Provisions a new inference instance on Vultrs platform for deploying and running machine learning models.
The vultr-cli inference create command provisions a new inference instance on Vultr's platform, allowing you to deploy and run machine learning models for inference workloads.
$ vultr-cli inference create [flags]
# Full example
$ vultr-cli inference create --label="example-inference"
| Shorthand | Long Version | Description |
|---|---|---|
| -l | --label | label for the new inference subscription |
No comments yet.