newsAWS Machine LearningTrust 88 · LabPublished 9d agoLive · 7d ago

Spreading the load: How Salesforce met Multi-AZ HA with SageMaker Inference Components

Learn how Salesforce used Amazon SageMaker AI Inference Component placement (the SchedulingConfig parameter) to distribute model copies across multiple Availability Zones, meeting their Multi-AZ high availability compliance requirements without sacrificing the cost efficiency of multi-model co-hosting.

Why these links exist

Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.

PossiblePossibly related (embedding) · 63%aws-samples/generative-ai-on-amazon-sagemaker →
PossiblePossibly related (embedding) · 61%aws/amazon-sagemaker-examples →
PossiblePossibly related (embedding) · 59%SuperCowPowers/workbench →
PossiblePossibly related (embedding) · 55%aws/sagemaker-python-sdk →
PossiblePossibly related (embedding) · 55%aws/sagemaker-example-notebooks-testing →

Covers

repoaws-samples/generative-ai-on-amazon-sagemaker repoaws/amazon-sagemaker-examples repoSuperCowPowers/workbench repoaws/sagemaker-python-sdk repoaws/sagemaker-example-notebooks-testing

Related across the graph

repoaws-samples/generative-ai-on-amazon-sagemaker repoaws/sagemaker-example-notebooks-testing repoaws/sagemaker-python-sdk repoaws/amazon-sagemaker-examples repoSuperCowPowers/workbench