Amazon SageMaker HyperPod Inference now supports NVIDIA Dynamo for disaggregated and multi-node inference
Amazon SageMaker HyperPod Inference now supports NVIDIA Dynamo for distributed, multi-node model serving. This allows users to run large models across multiple nodes and scale prefill and decode stages independently.
Also shipped Nov 17, 2026AWS in November 2026 →
[Launched] Generally Available: Intel and AMD v6 with temp disk for Azure Database for PostgreSQL
Microsoft announced general availability of Intel and AMD v6 compute options with local temporary disk for Azure Database for PostgreSQL Flexible Server.
BigQuery AI.IF and AI.CLASSIFY optimized mode is generally available
Google Cloud made optimized mode generally available for BigQuery managed AI functions AI.IF and AI.CLASSIFY to lower query latency and token usage.
AlphaGenome available without an allowlist
Google Cloud removed project allowlisting requirements for AlphaGenome models alphagenome-003 and alphagenome-004 in Model Garden.
[Launched] Generally Available: Intel and AMD v5 diskless tier for Azure Database for PostgreSQL
Microsoft announced the general availability of Intel and AMD v5 diskless compute options for Azure Database for PostgreSQL Flexible Server.
BigQuery REST API adds dataset replication and disaster recovery controls
Google Cloud made cross-region dataset replication and disaster recovery failover management generally available via the BigQuery REST API.
[Launched] Generally Available: Cobalt 200 compute for Azure Database for PostgreSQL
Microsoft announced general availability of ARM64-based Cobalt 200 compute options for Azure Database for PostgreSQL Flexible Server.
More from Amazon SageMakerEvery Amazon SageMaker release →
Amazon SageMaker now supports AI data preparation capabilities to build high-quality datasets for model development
Amazon SageMaker introduced AI data preparation features, including synthetic data generation, automated multi-task labeling, human review queues, and quality evaluation.
Amazon SageMaker HyperPod now supports cluster operations for tracking scaling and on-demand Deep Health Check requests
Amazon SageMaker HyperPod introduced cluster operations to provide tracking and diagnostic events for scaling and on-demand deep health check requests.
Amazon SageMaker AI now supports cross-Region inference routing
Amazon SageMaker AI added cross-Region inference routing to route endpoint traffic to healthy destinations in other AWS Regions and accounts during capacity shortages.
Amazon SageMaker HyperPod now supports higher pod density on EKS-orchestrated clusters
Amazon SageMaker HyperPod now supports higher pod density per node on EKS-orchestrated clusters to increase GPU, CPU, and memory utilization across workloads.
Amazon SageMaker AI now supports KV cache-aware routing for real-time inference endpoints
Amazon SageMaker AI now supports KV cache-aware routing for real-time inference endpoints. Working with engines like vLLM, SageMaker routes requests to endpoint instances holding matching prompt caches, reducing time to first token for workloads with shared system prompts or chat history.
Amazon SageMaker AI now detects rising response times, idle GPUs, and missed optimizations on your generative AI inference endpoints
Amazon SageMaker AI introduced default monitoring on generative AI inference endpoints to automatically detect latency spikes, idle GPUs, and configuration optimization opportunities.
Amazon SageMaker JumpStart now offers a model leaderboard to compare models on quality, speed, and cost
Amazon SageMaker JumpStart now includes a model leaderboard to compare foundation models based on reasoning benchmarks, latency, throughput, and deployment costs.
AWS Glue Data Catalog introduces data quality monitoring for catalogs and databases
AWS Glue Data Catalog now supports automated data quality monitoring, allowing users to profile and evaluate tables at scale using built-in statistics or custom DQDL rules.