| Package | Description |
|---|---|
| com.amazonaws.services.sagemaker |
Provides APIs for creating and managing SageMaker resources.
|
| com.amazonaws.services.sagemaker.model |
| Modifier and Type | Method and Description |
|---|---|
GetScalingConfigurationRecommendationRequest |
GetScalingConfigurationRecommendationRequest.clone() |
GetScalingConfigurationRecommendationRequest |
GetScalingConfigurationRecommendationRequest.withEndpointName(String endpointName)
The name of an endpoint benchmarked during a previously completed inference recommendation job.
|
GetScalingConfigurationRecommendationRequest |
GetScalingConfigurationRecommendationRequest.withInferenceRecommendationsJobName(String inferenceRecommendationsJobName)
The name of a previously completed Inference Recommender job.
|
GetScalingConfigurationRecommendationRequest |
GetScalingConfigurationRecommendationRequest.withRecommendationId(String recommendationId)
The recommendation ID of a previously completed inference recommendation.
|
GetScalingConfigurationRecommendationRequest |
GetScalingConfigurationRecommendationRequest.withScalingPolicyObjective(ScalingPolicyObjective scalingPolicyObjective)
An object where you specify the anticipated traffic pattern for an endpoint.
|
GetScalingConfigurationRecommendationRequest |
GetScalingConfigurationRecommendationRequest.withTargetCpuUtilizationPerCore(Integer targetCpuUtilizationPerCore)
The percentage of how much utilization you want an instance to use before autoscaling.
|
Copyright © 2025. All rights reserved.