Salesforce Achieves Multi-AZ HA with SageMaker Inference Components
AWS ML Blog · rss · 2026-08-29
This post details how Salesforce used new capabilities in Amazon SageMaker Inference Components (IC) to achieve High Availability (HA) across multiple Availability Zones. While ICs reduced infrastructure costs by 8x through GPU sharing, the default placement didn't guarantee cross-AZ balance. Salesforce utilized the SchedulingConfig parameter, featuring AvailabilityZoneBalance and PlacementStrategy: SPREAD, to ensure model copies are evenly distributed across AZs and instances, meeting 2-AZ compliance and mitigating single points of failure.
More from Infra
- Google Cloud launches Fault Injection Testing to automate cloud resilience checks — rseroter · 2026-08-29
- Opinion: Local Models Enable a New Class of Software with Embedded Intelligence — carsonfarmer · 2026-08-29
- TensorSharp hits 2x llama.cpp decode throughput on GLM-5.3-Flash — fuzhongkai · 2026-08-29
- Designing AI Event Routing: How System Architecture Mirrors Org Charts — zakelfassi · 2026-08-29
- OpenAI's 'Jalapeño' Chip Reportedly Beats Nvidia Blackwell — dylan522p · 2026-08-29
- Cerebras CEO explains why wafer-scale architecture is 2,500X faster than GPU for inference — rohanpaul_ai · 2026-08-29