Guides¶
Read how-to guides to explore the key features of BentoCloud.
Create a Bento Deployment on BentoCloud.
Customize the configurations of your Deployment, such as scaling replicas, environment variables, and instance types.
Manage the Deployment lifecycle using the BentoML CLI or API.
Run inference with Deployments.
Configure concurrency and autoscaling to achieve optimal resource utilization and cost-efficiency for your AI workloads.
Create and use API tokens to log in to BentoCloud or access protected Deployments.
Store sensitive data like credentials in pre-defined secret templates or create custom secrets.
Implement custom access control for BentoCloud users.
Run batch inference jobs with BentoML and BentoCloud.
The BentoCloud BYOC deployment helps you run AI applications in your own environment in a secure and cost-effective way.