software.amazon.awssdk.services.sagemaker.model.ProductionVariant Maven / Gradle / Ivy
Show all versions of sagemaker Show documentation
/*
* Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
*
* Licensed under the Apache License, Version 2.0 (the "License"). You may not use this file except in compliance with
* the License. A copy of the License is located at
*
* http://aws.amazon.com/apache2.0
*
* or in the "license" file accompanying this file. This file is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
* CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions
* and limitations under the License.
*/
package software.amazon.awssdk.services.sagemaker.model;
import java.io.Serializable;
import java.util.Arrays;
import java.util.Collections;
import java.util.List;
import java.util.Objects;
import java.util.Optional;
import java.util.function.BiConsumer;
import java.util.function.Consumer;
import java.util.function.Function;
import software.amazon.awssdk.annotations.Generated;
import software.amazon.awssdk.core.SdkField;
import software.amazon.awssdk.core.SdkPojo;
import software.amazon.awssdk.core.protocol.MarshallLocation;
import software.amazon.awssdk.core.protocol.MarshallingType;
import software.amazon.awssdk.core.traits.LocationTrait;
import software.amazon.awssdk.utils.ToString;
import software.amazon.awssdk.utils.builder.CopyableBuilder;
import software.amazon.awssdk.utils.builder.ToCopyableBuilder;
/**
*
* Identifies a model that you want to host and the resources chosen to deploy for hosting it. If you are deploying
* multiple models, tell SageMaker how to distribute traffic among the models by specifying variant weights. For more
* information on production variants, check Production variants.
*
*/
@Generated("software.amazon.awssdk:codegen")
public final class ProductionVariant implements SdkPojo, Serializable,
ToCopyableBuilder {
private static final SdkField VARIANT_NAME_FIELD = SdkField. builder(MarshallingType.STRING)
.memberName("VariantName").getter(getter(ProductionVariant::variantName)).setter(setter(Builder::variantName))
.traits(LocationTrait.builder().location(MarshallLocation.PAYLOAD).locationName("VariantName").build()).build();
private static final SdkField MODEL_NAME_FIELD = SdkField. builder(MarshallingType.STRING)
.memberName("ModelName").getter(getter(ProductionVariant::modelName)).setter(setter(Builder::modelName))
.traits(LocationTrait.builder().location(MarshallLocation.PAYLOAD).locationName("ModelName").build()).build();
private static final SdkField INITIAL_INSTANCE_COUNT_FIELD = SdkField. builder(MarshallingType.INTEGER)
.memberName("InitialInstanceCount").getter(getter(ProductionVariant::initialInstanceCount))
.setter(setter(Builder::initialInstanceCount))
.traits(LocationTrait.builder().location(MarshallLocation.PAYLOAD).locationName("InitialInstanceCount").build())
.build();
private static final SdkField INSTANCE_TYPE_FIELD = SdkField. builder(MarshallingType.STRING)
.memberName("InstanceType").getter(getter(ProductionVariant::instanceTypeAsString))
.setter(setter(Builder::instanceType))
.traits(LocationTrait.builder().location(MarshallLocation.PAYLOAD).locationName("InstanceType").build()).build();
private static final SdkField INITIAL_VARIANT_WEIGHT_FIELD = SdkField. builder(MarshallingType.FLOAT)
.memberName("InitialVariantWeight").getter(getter(ProductionVariant::initialVariantWeight))
.setter(setter(Builder::initialVariantWeight))
.traits(LocationTrait.builder().location(MarshallLocation.PAYLOAD).locationName("InitialVariantWeight").build())
.build();
private static final SdkField ACCELERATOR_TYPE_FIELD = SdkField. builder(MarshallingType.STRING)
.memberName("AcceleratorType").getter(getter(ProductionVariant::acceleratorTypeAsString))
.setter(setter(Builder::acceleratorType))
.traits(LocationTrait.builder().location(MarshallLocation.PAYLOAD).locationName("AcceleratorType").build()).build();
private static final SdkField CORE_DUMP_CONFIG_FIELD = SdkField
. builder(MarshallingType.SDK_POJO).memberName("CoreDumpConfig")
.getter(getter(ProductionVariant::coreDumpConfig)).setter(setter(Builder::coreDumpConfig))
.constructor(ProductionVariantCoreDumpConfig::builder)
.traits(LocationTrait.builder().location(MarshallLocation.PAYLOAD).locationName("CoreDumpConfig").build()).build();
private static final SdkField SERVERLESS_CONFIG_FIELD = SdkField
. builder(MarshallingType.SDK_POJO).memberName("ServerlessConfig")
.getter(getter(ProductionVariant::serverlessConfig)).setter(setter(Builder::serverlessConfig))
.constructor(ProductionVariantServerlessConfig::builder)
.traits(LocationTrait.builder().location(MarshallLocation.PAYLOAD).locationName("ServerlessConfig").build()).build();
private static final SdkField VOLUME_SIZE_IN_GB_FIELD = SdkField. builder(MarshallingType.INTEGER)
.memberName("VolumeSizeInGB").getter(getter(ProductionVariant::volumeSizeInGB))
.setter(setter(Builder::volumeSizeInGB))
.traits(LocationTrait.builder().location(MarshallLocation.PAYLOAD).locationName("VolumeSizeInGB").build()).build();
private static final SdkField MODEL_DATA_DOWNLOAD_TIMEOUT_IN_SECONDS_FIELD = SdkField
. builder(MarshallingType.INTEGER)
.memberName("ModelDataDownloadTimeoutInSeconds")
.getter(getter(ProductionVariant::modelDataDownloadTimeoutInSeconds))
.setter(setter(Builder::modelDataDownloadTimeoutInSeconds))
.traits(LocationTrait.builder().location(MarshallLocation.PAYLOAD).locationName("ModelDataDownloadTimeoutInSeconds")
.build()).build();
private static final SdkField CONTAINER_STARTUP_HEALTH_CHECK_TIMEOUT_IN_SECONDS_FIELD = SdkField
. builder(MarshallingType.INTEGER)
.memberName("ContainerStartupHealthCheckTimeoutInSeconds")
.getter(getter(ProductionVariant::containerStartupHealthCheckTimeoutInSeconds))
.setter(setter(Builder::containerStartupHealthCheckTimeoutInSeconds))
.traits(LocationTrait.builder().location(MarshallLocation.PAYLOAD)
.locationName("ContainerStartupHealthCheckTimeoutInSeconds").build()).build();
private static final SdkField ENABLE_SSM_ACCESS_FIELD = SdkField. builder(MarshallingType.BOOLEAN)
.memberName("EnableSSMAccess").getter(getter(ProductionVariant::enableSSMAccess))
.setter(setter(Builder::enableSSMAccess))
.traits(LocationTrait.builder().location(MarshallLocation.PAYLOAD).locationName("EnableSSMAccess").build()).build();
private static final SdkField MANAGED_INSTANCE_SCALING_FIELD = SdkField
. builder(MarshallingType.SDK_POJO).memberName("ManagedInstanceScaling")
.getter(getter(ProductionVariant::managedInstanceScaling)).setter(setter(Builder::managedInstanceScaling))
.constructor(ProductionVariantManagedInstanceScaling::builder)
.traits(LocationTrait.builder().location(MarshallLocation.PAYLOAD).locationName("ManagedInstanceScaling").build())
.build();
private static final SdkField ROUTING_CONFIG_FIELD = SdkField
. builder(MarshallingType.SDK_POJO).memberName("RoutingConfig")
.getter(getter(ProductionVariant::routingConfig)).setter(setter(Builder::routingConfig))
.constructor(ProductionVariantRoutingConfig::builder)
.traits(LocationTrait.builder().location(MarshallLocation.PAYLOAD).locationName("RoutingConfig").build()).build();
private static final SdkField INFERENCE_AMI_VERSION_FIELD = SdkField. builder(MarshallingType.STRING)
.memberName("InferenceAmiVersion").getter(getter(ProductionVariant::inferenceAmiVersionAsString))
.setter(setter(Builder::inferenceAmiVersion))
.traits(LocationTrait.builder().location(MarshallLocation.PAYLOAD).locationName("InferenceAmiVersion").build())
.build();
private static final List> SDK_FIELDS = Collections.unmodifiableList(Arrays.asList(VARIANT_NAME_FIELD,
MODEL_NAME_FIELD, INITIAL_INSTANCE_COUNT_FIELD, INSTANCE_TYPE_FIELD, INITIAL_VARIANT_WEIGHT_FIELD,
ACCELERATOR_TYPE_FIELD, CORE_DUMP_CONFIG_FIELD, SERVERLESS_CONFIG_FIELD, VOLUME_SIZE_IN_GB_FIELD,
MODEL_DATA_DOWNLOAD_TIMEOUT_IN_SECONDS_FIELD, CONTAINER_STARTUP_HEALTH_CHECK_TIMEOUT_IN_SECONDS_FIELD,
ENABLE_SSM_ACCESS_FIELD, MANAGED_INSTANCE_SCALING_FIELD, ROUTING_CONFIG_FIELD, INFERENCE_AMI_VERSION_FIELD));
private static final long serialVersionUID = 1L;
private final String variantName;
private final String modelName;
private final Integer initialInstanceCount;
private final String instanceType;
private final Float initialVariantWeight;
private final String acceleratorType;
private final ProductionVariantCoreDumpConfig coreDumpConfig;
private final ProductionVariantServerlessConfig serverlessConfig;
private final Integer volumeSizeInGB;
private final Integer modelDataDownloadTimeoutInSeconds;
private final Integer containerStartupHealthCheckTimeoutInSeconds;
private final Boolean enableSSMAccess;
private final ProductionVariantManagedInstanceScaling managedInstanceScaling;
private final ProductionVariantRoutingConfig routingConfig;
private final String inferenceAmiVersion;
private ProductionVariant(BuilderImpl builder) {
this.variantName = builder.variantName;
this.modelName = builder.modelName;
this.initialInstanceCount = builder.initialInstanceCount;
this.instanceType = builder.instanceType;
this.initialVariantWeight = builder.initialVariantWeight;
this.acceleratorType = builder.acceleratorType;
this.coreDumpConfig = builder.coreDumpConfig;
this.serverlessConfig = builder.serverlessConfig;
this.volumeSizeInGB = builder.volumeSizeInGB;
this.modelDataDownloadTimeoutInSeconds = builder.modelDataDownloadTimeoutInSeconds;
this.containerStartupHealthCheckTimeoutInSeconds = builder.containerStartupHealthCheckTimeoutInSeconds;
this.enableSSMAccess = builder.enableSSMAccess;
this.managedInstanceScaling = builder.managedInstanceScaling;
this.routingConfig = builder.routingConfig;
this.inferenceAmiVersion = builder.inferenceAmiVersion;
}
/**
*
* The name of the production variant.
*
*
* @return The name of the production variant.
*/
public final String variantName() {
return variantName;
}
/**
*
* The name of the model that you want to host. This is the name that you specified when creating the model.
*
*
* @return The name of the model that you want to host. This is the name that you specified when creating the model.
*/
public final String modelName() {
return modelName;
}
/**
*
* Number of instances to launch initially.
*
*
* @return Number of instances to launch initially.
*/
public final Integer initialInstanceCount() {
return initialInstanceCount;
}
/**
*
* The ML compute instance type.
*
*
* If the service returns an enum value that is not available in the current SDK version, {@link #instanceType} will
* return {@link ProductionVariantInstanceType#UNKNOWN_TO_SDK_VERSION}. The raw value returned by the service is
* available from {@link #instanceTypeAsString}.
*
*
* @return The ML compute instance type.
* @see ProductionVariantInstanceType
*/
public final ProductionVariantInstanceType instanceType() {
return ProductionVariantInstanceType.fromValue(instanceType);
}
/**
*
* The ML compute instance type.
*
*
* If the service returns an enum value that is not available in the current SDK version, {@link #instanceType} will
* return {@link ProductionVariantInstanceType#UNKNOWN_TO_SDK_VERSION}. The raw value returned by the service is
* available from {@link #instanceTypeAsString}.
*
*
* @return The ML compute instance type.
* @see ProductionVariantInstanceType
*/
public final String instanceTypeAsString() {
return instanceType;
}
/**
*
* Determines initial traffic distribution among all of the models that you specify in the endpoint configuration.
* The traffic to a production variant is determined by the ratio of the VariantWeight to the sum of
* all VariantWeight values across all ProductionVariants. If unspecified, it defaults to 1.0.
*
*
* @return Determines initial traffic distribution among all of the models that you specify in the endpoint
* configuration. The traffic to a production variant is determined by the ratio of the
* VariantWeight to the sum of all VariantWeight values across all
* ProductionVariants. If unspecified, it defaults to 1.0.
*/
public final Float initialVariantWeight() {
return initialVariantWeight;
}
/**
*
* The size of the Elastic Inference (EI) instance to use for the production variant. EI instances provide on-demand
* GPU computing for inference. For more information, see Using Elastic Inference in Amazon SageMaker.
*
*
* If the service returns an enum value that is not available in the current SDK version, {@link #acceleratorType}
* will return {@link ProductionVariantAcceleratorType#UNKNOWN_TO_SDK_VERSION}. The raw value returned by the
* service is available from {@link #acceleratorTypeAsString}.
*
*
* @return The size of the Elastic Inference (EI) instance to use for the production variant. EI instances provide
* on-demand GPU computing for inference. For more information, see Using Elastic Inference in Amazon
* SageMaker.
* @see ProductionVariantAcceleratorType
*/
public final ProductionVariantAcceleratorType acceleratorType() {
return ProductionVariantAcceleratorType.fromValue(acceleratorType);
}
/**
*
* The size of the Elastic Inference (EI) instance to use for the production variant. EI instances provide on-demand
* GPU computing for inference. For more information, see Using Elastic Inference in Amazon SageMaker.
*
*
* If the service returns an enum value that is not available in the current SDK version, {@link #acceleratorType}
* will return {@link ProductionVariantAcceleratorType#UNKNOWN_TO_SDK_VERSION}. The raw value returned by the
* service is available from {@link #acceleratorTypeAsString}.
*
*
* @return The size of the Elastic Inference (EI) instance to use for the production variant. EI instances provide
* on-demand GPU computing for inference. For more information, see Using Elastic Inference in Amazon
* SageMaker.
* @see ProductionVariantAcceleratorType
*/
public final String acceleratorTypeAsString() {
return acceleratorType;
}
/**
*
* Specifies configuration for a core dump from the model container when the process crashes.
*
*
* @return Specifies configuration for a core dump from the model container when the process crashes.
*/
public final ProductionVariantCoreDumpConfig coreDumpConfig() {
return coreDumpConfig;
}
/**
*
* The serverless configuration for an endpoint. Specifies a serverless endpoint configuration instead of an
* instance-based endpoint configuration.
*
*
* @return The serverless configuration for an endpoint. Specifies a serverless endpoint configuration instead of an
* instance-based endpoint configuration.
*/
public final ProductionVariantServerlessConfig serverlessConfig() {
return serverlessConfig;
}
/**
*
* The size, in GB, of the ML storage volume attached to individual inference instance associated with the
* production variant. Currently only Amazon EBS gp2 storage volumes are supported.
*
*
* @return The size, in GB, of the ML storage volume attached to individual inference instance associated with the
* production variant. Currently only Amazon EBS gp2 storage volumes are supported.
*/
public final Integer volumeSizeInGB() {
return volumeSizeInGB;
}
/**
*
* The timeout value, in seconds, to download and extract the model that you want to host from Amazon S3 to the
* individual inference instance associated with this production variant.
*
*
* @return The timeout value, in seconds, to download and extract the model that you want to host from Amazon S3 to
* the individual inference instance associated with this production variant.
*/
public final Integer modelDataDownloadTimeoutInSeconds() {
return modelDataDownloadTimeoutInSeconds;
}
/**
*
* The timeout value, in seconds, for your inference container to pass health check by SageMaker Hosting. For more
* information about health check, see How Your Container Should Respond to Health Check (Ping) Requests.
*
*
* @return The timeout value, in seconds, for your inference container to pass health check by SageMaker Hosting.
* For more information about health check, see How Your Container Should Respond to Health Check (Ping) Requests.
*/
public final Integer containerStartupHealthCheckTimeoutInSeconds() {
return containerStartupHealthCheckTimeoutInSeconds;
}
/**
*
* You can use this parameter to turn on native Amazon Web Services Systems Manager (SSM) access for a production
* variant behind an endpoint. By default, SSM access is disabled for all production variants behind an endpoint.
* You can turn on or turn off SSM access for a production variant behind an existing endpoint by creating a new
* endpoint configuration and calling UpdateEndpoint.
*
*
* @return You can use this parameter to turn on native Amazon Web Services Systems Manager (SSM) access for a
* production variant behind an endpoint. By default, SSM access is disabled for all production variants
* behind an endpoint. You can turn on or turn off SSM access for a production variant behind an existing
* endpoint by creating a new endpoint configuration and calling UpdateEndpoint.
*/
public final Boolean enableSSMAccess() {
return enableSSMAccess;
}
/**
*
* Settings that control the range in the number of instances that the endpoint provisions as it scales up or down
* to accommodate traffic.
*
*
* @return Settings that control the range in the number of instances that the endpoint provisions as it scales up
* or down to accommodate traffic.
*/
public final ProductionVariantManagedInstanceScaling managedInstanceScaling() {
return managedInstanceScaling;
}
/**
*
* Settings that control how the endpoint routes incoming traffic to the instances that the endpoint hosts.
*
*
* @return Settings that control how the endpoint routes incoming traffic to the instances that the endpoint hosts.
*/
public final ProductionVariantRoutingConfig routingConfig() {
return routingConfig;
}
/**
*
* Specifies an option from a collection of preconfigured Amazon Machine Image (AMI) images. Each image is
* configured by Amazon Web Services with a set of software and driver versions. Amazon Web Services optimizes these
* configurations for different machine learning workloads.
*
*
* By selecting an AMI version, you can ensure that your inference environment is compatible with specific software
* requirements, such as CUDA driver versions, Linux kernel versions, or Amazon Web Services Neuron driver versions.
*
*
* The AMI version names, and their configurations, are the following:
*
*
* - al2-ami-sagemaker-inference-gpu-2
* -
*
* -
*
* Accelerator: GPU
*
*
* -
*
* NVIDIA driver version: 535.54.03
*
*
* -
*
* CUDA driver version: 12.2
*
*
* -
*
* Supported instance types: ml.g4dn.*, ml.g5.*, ml.g6.*, ml.p3.*, ml.p4d.*, ml.p4de.*, ml.p5.*
*
*
*
*
*
*
* If the service returns an enum value that is not available in the current SDK version,
* {@link #inferenceAmiVersion} will return {@link ProductionVariantInferenceAmiVersion#UNKNOWN_TO_SDK_VERSION}. The
* raw value returned by the service is available from {@link #inferenceAmiVersionAsString}.
*
*
* @return Specifies an option from a collection of preconfigured Amazon Machine Image (AMI) images. Each image is
* configured by Amazon Web Services with a set of software and driver versions. Amazon Web Services
* optimizes these configurations for different machine learning workloads.
*
* By selecting an AMI version, you can ensure that your inference environment is compatible with specific
* software requirements, such as CUDA driver versions, Linux kernel versions, or Amazon Web Services Neuron
* driver versions.
*
*
* The AMI version names, and their configurations, are the following:
*
*
* - al2-ami-sagemaker-inference-gpu-2
* -
*
* -
*
* Accelerator: GPU
*
*
* -
*
* NVIDIA driver version: 535.54.03
*
*
* -
*
* CUDA driver version: 12.2
*
*
* -
*
* Supported instance types: ml.g4dn.*, ml.g5.*, ml.g6.*, ml.p3.*, ml.p4d.*, ml.p4de.*, ml.p5.*
*
*
*
*
* @see ProductionVariantInferenceAmiVersion
*/
public final ProductionVariantInferenceAmiVersion inferenceAmiVersion() {
return ProductionVariantInferenceAmiVersion.fromValue(inferenceAmiVersion);
}
/**
*
* Specifies an option from a collection of preconfigured Amazon Machine Image (AMI) images. Each image is
* configured by Amazon Web Services with a set of software and driver versions. Amazon Web Services optimizes these
* configurations for different machine learning workloads.
*
*
* By selecting an AMI version, you can ensure that your inference environment is compatible with specific software
* requirements, such as CUDA driver versions, Linux kernel versions, or Amazon Web Services Neuron driver versions.
*
*
* The AMI version names, and their configurations, are the following:
*
*
* - al2-ami-sagemaker-inference-gpu-2
* -
*
* -
*
* Accelerator: GPU
*
*
* -
*
* NVIDIA driver version: 535.54.03
*
*
* -
*
* CUDA driver version: 12.2
*
*
* -
*
* Supported instance types: ml.g4dn.*, ml.g5.*, ml.g6.*, ml.p3.*, ml.p4d.*, ml.p4de.*, ml.p5.*
*
*
*
*
*
*
* If the service returns an enum value that is not available in the current SDK version,
* {@link #inferenceAmiVersion} will return {@link ProductionVariantInferenceAmiVersion#UNKNOWN_TO_SDK_VERSION}. The
* raw value returned by the service is available from {@link #inferenceAmiVersionAsString}.
*
*
* @return Specifies an option from a collection of preconfigured Amazon Machine Image (AMI) images. Each image is
* configured by Amazon Web Services with a set of software and driver versions. Amazon Web Services
* optimizes these configurations for different machine learning workloads.
*
* By selecting an AMI version, you can ensure that your inference environment is compatible with specific
* software requirements, such as CUDA driver versions, Linux kernel versions, or Amazon Web Services Neuron
* driver versions.
*
*
* The AMI version names, and their configurations, are the following:
*
*
* - al2-ami-sagemaker-inference-gpu-2
* -
*
* -
*
* Accelerator: GPU
*
*
* -
*
* NVIDIA driver version: 535.54.03
*
*
* -
*
* CUDA driver version: 12.2
*
*
* -
*
* Supported instance types: ml.g4dn.*, ml.g5.*, ml.g6.*, ml.p3.*, ml.p4d.*, ml.p4de.*, ml.p5.*
*
*
*
*
* @see ProductionVariantInferenceAmiVersion
*/
public final String inferenceAmiVersionAsString() {
return inferenceAmiVersion;
}
@Override
public Builder toBuilder() {
return new BuilderImpl(this);
}
public static Builder builder() {
return new BuilderImpl();
}
public static Class serializableBuilderClass() {
return BuilderImpl.class;
}
@Override
public final int hashCode() {
int hashCode = 1;
hashCode = 31 * hashCode + Objects.hashCode(variantName());
hashCode = 31 * hashCode + Objects.hashCode(modelName());
hashCode = 31 * hashCode + Objects.hashCode(initialInstanceCount());
hashCode = 31 * hashCode + Objects.hashCode(instanceTypeAsString());
hashCode = 31 * hashCode + Objects.hashCode(initialVariantWeight());
hashCode = 31 * hashCode + Objects.hashCode(acceleratorTypeAsString());
hashCode = 31 * hashCode + Objects.hashCode(coreDumpConfig());
hashCode = 31 * hashCode + Objects.hashCode(serverlessConfig());
hashCode = 31 * hashCode + Objects.hashCode(volumeSizeInGB());
hashCode = 31 * hashCode + Objects.hashCode(modelDataDownloadTimeoutInSeconds());
hashCode = 31 * hashCode + Objects.hashCode(containerStartupHealthCheckTimeoutInSeconds());
hashCode = 31 * hashCode + Objects.hashCode(enableSSMAccess());
hashCode = 31 * hashCode + Objects.hashCode(managedInstanceScaling());
hashCode = 31 * hashCode + Objects.hashCode(routingConfig());
hashCode = 31 * hashCode + Objects.hashCode(inferenceAmiVersionAsString());
return hashCode;
}
@Override
public final boolean equals(Object obj) {
return equalsBySdkFields(obj);
}
@Override
public final boolean equalsBySdkFields(Object obj) {
if (this == obj) {
return true;
}
if (obj == null) {
return false;
}
if (!(obj instanceof ProductionVariant)) {
return false;
}
ProductionVariant other = (ProductionVariant) obj;
return Objects.equals(variantName(), other.variantName())
&& Objects.equals(modelName(), other.modelName())
&& Objects.equals(initialInstanceCount(), other.initialInstanceCount())
&& Objects.equals(instanceTypeAsString(), other.instanceTypeAsString())
&& Objects.equals(initialVariantWeight(), other.initialVariantWeight())
&& Objects.equals(acceleratorTypeAsString(), other.acceleratorTypeAsString())
&& Objects.equals(coreDumpConfig(), other.coreDumpConfig())
&& Objects.equals(serverlessConfig(), other.serverlessConfig())
&& Objects.equals(volumeSizeInGB(), other.volumeSizeInGB())
&& Objects.equals(modelDataDownloadTimeoutInSeconds(), other.modelDataDownloadTimeoutInSeconds())
&& Objects.equals(containerStartupHealthCheckTimeoutInSeconds(),
other.containerStartupHealthCheckTimeoutInSeconds())
&& Objects.equals(enableSSMAccess(), other.enableSSMAccess())
&& Objects.equals(managedInstanceScaling(), other.managedInstanceScaling())
&& Objects.equals(routingConfig(), other.routingConfig())
&& Objects.equals(inferenceAmiVersionAsString(), other.inferenceAmiVersionAsString());
}
/**
* Returns a string representation of this object. This is useful for testing and debugging. Sensitive data will be
* redacted from this string using a placeholder value.
*/
@Override
public final String toString() {
return ToString.builder("ProductionVariant").add("VariantName", variantName()).add("ModelName", modelName())
.add("InitialInstanceCount", initialInstanceCount()).add("InstanceType", instanceTypeAsString())
.add("InitialVariantWeight", initialVariantWeight()).add("AcceleratorType", acceleratorTypeAsString())
.add("CoreDumpConfig", coreDumpConfig()).add("ServerlessConfig", serverlessConfig())
.add("VolumeSizeInGB", volumeSizeInGB())
.add("ModelDataDownloadTimeoutInSeconds", modelDataDownloadTimeoutInSeconds())
.add("ContainerStartupHealthCheckTimeoutInSeconds", containerStartupHealthCheckTimeoutInSeconds())
.add("EnableSSMAccess", enableSSMAccess()).add("ManagedInstanceScaling", managedInstanceScaling())
.add("RoutingConfig", routingConfig()).add("InferenceAmiVersion", inferenceAmiVersionAsString()).build();
}
public final Optional getValueForField(String fieldName, Class clazz) {
switch (fieldName) {
case "VariantName":
return Optional.ofNullable(clazz.cast(variantName()));
case "ModelName":
return Optional.ofNullable(clazz.cast(modelName()));
case "InitialInstanceCount":
return Optional.ofNullable(clazz.cast(initialInstanceCount()));
case "InstanceType":
return Optional.ofNullable(clazz.cast(instanceTypeAsString()));
case "InitialVariantWeight":
return Optional.ofNullable(clazz.cast(initialVariantWeight()));
case "AcceleratorType":
return Optional.ofNullable(clazz.cast(acceleratorTypeAsString()));
case "CoreDumpConfig":
return Optional.ofNullable(clazz.cast(coreDumpConfig()));
case "ServerlessConfig":
return Optional.ofNullable(clazz.cast(serverlessConfig()));
case "VolumeSizeInGB":
return Optional.ofNullable(clazz.cast(volumeSizeInGB()));
case "ModelDataDownloadTimeoutInSeconds":
return Optional.ofNullable(clazz.cast(modelDataDownloadTimeoutInSeconds()));
case "ContainerStartupHealthCheckTimeoutInSeconds":
return Optional.ofNullable(clazz.cast(containerStartupHealthCheckTimeoutInSeconds()));
case "EnableSSMAccess":
return Optional.ofNullable(clazz.cast(enableSSMAccess()));
case "ManagedInstanceScaling":
return Optional.ofNullable(clazz.cast(managedInstanceScaling()));
case "RoutingConfig":
return Optional.ofNullable(clazz.cast(routingConfig()));
case "InferenceAmiVersion":
return Optional.ofNullable(clazz.cast(inferenceAmiVersionAsString()));
default:
return Optional.empty();
}
}
@Override
public final List> sdkFields() {
return SDK_FIELDS;
}
private static Function getter(Function g) {
return obj -> g.apply((ProductionVariant) obj);
}
private static BiConsumer setter(BiConsumer s) {
return (obj, val) -> s.accept((Builder) obj, val);
}
public interface Builder extends SdkPojo, CopyableBuilder {
/**
*
* The name of the production variant.
*
*
* @param variantName
* The name of the production variant.
* @return Returns a reference to this object so that method calls can be chained together.
*/
Builder variantName(String variantName);
/**
*
* The name of the model that you want to host. This is the name that you specified when creating the model.
*
*
* @param modelName
* The name of the model that you want to host. This is the name that you specified when creating the
* model.
* @return Returns a reference to this object so that method calls can be chained together.
*/
Builder modelName(String modelName);
/**
*
* Number of instances to launch initially.
*
*
* @param initialInstanceCount
* Number of instances to launch initially.
* @return Returns a reference to this object so that method calls can be chained together.
*/
Builder initialInstanceCount(Integer initialInstanceCount);
/**
*
* The ML compute instance type.
*
*
* @param instanceType
* The ML compute instance type.
* @see ProductionVariantInstanceType
* @return Returns a reference to this object so that method calls can be chained together.
* @see ProductionVariantInstanceType
*/
Builder instanceType(String instanceType);
/**
*
* The ML compute instance type.
*
*
* @param instanceType
* The ML compute instance type.
* @see ProductionVariantInstanceType
* @return Returns a reference to this object so that method calls can be chained together.
* @see ProductionVariantInstanceType
*/
Builder instanceType(ProductionVariantInstanceType instanceType);
/**
*
* Determines initial traffic distribution among all of the models that you specify in the endpoint
* configuration. The traffic to a production variant is determined by the ratio of the
* VariantWeight to the sum of all VariantWeight values across all ProductionVariants.
* If unspecified, it defaults to 1.0.
*
*
* @param initialVariantWeight
* Determines initial traffic distribution among all of the models that you specify in the endpoint
* configuration. The traffic to a production variant is determined by the ratio of the
* VariantWeight to the sum of all VariantWeight values across all
* ProductionVariants. If unspecified, it defaults to 1.0.
* @return Returns a reference to this object so that method calls can be chained together.
*/
Builder initialVariantWeight(Float initialVariantWeight);
/**
*
* The size of the Elastic Inference (EI) instance to use for the production variant. EI instances provide
* on-demand GPU computing for inference. For more information, see Using Elastic Inference in Amazon
* SageMaker.
*
*
* @param acceleratorType
* The size of the Elastic Inference (EI) instance to use for the production variant. EI instances
* provide on-demand GPU computing for inference. For more information, see Using Elastic Inference in Amazon
* SageMaker.
* @see ProductionVariantAcceleratorType
* @return Returns a reference to this object so that method calls can be chained together.
* @see ProductionVariantAcceleratorType
*/
Builder acceleratorType(String acceleratorType);
/**
*
* The size of the Elastic Inference (EI) instance to use for the production variant. EI instances provide
* on-demand GPU computing for inference. For more information, see Using Elastic Inference in Amazon
* SageMaker.
*
*
* @param acceleratorType
* The size of the Elastic Inference (EI) instance to use for the production variant. EI instances
* provide on-demand GPU computing for inference. For more information, see Using Elastic Inference in Amazon
* SageMaker.
* @see ProductionVariantAcceleratorType
* @return Returns a reference to this object so that method calls can be chained together.
* @see ProductionVariantAcceleratorType
*/
Builder acceleratorType(ProductionVariantAcceleratorType acceleratorType);
/**
*
* Specifies configuration for a core dump from the model container when the process crashes.
*
*
* @param coreDumpConfig
* Specifies configuration for a core dump from the model container when the process crashes.
* @return Returns a reference to this object so that method calls can be chained together.
*/
Builder coreDumpConfig(ProductionVariantCoreDumpConfig coreDumpConfig);
/**
*
* Specifies configuration for a core dump from the model container when the process crashes.
*
* This is a convenience method that creates an instance of the {@link ProductionVariantCoreDumpConfig.Builder}
* avoiding the need to create one manually via {@link ProductionVariantCoreDumpConfig#builder()}.
*
*
* When the {@link Consumer} completes, {@link ProductionVariantCoreDumpConfig.Builder#build()} is called
* immediately and its result is passed to {@link #coreDumpConfig(ProductionVariantCoreDumpConfig)}.
*
* @param coreDumpConfig
* a consumer that will call methods on {@link ProductionVariantCoreDumpConfig.Builder}
* @return Returns a reference to this object so that method calls can be chained together.
* @see #coreDumpConfig(ProductionVariantCoreDumpConfig)
*/
default Builder coreDumpConfig(Consumer coreDumpConfig) {
return coreDumpConfig(ProductionVariantCoreDumpConfig.builder().applyMutation(coreDumpConfig).build());
}
/**
*
* The serverless configuration for an endpoint. Specifies a serverless endpoint configuration instead of an
* instance-based endpoint configuration.
*
*
* @param serverlessConfig
* The serverless configuration for an endpoint. Specifies a serverless endpoint configuration instead of
* an instance-based endpoint configuration.
* @return Returns a reference to this object so that method calls can be chained together.
*/
Builder serverlessConfig(ProductionVariantServerlessConfig serverlessConfig);
/**
*
* The serverless configuration for an endpoint. Specifies a serverless endpoint configuration instead of an
* instance-based endpoint configuration.
*
* This is a convenience method that creates an instance of the
* {@link ProductionVariantServerlessConfig.Builder} avoiding the need to create one manually via
* {@link ProductionVariantServerlessConfig#builder()}.
*
*
* When the {@link Consumer} completes, {@link ProductionVariantServerlessConfig.Builder#build()} is called
* immediately and its result is passed to {@link #serverlessConfig(ProductionVariantServerlessConfig)}.
*
* @param serverlessConfig
* a consumer that will call methods on {@link ProductionVariantServerlessConfig.Builder}
* @return Returns a reference to this object so that method calls can be chained together.
* @see #serverlessConfig(ProductionVariantServerlessConfig)
*/
default Builder serverlessConfig(Consumer serverlessConfig) {
return serverlessConfig(ProductionVariantServerlessConfig.builder().applyMutation(serverlessConfig).build());
}
/**
*
* The size, in GB, of the ML storage volume attached to individual inference instance associated with the
* production variant. Currently only Amazon EBS gp2 storage volumes are supported.
*
*
* @param volumeSizeInGB
* The size, in GB, of the ML storage volume attached to individual inference instance associated with
* the production variant. Currently only Amazon EBS gp2 storage volumes are supported.
* @return Returns a reference to this object so that method calls can be chained together.
*/
Builder volumeSizeInGB(Integer volumeSizeInGB);
/**
*
* The timeout value, in seconds, to download and extract the model that you want to host from Amazon S3 to the
* individual inference instance associated with this production variant.
*
*
* @param modelDataDownloadTimeoutInSeconds
* The timeout value, in seconds, to download and extract the model that you want to host from Amazon S3
* to the individual inference instance associated with this production variant.
* @return Returns a reference to this object so that method calls can be chained together.
*/
Builder modelDataDownloadTimeoutInSeconds(Integer modelDataDownloadTimeoutInSeconds);
/**
*
* The timeout value, in seconds, for your inference container to pass health check by SageMaker Hosting. For
* more information about health check, see How Your Container Should Respond to Health Check (Ping) Requests.
*
*
* @param containerStartupHealthCheckTimeoutInSeconds
* The timeout value, in seconds, for your inference container to pass health check by SageMaker Hosting.
* For more information about health check, see How Your Container Should Respond to Health Check (Ping) Requests.
* @return Returns a reference to this object so that method calls can be chained together.
*/
Builder containerStartupHealthCheckTimeoutInSeconds(Integer containerStartupHealthCheckTimeoutInSeconds);
/**
*
* You can use this parameter to turn on native Amazon Web Services Systems Manager (SSM) access for a
* production variant behind an endpoint. By default, SSM access is disabled for all production variants behind
* an endpoint. You can turn on or turn off SSM access for a production variant behind an existing endpoint by
* creating a new endpoint configuration and calling UpdateEndpoint.
*
*
* @param enableSSMAccess
* You can use this parameter to turn on native Amazon Web Services Systems Manager (SSM) access for a
* production variant behind an endpoint. By default, SSM access is disabled for all production variants
* behind an endpoint. You can turn on or turn off SSM access for a production variant behind an existing
* endpoint by creating a new endpoint configuration and calling UpdateEndpoint.
* @return Returns a reference to this object so that method calls can be chained together.
*/
Builder enableSSMAccess(Boolean enableSSMAccess);
/**
*
* Settings that control the range in the number of instances that the endpoint provisions as it scales up or
* down to accommodate traffic.
*
*
* @param managedInstanceScaling
* Settings that control the range in the number of instances that the endpoint provisions as it scales
* up or down to accommodate traffic.
* @return Returns a reference to this object so that method calls can be chained together.
*/
Builder managedInstanceScaling(ProductionVariantManagedInstanceScaling managedInstanceScaling);
/**
*
* Settings that control the range in the number of instances that the endpoint provisions as it scales up or
* down to accommodate traffic.
*
* This is a convenience method that creates an instance of the
* {@link ProductionVariantManagedInstanceScaling.Builder} avoiding the need to create one manually via
* {@link ProductionVariantManagedInstanceScaling#builder()}.
*
*
* When the {@link Consumer} completes, {@link ProductionVariantManagedInstanceScaling.Builder#build()} is
* called immediately and its result is passed to
* {@link #managedInstanceScaling(ProductionVariantManagedInstanceScaling)}.
*
* @param managedInstanceScaling
* a consumer that will call methods on {@link ProductionVariantManagedInstanceScaling.Builder}
* @return Returns a reference to this object so that method calls can be chained together.
* @see #managedInstanceScaling(ProductionVariantManagedInstanceScaling)
*/
default Builder managedInstanceScaling(Consumer managedInstanceScaling) {
return managedInstanceScaling(ProductionVariantManagedInstanceScaling.builder().applyMutation(managedInstanceScaling)
.build());
}
/**
*
* Settings that control how the endpoint routes incoming traffic to the instances that the endpoint hosts.
*
*
* @param routingConfig
* Settings that control how the endpoint routes incoming traffic to the instances that the endpoint
* hosts.
* @return Returns a reference to this object so that method calls can be chained together.
*/
Builder routingConfig(ProductionVariantRoutingConfig routingConfig);
/**
*
* Settings that control how the endpoint routes incoming traffic to the instances that the endpoint hosts.
*
* This is a convenience method that creates an instance of the {@link ProductionVariantRoutingConfig.Builder}
* avoiding the need to create one manually via {@link ProductionVariantRoutingConfig#builder()}.
*
*
* When the {@link Consumer} completes, {@link ProductionVariantRoutingConfig.Builder#build()} is called
* immediately and its result is passed to {@link #routingConfig(ProductionVariantRoutingConfig)}.
*
* @param routingConfig
* a consumer that will call methods on {@link ProductionVariantRoutingConfig.Builder}
* @return Returns a reference to this object so that method calls can be chained together.
* @see #routingConfig(ProductionVariantRoutingConfig)
*/
default Builder routingConfig(Consumer routingConfig) {
return routingConfig(ProductionVariantRoutingConfig.builder().applyMutation(routingConfig).build());
}
/**
*
* Specifies an option from a collection of preconfigured Amazon Machine Image (AMI) images. Each image is
* configured by Amazon Web Services with a set of software and driver versions. Amazon Web Services optimizes
* these configurations for different machine learning workloads.
*
*
* By selecting an AMI version, you can ensure that your inference environment is compatible with specific
* software requirements, such as CUDA driver versions, Linux kernel versions, or Amazon Web Services Neuron
* driver versions.
*
*
* The AMI version names, and their configurations, are the following:
*
*
* - al2-ami-sagemaker-inference-gpu-2
* -
*
* -
*
* Accelerator: GPU
*
*
* -
*
* NVIDIA driver version: 535.54.03
*
*
* -
*
* CUDA driver version: 12.2
*
*
* -
*
* Supported instance types: ml.g4dn.*, ml.g5.*, ml.g6.*, ml.p3.*, ml.p4d.*, ml.p4de.*, ml.p5.*
*
*
*
*
*
*
* @param inferenceAmiVersion
* Specifies an option from a collection of preconfigured Amazon Machine Image (AMI) images. Each image
* is configured by Amazon Web Services with a set of software and driver versions. Amazon Web Services
* optimizes these configurations for different machine learning workloads.
*
* By selecting an AMI version, you can ensure that your inference environment is compatible with
* specific software requirements, such as CUDA driver versions, Linux kernel versions, or Amazon Web
* Services Neuron driver versions.
*
*
* The AMI version names, and their configurations, are the following:
*
*
* - al2-ami-sagemaker-inference-gpu-2
* -
*
* -
*
* Accelerator: GPU
*
*
* -
*
* NVIDIA driver version: 535.54.03
*
*
* -
*
* CUDA driver version: 12.2
*
*
* -
*
* Supported instance types: ml.g4dn.*, ml.g5.*, ml.g6.*, ml.p3.*, ml.p4d.*, ml.p4de.*, ml.p5.*
*
*
*
*
* @see ProductionVariantInferenceAmiVersion
* @return Returns a reference to this object so that method calls can be chained together.
* @see ProductionVariantInferenceAmiVersion
*/
Builder inferenceAmiVersion(String inferenceAmiVersion);
/**
*
* Specifies an option from a collection of preconfigured Amazon Machine Image (AMI) images. Each image is
* configured by Amazon Web Services with a set of software and driver versions. Amazon Web Services optimizes
* these configurations for different machine learning workloads.
*
*
* By selecting an AMI version, you can ensure that your inference environment is compatible with specific
* software requirements, such as CUDA driver versions, Linux kernel versions, or Amazon Web Services Neuron
* driver versions.
*
*
* The AMI version names, and their configurations, are the following:
*
*
* - al2-ami-sagemaker-inference-gpu-2
* -
*
* -
*
* Accelerator: GPU
*
*
* -
*
* NVIDIA driver version: 535.54.03
*
*
* -
*
* CUDA driver version: 12.2
*
*
* -
*
* Supported instance types: ml.g4dn.*, ml.g5.*, ml.g6.*, ml.p3.*, ml.p4d.*, ml.p4de.*, ml.p5.*
*
*
*
*
*
*
* @param inferenceAmiVersion
* Specifies an option from a collection of preconfigured Amazon Machine Image (AMI) images. Each image
* is configured by Amazon Web Services with a set of software and driver versions. Amazon Web Services
* optimizes these configurations for different machine learning workloads.
*
* By selecting an AMI version, you can ensure that your inference environment is compatible with
* specific software requirements, such as CUDA driver versions, Linux kernel versions, or Amazon Web
* Services Neuron driver versions.
*
*
* The AMI version names, and their configurations, are the following:
*
*
* - al2-ami-sagemaker-inference-gpu-2
* -
*
* -
*
* Accelerator: GPU
*
*
* -
*
* NVIDIA driver version: 535.54.03
*
*
* -
*
* CUDA driver version: 12.2
*
*
* -
*
* Supported instance types: ml.g4dn.*, ml.g5.*, ml.g6.*, ml.p3.*, ml.p4d.*, ml.p4de.*, ml.p5.*
*
*
*
*
* @see ProductionVariantInferenceAmiVersion
* @return Returns a reference to this object so that method calls can be chained together.
* @see ProductionVariantInferenceAmiVersion
*/
Builder inferenceAmiVersion(ProductionVariantInferenceAmiVersion inferenceAmiVersion);
}
static final class BuilderImpl implements Builder {
private String variantName;
private String modelName;
private Integer initialInstanceCount;
private String instanceType;
private Float initialVariantWeight;
private String acceleratorType;
private ProductionVariantCoreDumpConfig coreDumpConfig;
private ProductionVariantServerlessConfig serverlessConfig;
private Integer volumeSizeInGB;
private Integer modelDataDownloadTimeoutInSeconds;
private Integer containerStartupHealthCheckTimeoutInSeconds;
private Boolean enableSSMAccess;
private ProductionVariantManagedInstanceScaling managedInstanceScaling;
private ProductionVariantRoutingConfig routingConfig;
private String inferenceAmiVersion;
private BuilderImpl() {
}
private BuilderImpl(ProductionVariant model) {
variantName(model.variantName);
modelName(model.modelName);
initialInstanceCount(model.initialInstanceCount);
instanceType(model.instanceType);
initialVariantWeight(model.initialVariantWeight);
acceleratorType(model.acceleratorType);
coreDumpConfig(model.coreDumpConfig);
serverlessConfig(model.serverlessConfig);
volumeSizeInGB(model.volumeSizeInGB);
modelDataDownloadTimeoutInSeconds(model.modelDataDownloadTimeoutInSeconds);
containerStartupHealthCheckTimeoutInSeconds(model.containerStartupHealthCheckTimeoutInSeconds);
enableSSMAccess(model.enableSSMAccess);
managedInstanceScaling(model.managedInstanceScaling);
routingConfig(model.routingConfig);
inferenceAmiVersion(model.inferenceAmiVersion);
}
public final String getVariantName() {
return variantName;
}
public final void setVariantName(String variantName) {
this.variantName = variantName;
}
@Override
public final Builder variantName(String variantName) {
this.variantName = variantName;
return this;
}
public final String getModelName() {
return modelName;
}
public final void setModelName(String modelName) {
this.modelName = modelName;
}
@Override
public final Builder modelName(String modelName) {
this.modelName = modelName;
return this;
}
public final Integer getInitialInstanceCount() {
return initialInstanceCount;
}
public final void setInitialInstanceCount(Integer initialInstanceCount) {
this.initialInstanceCount = initialInstanceCount;
}
@Override
public final Builder initialInstanceCount(Integer initialInstanceCount) {
this.initialInstanceCount = initialInstanceCount;
return this;
}
public final String getInstanceType() {
return instanceType;
}
public final void setInstanceType(String instanceType) {
this.instanceType = instanceType;
}
@Override
public final Builder instanceType(String instanceType) {
this.instanceType = instanceType;
return this;
}
@Override
public final Builder instanceType(ProductionVariantInstanceType instanceType) {
this.instanceType(instanceType == null ? null : instanceType.toString());
return this;
}
public final Float getInitialVariantWeight() {
return initialVariantWeight;
}
public final void setInitialVariantWeight(Float initialVariantWeight) {
this.initialVariantWeight = initialVariantWeight;
}
@Override
public final Builder initialVariantWeight(Float initialVariantWeight) {
this.initialVariantWeight = initialVariantWeight;
return this;
}
public final String getAcceleratorType() {
return acceleratorType;
}
public final void setAcceleratorType(String acceleratorType) {
this.acceleratorType = acceleratorType;
}
@Override
public final Builder acceleratorType(String acceleratorType) {
this.acceleratorType = acceleratorType;
return this;
}
@Override
public final Builder acceleratorType(ProductionVariantAcceleratorType acceleratorType) {
this.acceleratorType(acceleratorType == null ? null : acceleratorType.toString());
return this;
}
public final ProductionVariantCoreDumpConfig.Builder getCoreDumpConfig() {
return coreDumpConfig != null ? coreDumpConfig.toBuilder() : null;
}
public final void setCoreDumpConfig(ProductionVariantCoreDumpConfig.BuilderImpl coreDumpConfig) {
this.coreDumpConfig = coreDumpConfig != null ? coreDumpConfig.build() : null;
}
@Override
public final Builder coreDumpConfig(ProductionVariantCoreDumpConfig coreDumpConfig) {
this.coreDumpConfig = coreDumpConfig;
return this;
}
public final ProductionVariantServerlessConfig.Builder getServerlessConfig() {
return serverlessConfig != null ? serverlessConfig.toBuilder() : null;
}
public final void setServerlessConfig(ProductionVariantServerlessConfig.BuilderImpl serverlessConfig) {
this.serverlessConfig = serverlessConfig != null ? serverlessConfig.build() : null;
}
@Override
public final Builder serverlessConfig(ProductionVariantServerlessConfig serverlessConfig) {
this.serverlessConfig = serverlessConfig;
return this;
}
public final Integer getVolumeSizeInGB() {
return volumeSizeInGB;
}
public final void setVolumeSizeInGB(Integer volumeSizeInGB) {
this.volumeSizeInGB = volumeSizeInGB;
}
@Override
public final Builder volumeSizeInGB(Integer volumeSizeInGB) {
this.volumeSizeInGB = volumeSizeInGB;
return this;
}
public final Integer getModelDataDownloadTimeoutInSeconds() {
return modelDataDownloadTimeoutInSeconds;
}
public final void setModelDataDownloadTimeoutInSeconds(Integer modelDataDownloadTimeoutInSeconds) {
this.modelDataDownloadTimeoutInSeconds = modelDataDownloadTimeoutInSeconds;
}
@Override
public final Builder modelDataDownloadTimeoutInSeconds(Integer modelDataDownloadTimeoutInSeconds) {
this.modelDataDownloadTimeoutInSeconds = modelDataDownloadTimeoutInSeconds;
return this;
}
public final Integer getContainerStartupHealthCheckTimeoutInSeconds() {
return containerStartupHealthCheckTimeoutInSeconds;
}
public final void setContainerStartupHealthCheckTimeoutInSeconds(Integer containerStartupHealthCheckTimeoutInSeconds) {
this.containerStartupHealthCheckTimeoutInSeconds = containerStartupHealthCheckTimeoutInSeconds;
}
@Override
public final Builder containerStartupHealthCheckTimeoutInSeconds(Integer containerStartupHealthCheckTimeoutInSeconds) {
this.containerStartupHealthCheckTimeoutInSeconds = containerStartupHealthCheckTimeoutInSeconds;
return this;
}
public final Boolean getEnableSSMAccess() {
return enableSSMAccess;
}
public final void setEnableSSMAccess(Boolean enableSSMAccess) {
this.enableSSMAccess = enableSSMAccess;
}
@Override
public final Builder enableSSMAccess(Boolean enableSSMAccess) {
this.enableSSMAccess = enableSSMAccess;
return this;
}
public final ProductionVariantManagedInstanceScaling.Builder getManagedInstanceScaling() {
return managedInstanceScaling != null ? managedInstanceScaling.toBuilder() : null;
}
public final void setManagedInstanceScaling(ProductionVariantManagedInstanceScaling.BuilderImpl managedInstanceScaling) {
this.managedInstanceScaling = managedInstanceScaling != null ? managedInstanceScaling.build() : null;
}
@Override
public final Builder managedInstanceScaling(ProductionVariantManagedInstanceScaling managedInstanceScaling) {
this.managedInstanceScaling = managedInstanceScaling;
return this;
}
public final ProductionVariantRoutingConfig.Builder getRoutingConfig() {
return routingConfig != null ? routingConfig.toBuilder() : null;
}
public final void setRoutingConfig(ProductionVariantRoutingConfig.BuilderImpl routingConfig) {
this.routingConfig = routingConfig != null ? routingConfig.build() : null;
}
@Override
public final Builder routingConfig(ProductionVariantRoutingConfig routingConfig) {
this.routingConfig = routingConfig;
return this;
}
public final String getInferenceAmiVersion() {
return inferenceAmiVersion;
}
public final void setInferenceAmiVersion(String inferenceAmiVersion) {
this.inferenceAmiVersion = inferenceAmiVersion;
}
@Override
public final Builder inferenceAmiVersion(String inferenceAmiVersion) {
this.inferenceAmiVersion = inferenceAmiVersion;
return this;
}
@Override
public final Builder inferenceAmiVersion(ProductionVariantInferenceAmiVersion inferenceAmiVersion) {
this.inferenceAmiVersion(inferenceAmiVersion == null ? null : inferenceAmiVersion.toString());
return this;
}
@Override
public ProductionVariant build() {
return new ProductionVariant(this);
}
@Override
public List> sdkFields() {
return SDK_FIELDS;
}
}
}