Interface IEndpointInstanceProductionVariant

All Superinterfaces:
software.amazon.jsii.JsiiSerializable
All Known Subinterfaces:
IEndpointInstanceProductionVariant.Jsii$Default
All Known Implementing Classes:
IEndpointInstanceProductionVariant.Jsii$Proxy

@Generated(value="jsii-pacmak/1.98.0 (build 00b106d)", date="2024-05-08T21:35:16.005Z") @Stability(Experimental) public interface IEndpointInstanceProductionVariant extends software.amazon.jsii.JsiiSerializable
(experimental) Represents an instance production variant that has been associated with an endpoint.
  • Method Details

    • getVariantName

      @Stability(Experimental) @NotNull String 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

      @Stability(Experimental) @NotNull Metric metricCpuUtilization(@Nullable MetricOptions props)
      (experimental) Metric for CPU utilization.

      Default: - average over 5 minutes

      Parameters:
      props -
    • metricCpuUtilization

      @Stability(Experimental) @NotNull Metric metricCpuUtilization()
      (experimental) Metric for CPU utilization.

      Default: - average over 5 minutes

    • metricDiskUtilization

      @Stability(Experimental) @NotNull Metric metricDiskUtilization(@Nullable MetricOptions props)
      (experimental) Metric for disk utilization.

      Default: - average over 5 minutes

      Parameters:
      props -
    • metricDiskUtilization

      @Stability(Experimental) @NotNull Metric metricDiskUtilization()
      (experimental) Metric for disk utilization.

      Default: - average over 5 minutes

    • metricGpuMemoryUtilization

      @Stability(Experimental) @NotNull Metric metricGpuMemoryUtilization(@Nullable MetricOptions props)
      (experimental) Metric for GPU memory utilization.

      Default: - average over 5 minutes

      Parameters:
      props -
    • metricGpuMemoryUtilization

      @Stability(Experimental) @NotNull Metric metricGpuMemoryUtilization()
      (experimental) Metric for GPU memory utilization.

      Default: - average over 5 minutes

    • metricGpuUtilization

      @Stability(Experimental) @NotNull Metric metricGpuUtilization(@Nullable MetricOptions props)
      (experimental) Metric for GPU utilization.

      Default: - average over 5 minutes

      Parameters:
      props -
    • metricGpuUtilization

      @Stability(Experimental) @NotNull Metric 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

      @Stability(Experimental) @NotNull Metric metricInvocations(@Nullable MetricOptions props)
      (experimental) Metric for the number of invocations.

      Default: - sum over 5 minutes

      Parameters:
      props -
    • metricInvocations

      @Stability(Experimental) @NotNull Metric 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

      @Stability(Experimental) @NotNull Metric metricInvocationsPerInstance()
      (experimental) Metric for the number of invocations per instance.

      Default: - sum over 5 minutes

    • metricMemoryUtilization

      @Stability(Experimental) @NotNull Metric metricMemoryUtilization(@Nullable MetricOptions props)
      (experimental) Metric for memory utilization.

      Default: - average over 5 minutes

      Parameters:
      props -
    • metricMemoryUtilization

      @Stability(Experimental) @NotNull Metric metricMemoryUtilization()
      (experimental) Metric for memory utilization.

      Default: - average over 5 minutes

    • metricModelLatency

      @Stability(Experimental) @NotNull Metric metricModelLatency(@Nullable MetricOptions props)
      (experimental) Metric for model latency.

      Default: - average over 5 minutes

      Parameters:
      props -
    • metricModelLatency

      @Stability(Experimental) @NotNull Metric metricModelLatency()
      (experimental) Metric for model latency.

      Default: - average over 5 minutes

    • metricOverheadLatency

      @Stability(Experimental) @NotNull Metric metricOverheadLatency(@Nullable MetricOptions props)
      (experimental) Metric for overhead latency.

      Default: - average over 5 minutes

      Parameters:
      props -
    • metricOverheadLatency

      @Stability(Experimental) @NotNull Metric metricOverheadLatency()
      (experimental) Metric for overhead latency.

      Default: - average over 5 minutes