2025-11-26

11/26/2025, 12:00:00 AM ~ 11/27/2025, 12:00:00 AM (UTC) Recent Announcements 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....

November 26, 2025

2025-11-18

11/18/2025, 12:00:00 AM ~ 11/19/2025, 12:00:00 AM (UTC) Recent Announcements Amazon EC2 P6-B300 instances with NVIDIA Blackwell Ultra GPUs are now available Today, AWS announces the general availability of Amazon Elastic Compute Cloud (Amazon EC2) P6-B300 instances, accelerated by NVIDIA Blackwell Ultra B300 GPUs. Amazon EC2 P6-B300 instances provide 8x NVIDIA Blackwell Ultra GPUs with 2.1 TB high bandwidth GPU memory, 6.4 Tbps EFA networking, 300 Gbps dedicated ENA throughput, and 4 TB of system memory....

November 18, 2025

2025-11-12

11/12/2025, 12:00:00 AM ~ 11/13/2025, 12:00:00 AM (UTC) Recent Announcements Application loadbalancer support client credential flow with JWT verification Amazon Web Services (AWS) announces JWT Verification for Application Load Balancer (ALB), enabling secure machine-to-machine (M2M) and service-to-service (S2S) communications. This feature allows ALB to verify JSON Web Tokens (JWTs) included in request headers, validating token signatures, expiration times, and claims without requiring modifications to application code.\n By offloading OAuth 2.0 token validation to ALB, customers can significantly reduce architectural complexity and streamline their security implementation....

November 12, 2025

2025-11-11

11/11/2025, 12:00:00 AM ~ 11/12/2025, 12:00:00 AM (UTC) Recent Announcements AWS Parallel Computing Service (PCS) now supports Slurm CLI Filter plugins AWS Parallel Computing Service (PCS) now supports Slurm CLI Filter plugins, enabling you to extend and modify how Slurm schedules and processes your high performance computing (HPC) workloads without modifying Slurm directly.\n Using CLI Filter plugins, you can now define custom policies for job submission to your clusters. For example, you can define policies that verify certain flags or fields of jobs when users submit them, automatically reject jobs submitted without specific attributes, or even modify job parameters....

November 11, 2025

2025-11-10

11/10/2025, 12:00:00 AM ~ 11/11/2025, 12:00:00 AM (UTC) Recent Announcements AWS Control Tower supports automatic enrollment of accounts AWS Control Tower customers can now simply move their accounts to an Organizational Unit (OU) to enroll them under AWS Control Tower governance. This feature helps customers maintain consistency across their AWS environment and simplifies the account creation and enrollment processes. When enrolled, member accounts receive best practice configurations, controls, and baseline resources required for AWS Control Tower governance....

November 10, 2025