Choosing a SageMaker AI inference option

MLA-C01 · Deployment and Orchestration of ML Workflows · Updated

Compare real-time, serverless, asynchronous and batch inference in SageMaker AI, plus multi-model endpoints, autoscaling and edge deployment.

This lesson is part of full MLA-C01 access

The first 2 MLA-C01 lessons are free. Full access opens every lesson with its practice questions, and the exam-style MLA-C01 question bank.

In this lesson
  • The four options
  • Cost and scale features
  • Deployment safety
  • Edge and optimization
  • Bringing your own container
  • Security basics for endpoints
  • Exam traps
  • Practice questions

Get full access Try the free practice exam Log in

MLA-C01 course outline

All 8 lessons · Course overview
  1. Data storage, ingestion and Feature StoreData Preparation for Machine Learning Free
  2. Cleaning data, imbalance and biasData Preparation for Machine Learning Free
  3. Choosing SageMaker AI algorithms and approachesML Model Development Full access
  4. Training, tuning and overfitting in SageMaker AIML Model Development Full access
  5. Choosing a SageMaker AI inference optionDeployment and Orchestration of ML Workflows Full access
  6. SageMaker AI Pipelines, Model Registry and CI/CDDeployment and Orchestration of ML Workflows Full access
  7. Monitoring models, drift and costML Solution Monitoring, Maintenance, and Security Full access
  8. Securing ML workloads on AWSML Solution Monitoring, Maintenance, and Security Full access