Deploy ML models for inference at high performance & low cost
summary
Shows how to use Amazon SageMaker inference features to deploy machine-learning models into production with a focus on achieving high throughput and low cost while minimizing operational overhead. Covers SageMaker’s managed deployment capabilities for scaling inference at production scale.
AI-written summary · about
chapters (13)
- 0:00Start
- 4:21Deploy model to serve inference
- 5:21Model deployment - How do you strike the right balance?
- 6:33Deployment complexity
- 9:57SageMaker for best inference performance
- 12:10Infrastructure Cost
- 13:29Deploy on SageMaker Serverless Inference
- 33:34TV Monitoring Preprocessing
- 34:41Video segmentation automation
- 36:04Architecture (Inferencing/MME)
- 36:54Monitoring and optimization
- 37:18Empowering Data Scientists
- 39:22Summary
related talks
45mDeploying ML Models to Production with Amazon SageMaker
19mUsing Amazon SageMaker to develop and deploy ML models
33mBuild, train, and deploy ML models using Amazon SageMaker
34mBuild, train and deploy Machine Learning models with Amazon SageMaker
27mScaling ML to the next level: Hosting thousands of models on SageMaker
43mDesigning and Building Complex Machine Learning Projects
31mBuild, train, and deploy ML models using Amazon SageMaker
01h 00mHigh-performance & cost-effective model deployment with Amazon SageMaker