Deployment

Read how-to guides to create and manage your Deployments on BentoCloud.

Create Deployments

Create a Bento Deployment on BentoCloud.

Create Deployments

Configure Deployments

Customize the configurations of your Deployment, such as scaling replicas, environment variables, and instance types.

Configure Deployments

Manage Deployments

Manage the Deployment lifecycle using the BentoML CLI or API.

Manage Deployments

Call Deployment endpoints

Run inference with Deployments.

Call Deployment endpoints

Create canary Deployments

Gradually roll out a new application version to a subset of users and monitor performance before wider release.

Create canary Deployments

Sandboxes

Run AI-generated code in an isolated, scalable and secure environment.

Sandboxes

Batch inference jobs

Run batch inference jobs with BentoML and BentoCloud.

Batch inference jobs

Build CI/CD pipelines

Build CI/CD pipelines to automate AI deployments on BentoCloud.

Build CI/CD pipelines