@aws-cdk_aws-sagemaker-alpha.IEndpointInstanceProductionVariant

interface IEndpointInstanceProductionVariant ๐Ÿ”น

LanguageType name
.NETAmazon.CDK.AWS.Sagemaker.Alpha.IEndpointInstanceProductionVariant
Gogithub.com/aws/aws-cdk-go/awscdksagemakeralpha/v2#IEndpointInstanceProductionVariant
Javasoftware.amazon.awscdk.services.sagemaker.alpha.IEndpointInstanceProductionVariant
Pythonaws_cdk.aws_sagemaker_alpha.IEndpointInstanceProductionVariant
TypeScript (source)@aws-cdk/aws-sagemaker-alpha ยป IEndpointInstanceProductionVariant

Obtainable from Endpoint.findInstanceProductionVariant()

Represents an instance production variant that has been associated with an endpoint.

Properties

NameTypeDescription
variantName๐Ÿ”นstringThe name of the production variant.

variantName๐Ÿ”น

Type: string

The name of the production variant.

Methods

NameDescription
autoScaleInstanceCount(scalingProps)๐Ÿ”นEnable autoscaling for SageMaker Endpoint production variant.
metric(namespace, metricName, props?)๐Ÿ”นReturn the given named metric for Endpoint.
metricCpuUtilization(props?)๐Ÿ”นMetric for CPU utilization.
metricDiskUtilization(props?)๐Ÿ”นMetric for disk utilization.
metricGpuMemoryUtilization(props?)๐Ÿ”นMetric for GPU memory utilization.
metricGpuUtilization(props?)๐Ÿ”นMetric for GPU utilization.
metricInvocationResponseCode(responseCode, props?)๐Ÿ”นMetric for the number of invocations by HTTP response code.
metricInvocations(props?)๐Ÿ”นMetric for the number of invocations.
metricInvocationsPerInstance(props?)๐Ÿ”นMetric for the number of invocations per instance.
metricMemoryUtilization(props?)๐Ÿ”นMetric for memory utilization.
metricModelLatency(props?)๐Ÿ”นMetric for model latency.
metricOverheadLatency(props?)๐Ÿ”นMetric for overhead latency.

autoScaleInstanceCount(scalingProps)๐Ÿ”น

public autoScaleInstanceCount(scalingProps: EnableScalingProps): ScalableInstanceCount

Parameters

  • scalingProps EnableScalingProps โ€” EnableScalingProps.

Returns

  • ScalableInstanceCount

Enable autoscaling for SageMaker Endpoint production variant.


metric(namespace, metricName, props?)๐Ÿ”น

public metric(namespace: string, metricName: string, props?: MetricOptions): Metric

Parameters

  • namespace string
  • metricName string
  • props MetricOptions

Returns

  • Metric

Return the given named metric for Endpoint.


metricCpuUtilization(props?)๐Ÿ”น

public metricCpuUtilization(props?: MetricOptions): Metric

Parameters

  • props MetricOptions

Returns

  • Metric

Metric for CPU utilization.


metricDiskUtilization(props?)๐Ÿ”น

public metricDiskUtilization(props?: MetricOptions): Metric

Parameters

  • props MetricOptions

Returns

  • Metric

Metric for disk utilization.


metricGpuMemoryUtilization(props?)๐Ÿ”น

public metricGpuMemoryUtilization(props?: MetricOptions): Metric

Parameters

  • props MetricOptions

Returns

  • Metric

Metric for GPU memory utilization.


metricGpuUtilization(props?)๐Ÿ”น

public metricGpuUtilization(props?: MetricOptions): Metric

Parameters

  • props MetricOptions

Returns

  • Metric

Metric for GPU utilization.


metricInvocationResponseCode(responseCode, props?)๐Ÿ”น

public metricInvocationResponseCode(responseCode: InvocationHttpResponseCode, props?: MetricOptions): Metric

Parameters

  • responseCode InvocationHttpResponseCode
  • props MetricOptions

Returns

  • Metric

Metric for the number of invocations by HTTP response code.


metricInvocations(props?)๐Ÿ”น

public metricInvocations(props?: MetricOptions): Metric

Parameters

  • props MetricOptions

Returns

  • Metric

Metric for the number of invocations.


metricInvocationsPerInstance(props?)๐Ÿ”น

public metricInvocationsPerInstance(props?: MetricOptions): Metric

Parameters

  • props MetricOptions

Returns

  • Metric

Metric for the number of invocations per instance.


metricMemoryUtilization(props?)๐Ÿ”น

public metricMemoryUtilization(props?: MetricOptions): Metric

Parameters

  • props MetricOptions

Returns

  • Metric

Metric for memory utilization.


metricModelLatency(props?)๐Ÿ”น

public metricModelLatency(props?: MetricOptions): Metric

Parameters

  • props MetricOptions

Returns

  • Metric

Metric for model latency.


metricOverheadLatency(props?)๐Ÿ”น

public metricOverheadLatency(props?: MetricOptions): Metric

Parameters

  • props MetricOptions

Returns

  • Metric

Metric for overhead latency.