AITOPAI热报
ProductsOfficialSelected

Salesforce Uses SageMaker for Multi-AZ HA

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

官方一手AWS Machine Learning Blog@Rielah De Jesus
Blog/Media
Read the original
Why we picked it

Salesforce's solution provides a blueprint for enterprises in ASEAN needing high availability without increased costs on AWS.

Salesforce implemented Amazon SageMaker AI Inference Component placement to distribute model copies across multiple Availability Zones. This solution met their Multi-AZ high availability compliance requirements. The approach maintained cost efficiency through multi-model co-hosting. The SchedulingConfig parameter enabled this distributed deployment.

Image · AWS Machine Learning Blog
Original · AWS Machine Learning Blog

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.

#Salesforce#Amazon SageMaker#Inference Components#Multi-AZ#high availability

Keep reading

Recent stories with the same tag or section
ProductsBuildersSelected08:13
Salesforce's Moirai 2.0 powers zero-shot forecasting in Data 360

Foundation models are moving beyond text into tabular time-series, and Salesforce embedding one directly into its analytics stack signals that zero-shot forecasting is becoming a default enterprise feature rather than a data-science project. Analysts and BI teams on Tableau or Data 360 can trial it without any modelling work, and competitors like Google BigQuery and AWS Forecast now face a ready-built rival. Plans to put Moirai inside root-cause-analysis agents point to where forecasting products are heading next.

#Moirai 2.0#Salesforce#Data 360#Tableau
官方账号Salesforce AI Research@SFResearchSource
PapersBuildersSelected00:19
SF Research Launches EvoHarnessBench for Evolving Agent Harnesses

Most agent benchmarks score a fixed toolset, so they miss the stability-versus-plasticity problem that surfaces in production, where harnesses keep growing and stored artifacts go stale. Teams building or selecting agent frameworks can run the benchmark via the live demo or plug in their own agent to see where their setup fails as capabilities expand. It suits engineering leads evaluating agent reliability over time rather than one-shot benchmark numbers.

#EvoHarnessBench#SF Research#agents#benchmarks
官方账号Salesforce AI Research@SFResearchSource