software.amazon.awssdk.services.sagemaker.model

Class ProductionVariant

java.lang.Object

software.amazon.awssdk.services.sagemaker.model.ProductionVariant

All Implemented Interfaces:

Serializable, SdkPojo, ToCopyableBuilder<ProductionVariant.Builder,ProductionVariant>

@Generated(value="software.amazon.awssdk:codegen")
public final class ProductionVariant
extends Object
implements SdkPojo, Serializable, ToCopyableBuilder<ProductionVariant.Builder,ProductionVariant>

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.

See Also:

Serialized Form

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static interface	ProductionVariant.Builder

Method Summary

Modifier and Type	Method and Description
ProductionVariantAcceleratorType	acceleratorType() The size of the Elastic Inference (EI) instance to use for the production variant.
String	acceleratorTypeAsString() The size of the Elastic Inference (EI) instance to use for the production variant.
static ProductionVariant.Builder	builder()
ProductionVariantCoreDumpConfig	coreDumpConfig() Specifies configuration for a core dump from the model container when the process crashes.
boolean	equals(Object obj)
boolean	equalsBySdkFields(Object obj)
<T> Optional<T>	getValueForField(String fieldName, Class<T> clazz)
int	hashCode()
Integer	initialInstanceCount() Number of instances to launch initially.
Float	initialVariantWeight() Determines initial traffic distribution among all of the models that you specify in the endpoint configuration.
ProductionVariantInstanceType	instanceType() The ML compute instance type.
String	instanceTypeAsString() The ML compute instance type.
String	modelName() The name of the model that you want to host.
List<SdkField<?>>	sdkFields()
static Class<? extends ProductionVariant.Builder>	serializableBuilderClass()
ProductionVariantServerlessConfig	serverlessConfig() The serverless configuration for an endpoint.
ProductionVariant.Builder	toBuilder()
String	toString() Returns a string representation of this object.
String	variantName() The name of the production variant.

Methods inherited from class java.lang.Object

clone, finalize, getClass, notify, notifyAll, wait, wait, wait

Methods inherited from interface software.amazon.awssdk.utils.builder.ToCopyableBuilder

copy

Method Detail

variantName

public final String variantName()

The name of the production variant.

Returns:

The name of the production variant.

modelName

public final String modelName()

The name of the model that you want to host. This is the name that you specified when creating the model.

Returns:

The name of the model that you want to host. This is the name that you specified when creating the model.

initialInstanceCount

public final Integer initialInstanceCount()

Number of instances to launch initially.

Returns:

Number of instances to launch initially.

instanceType

public final ProductionVariantInstanceType instanceType()

The ML compute instance type.

If the service returns an enum value that is not available in the current SDK version, instanceType will return ProductionVariantInstanceType.UNKNOWN_TO_SDK_VERSION. The raw value returned by the service is available from instanceTypeAsString().

Returns:

The ML compute instance type.

See Also:

ProductionVariantInstanceType

instanceTypeAsString

public final String instanceTypeAsString()

The ML compute instance type.

If the service returns an enum value that is not available in the current SDK version, instanceType will return ProductionVariantInstanceType.UNKNOWN_TO_SDK_VERSION. The raw value returned by the service is available from instanceTypeAsString().

Returns:

The ML compute instance type.

See Also:

ProductionVariantInstanceType

initialVariantWeight

public final Float 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.

Returns:

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.

acceleratorType

public final ProductionVariantAcceleratorType 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, acceleratorType will return ProductionVariantAcceleratorType.UNKNOWN_TO_SDK_VERSION. The raw value returned by the service is available from acceleratorTypeAsString().

Returns:

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 Also:

ProductionVariantAcceleratorType

acceleratorTypeAsString

public final String acceleratorTypeAsString()

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, acceleratorType will return ProductionVariantAcceleratorType.UNKNOWN_TO_SDK_VERSION. The raw value returned by the service is available from acceleratorTypeAsString().

Returns:

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 Also:

ProductionVariantAcceleratorType

coreDumpConfig

public final ProductionVariantCoreDumpConfig coreDumpConfig()

Specifies configuration for a core dump from the model container when the process crashes.

Returns:

Specifies configuration for a core dump from the model container when the process crashes.

serverlessConfig

public final ProductionVariantServerlessConfig serverlessConfig()

The serverless configuration for an endpoint. Specifies a serverless endpoint configuration instead of an instance-based endpoint configuration.

Returns:

The serverless configuration for an endpoint. Specifies a serverless endpoint configuration instead of an instance-based endpoint configuration.

toBuilder

public ProductionVariant.Builder toBuilder()

Specified by:

toBuilder in interface ToCopyableBuilder<ProductionVariant.Builder,ProductionVariant>

builder

public static ProductionVariant.Builder builder()

serializableBuilderClass

public static Class<? extends ProductionVariant.Builder> serializableBuilderClass()

hashCode

public final int hashCode()

Overrides:

hashCode in class Object

equals

public final boolean equals(Object obj)

Overrides:

equals in class Object

equalsBySdkFields

public final boolean equalsBySdkFields(Object obj)

Specified by:

equalsBySdkFields in interface SdkPojo

toString

public final String toString()

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.

Overrides:

toString in class Object

getValueForField

public final <T> Optional<T> getValueForField(String fieldName,
                                              Class<T> clazz)

sdkFields

public final List<SdkField<?>> sdkFields()

Specified by:

sdkFields in interface SdkPojo