Serving and Scaling Models
Deploying models for online and batch prediction on Vertex AI and GKE, with scaling, latency and cost trade-offs.
GCP-363 12 lessons planned ▶ Video lessons coming soon
Offered by HSM University · Google Cloud Certification Prep
Course content
- 1Online and batch predictionComing
- 2Vertex AI endpointsComing
- 3Autoscaling and machine selectionComing
- 4Serving on GKE and Cloud RunComing
- 5Optimizing models for inferenceComing
- 6A/B testing and traffic splittingComing
- 7Serving generative AI modelsComing
- 8Securing prediction endpointsComing
- 9Latency and throughput tuningComing
- 10Edge and on-device deploymentComing
- 11Serving cost managementComing
- 12Lab walkthrough: deploying a model endpointComing
Requirements
Recommended background. You can start any course at any time.
Description
Deploying models for online and batch prediction on Vertex AI and GKE, with scaling, latency and cost trade-offs.