Artificial Intelligence1 min read

Introducing Amazon SageMaker HyperPod Global Inference Gateway: One endpoint across Regions and clusters

By · Published by Everything Blog

In short

The architecture functions as a secondary tier above existing cluster-level gateways, transporting traffic over the AWS backbone to prevent compute bottlenecks. Teams can bypass custom DNS setups and load balancers by publishing clusters via an API call that automates controller, endpoint, and certificate management. Gaming firm Bagelcode has already tested the configuration, verifying successful cross-Region traffic routing and automated failover across two separate AWS Regions.

Key points

  • Infrastructure teams can balance artificial intelligence inference traffic across multipl…: Infrastructure teams can balance artificial intelligence inference traffic across multiple clusters and Regions using a single endpoint.
  • Automated failover mechanisms ensure continuous availability by redirecting model request…: Automated failover mechanisms ensure continuous availability by redirecting model requests away from saturated or failing clusters.
  • Clusters remain isolated and private until administrators publish them to the global gate…: Clusters remain isolated and private until administrators publish them to the global gateway using standard configuration blocks.

Sources checked by our analysis pipeline: 1

Artificial Intelligence

Introducing Amazon SageMaker HyperPod Global Inference Gateway: One endpoint across Regions and clusters

During a traffic peak, a request can sit in a queue on a saturated HyperPod cluster while GPUs on another cluster, sometimes in another AWS Region, sit idle. You have already paid for that capacity, but your requests can’t reach it.

In Introducing Amazon SageMaker HyperPod Inference Gateway, we showed how the Inference Gateway gives each Amazon SageMaker HyperPod cluster a single, GPU-aware endpoint. It reads real-time signals such as key-value (KV) cache utilization and queue depth to place every request on the best-suited pod. That solves routing inside one cluster, but not across clusters.

Today, SageMaker HyperPod introduces the Global Inference Gateway. It is one SageMaker-managed gateway that routes across every cluster you register, in one Region or across Regions. The gateway picks the cluster and carries the request over the AWS backbone, with automatic failover and authentication through AWS Signature Version 4 (SigV4) and AWS Identity and Access Management (IAM). Inside each cluster, the Inference Gateway keeps picking the pod, unchanged. The Global…

Artificial Intelligence