Interface IEndpointInstanceProductionVariant
- All Superinterfaces:
software.amazon.jsii.JsiiSerializable
- All Known Subinterfaces:
IEndpointInstanceProductionVariant.Jsii$Default
- All Known Implementing Classes:
IEndpointInstanceProductionVariant.Jsii$Proxy
-
Nested Class Summary
Nested ClassesModifier and TypeInterfaceDescriptionstatic interface
Internal default implementation forIEndpointInstanceProductionVariant
.static final class
A proxy class which represents a concrete javascript instance of this type. -
Method Summary
Modifier and TypeMethodDescriptionautoScaleInstanceCount
(EnableScalingProps scalingProps) (experimental) Enable autoscaling for SageMaker Endpoint production variant.(experimental) The name of the production variant.(experimental) Return the given named metric for Endpoint.metric
(String namespace, String metricName, MetricOptions props) (experimental) Return the given named metric for Endpoint.(experimental) Metric for CPU utilization.(experimental) Metric for CPU utilization.(experimental) Metric for disk utilization.(experimental) Metric for disk utilization.(experimental) Metric for GPU memory utilization.(experimental) Metric for GPU memory utilization.(experimental) Metric for GPU utilization.(experimental) Metric for GPU utilization.metricInvocationResponseCode
(InvocationHttpResponseCode responseCode) (experimental) Metric for the number of invocations by HTTP response code.metricInvocationResponseCode
(InvocationHttpResponseCode responseCode, MetricOptions props) (experimental) Metric for the number of invocations by HTTP response code.(experimental) Metric for the number of invocations.metricInvocations
(MetricOptions props) (experimental) Metric for the number of invocations.(experimental) Metric for the number of invocations per instance.(experimental) Metric for the number of invocations per instance.(experimental) Metric for memory utilization.(experimental) Metric for memory utilization.(experimental) Metric for model latency.metricModelLatency
(MetricOptions props) (experimental) Metric for model latency.(experimental) Metric for overhead latency.(experimental) Metric for overhead latency.Methods inherited from interface software.amazon.jsii.JsiiSerializable
$jsii$toJson
-
Method Details
-
getVariantName
(experimental) The name of the production variant. -
autoScaleInstanceCount
@Stability(Experimental) @NotNull ScalableInstanceCount autoScaleInstanceCount(@NotNull EnableScalingProps scalingProps) (experimental) Enable autoscaling for SageMaker Endpoint production variant.- Parameters:
scalingProps
- EnableScalingProps. This parameter is required.
-
metric
@Stability(Experimental) @NotNull Metric metric(@NotNull String namespace, @NotNull String metricName, @Nullable MetricOptions props) (experimental) Return the given named metric for Endpoint.Default: - sum over 5 minutes
- Parameters:
namespace
- This parameter is required.metricName
- This parameter is required.props
-
-
metric
@Stability(Experimental) @NotNull Metric metric(@NotNull String namespace, @NotNull String metricName) (experimental) Return the given named metric for Endpoint.Default: - sum over 5 minutes
- Parameters:
namespace
- This parameter is required.metricName
- This parameter is required.
-
metricCpuUtilization
(experimental) Metric for CPU utilization.Default: - average over 5 minutes
- Parameters:
props
-
-
metricCpuUtilization
(experimental) Metric for CPU utilization.Default: - average over 5 minutes
-
metricDiskUtilization
(experimental) Metric for disk utilization.Default: - average over 5 minutes
- Parameters:
props
-
-
metricDiskUtilization
(experimental) Metric for disk utilization.Default: - average over 5 minutes
-
metricGpuMemoryUtilization
(experimental) Metric for GPU memory utilization.Default: - average over 5 minutes
- Parameters:
props
-
-
metricGpuMemoryUtilization
(experimental) Metric for GPU memory utilization.Default: - average over 5 minutes
-
metricGpuUtilization
(experimental) Metric for GPU utilization.Default: - average over 5 minutes
- Parameters:
props
-
-
metricGpuUtilization
(experimental) Metric for GPU utilization.Default: - average over 5 minutes
-
metricInvocationResponseCode
@Stability(Experimental) @NotNull Metric metricInvocationResponseCode(@NotNull InvocationHttpResponseCode responseCode, @Nullable MetricOptions props) (experimental) Metric for the number of invocations by HTTP response code.Default: - sum over 5 minutes
- Parameters:
responseCode
- This parameter is required.props
-
-
metricInvocationResponseCode
@Stability(Experimental) @NotNull Metric metricInvocationResponseCode(@NotNull InvocationHttpResponseCode responseCode) (experimental) Metric for the number of invocations by HTTP response code.Default: - sum over 5 minutes
- Parameters:
responseCode
- This parameter is required.
-
metricInvocations
(experimental) Metric for the number of invocations.Default: - sum over 5 minutes
- Parameters:
props
-
-
metricInvocations
(experimental) Metric for the number of invocations.Default: - sum over 5 minutes
-
metricInvocationsPerInstance
@Stability(Experimental) @NotNull Metric metricInvocationsPerInstance(@Nullable MetricOptions props) (experimental) Metric for the number of invocations per instance.Default: - sum over 5 minutes
- Parameters:
props
-
-
metricInvocationsPerInstance
(experimental) Metric for the number of invocations per instance.Default: - sum over 5 minutes
-
metricMemoryUtilization
(experimental) Metric for memory utilization.Default: - average over 5 minutes
- Parameters:
props
-
-
metricMemoryUtilization
(experimental) Metric for memory utilization.Default: - average over 5 minutes
-
metricModelLatency
(experimental) Metric for model latency.Default: - average over 5 minutes
- Parameters:
props
-
-
metricModelLatency
(experimental) Metric for model latency.Default: - average over 5 minutes
-
metricOverheadLatency
(experimental) Metric for overhead latency.Default: - average over 5 minutes
- Parameters:
props
-
-
metricOverheadLatency
(experimental) Metric for overhead latency.Default: - average over 5 minutes
-