Builder

class Builder

Properties

Link copied to clipboard

Defines the cost per hour for the instance.

Link copied to clipboard

Defines the cost per inference for the instance .

Link copied to clipboard

The expected CPU utilization at maximum invocations per minute for the instance.

Link copied to clipboard

The expected maximum number of requests per minute for the instance.

Link copied to clipboard

The expected memory utilization at maximum invocations per minute for the instance.

Link copied to clipboard

The expected model latency at maximum invocation per minute for the instance.

Link copied to clipboard

The time it takes to launch new compute resources for a serverless endpoint. The time can vary depending on the model size, how long it takes to download the model, and the start-up time of the container.