flows to run automatically at specified times or intervals, improving operational efficiency and ensuring critical tasks execute consistently. You can schedule Quick Flows to run daily, weekly, monthly, or on custom intervals. This capability is great for automating routine and administrative tasks such as generating recurring reports from dashboards, summarizing open items assigned to you in external services, or generating daily meeting briefings before you head out to work. You can schedule any flow you have access to—whether you created it or it was shared with you. To schedule a flow, click the scheduling icon and configure your desired date, time, and frequency. Scheduling in Quick Flows is available now in IAD, PDX, and DUB. There are no additional charges for using scheduled execution beyond standard Quick Flows usage. To learn more about configuring scheduled Quick Flows, please visit our documentation.
Quelle: aws.amazon.com