Outline some scenarios for choosing serverless inference versus real-time inference endpoints in AWS SageMaker
MLE Q&A #02. Serverless vs real-time inference in AWS SageMaker
Today we're discussing deployment options for machine learning models in SageMaker.
Could you outline some scenarios for choosing serverless inference versus real-time inference endpoints?
The traffic patterns and latency requirements are the main factors when deciding between serverless and real-time inference.
Keep reading with a 7-day free trial
Subscribe to The Data Interview to keep reading this post and get 7 days of free access to the full post archives.