Interface IEndpointInstanceProductionVariant.Jsii$Default
- All Superinterfaces:
IEndpointInstanceProductionVariant
,software.amazon.jsii.JsiiSerializable
- All Known Implementing Classes:
IEndpointInstanceProductionVariant.Jsii$Proxy
- Enclosing interface:
IEndpointInstanceProductionVariant
@Internal
public static interface IEndpointInstanceProductionVariant.Jsii$Default
extends IEndpointInstanceProductionVariant
Internal default implementation for
IEndpointInstanceProductionVariant
.-
Nested Class Summary
Nested classes/interfaces inherited from interface software.amazon.awscdk.services.sagemaker.alpha.IEndpointInstanceProductionVariant
IEndpointInstanceProductionVariant.Jsii$Default, IEndpointInstanceProductionVariant.Jsii$Proxy
-
Method Summary
Modifier and TypeMethodDescriptiondefault ScalableInstanceCount
autoScaleInstanceCount
(EnableScalingProps scalingProps) (experimental) Enable autoscaling for SageMaker Endpoint production variant.default String
(experimental) The name of the production variant.default Metric
metric
(String namespace, String metricName, MetricOptions props) (experimental) Return the given named metric for Endpoint.default Metric
(experimental) Metric for CPU utilization.default Metric
(experimental) Metric for disk utilization.default Metric
(experimental) Metric for GPU memory utilization.default Metric
(experimental) Metric for GPU utilization.default Metric
metricInvocationResponseCode
(InvocationHttpResponseCode responseCode, MetricOptions props) (experimental) Metric for the number of invocations by HTTP response code.default Metric
metricInvocations
(MetricOptions props) (experimental) Metric for the number of invocations.default Metric
(experimental) Metric for the number of invocations per instance.default Metric
(experimental) Metric for memory utilization.default Metric
metricModelLatency
(MetricOptions props) (experimental) Metric for model latency.default Metric
(experimental) Metric for overhead latency.Methods inherited from interface software.amazon.awscdk.services.sagemaker.alpha.IEndpointInstanceProductionVariant
metric, metricCpuUtilization, metricDiskUtilization, metricGpuMemoryUtilization, metricGpuUtilization, metricInvocationResponseCode, metricInvocations, metricInvocationsPerInstance, metricMemoryUtilization, metricModelLatency, metricOverheadLatency
Methods inherited from interface software.amazon.jsii.JsiiSerializable
$jsii$toJson
-
Method Details
-
getVariantName
(experimental) The name of the production variant.- Specified by:
getVariantName
in interfaceIEndpointInstanceProductionVariant
-
autoScaleInstanceCount
@Stability(Experimental) @NotNull default ScalableInstanceCount autoScaleInstanceCount(@NotNull EnableScalingProps scalingProps) (experimental) Enable autoscaling for SageMaker Endpoint production variant.- Specified by:
autoScaleInstanceCount
in interfaceIEndpointInstanceProductionVariant
- Parameters:
scalingProps
- EnableScalingProps. This parameter is required.
-
metric
@Stability(Experimental) @NotNull default Metric metric(@NotNull String namespace, @NotNull String metricName, @Nullable MetricOptions props) (experimental) Return the given named metric for Endpoint.Default: - sum over 5 minutes
- Specified by:
metric
in interfaceIEndpointInstanceProductionVariant
- Parameters:
namespace
- This parameter is required.metricName
- This parameter is required.props
-
-
metricCpuUtilization
@Stability(Experimental) @NotNull default Metric metricCpuUtilization(@Nullable MetricOptions props) (experimental) Metric for CPU utilization.Default: - average over 5 minutes
- Specified by:
metricCpuUtilization
in interfaceIEndpointInstanceProductionVariant
- Parameters:
props
-
-
metricDiskUtilization
@Stability(Experimental) @NotNull default Metric metricDiskUtilization(@Nullable MetricOptions props) (experimental) Metric for disk utilization.Default: - average over 5 minutes
- Specified by:
metricDiskUtilization
in interfaceIEndpointInstanceProductionVariant
- Parameters:
props
-
-
metricGpuMemoryUtilization
@Stability(Experimental) @NotNull default Metric metricGpuMemoryUtilization(@Nullable MetricOptions props) (experimental) Metric for GPU memory utilization.Default: - average over 5 minutes
- Specified by:
metricGpuMemoryUtilization
in interfaceIEndpointInstanceProductionVariant
- Parameters:
props
-
-
metricGpuUtilization
@Stability(Experimental) @NotNull default Metric metricGpuUtilization(@Nullable MetricOptions props) (experimental) Metric for GPU utilization.Default: - average over 5 minutes
- Specified by:
metricGpuUtilization
in interfaceIEndpointInstanceProductionVariant
- Parameters:
props
-
-
metricInvocationResponseCode
@Stability(Experimental) @NotNull default Metric metricInvocationResponseCode(@NotNull InvocationHttpResponseCode responseCode, @Nullable MetricOptions props) (experimental) Metric for the number of invocations by HTTP response code.Default: - sum over 5 minutes
- Specified by:
metricInvocationResponseCode
in interfaceIEndpointInstanceProductionVariant
- Parameters:
responseCode
- This parameter is required.props
-
-
metricInvocations
(experimental) Metric for the number of invocations.Default: - sum over 5 minutes
- Specified by:
metricInvocations
in interfaceIEndpointInstanceProductionVariant
- Parameters:
props
-
-
metricInvocationsPerInstance
@Stability(Experimental) @NotNull default Metric metricInvocationsPerInstance(@Nullable MetricOptions props) (experimental) Metric for the number of invocations per instance.Default: - sum over 5 minutes
- Specified by:
metricInvocationsPerInstance
in interfaceIEndpointInstanceProductionVariant
- Parameters:
props
-
-
metricMemoryUtilization
@Stability(Experimental) @NotNull default Metric metricMemoryUtilization(@Nullable MetricOptions props) (experimental) Metric for memory utilization.Default: - average over 5 minutes
- Specified by:
metricMemoryUtilization
in interfaceIEndpointInstanceProductionVariant
- Parameters:
props
-
-
metricModelLatency
(experimental) Metric for model latency.Default: - average over 5 minutes
- Specified by:
metricModelLatency
in interfaceIEndpointInstanceProductionVariant
- Parameters:
props
-
-
metricOverheadLatency
@Stability(Experimental) @NotNull default Metric metricOverheadLatency(@Nullable MetricOptions props) (experimental) Metric for overhead latency.Default: - average over 5 minutes
- Specified by:
metricOverheadLatency
in interfaceIEndpointInstanceProductionVariant
- Parameters:
props
-
-