Amazonka.SageMaker.Types.ProductionVariant

Documentation

data 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: newProductionVariant smart constructor.

Constructors

ProductionVariant'

Fields

• acceleratorType :: Maybe ProductionVariantAcceleratorType

  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.

• containerStartupHealthCheckTimeoutInSeconds :: Maybe Natural

  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.

• coreDumpConfig :: Maybe ProductionVariantCoreDumpConfig

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

• initialInstanceCount :: Maybe Natural

  Number of instances to launch initially.

• initialVariantWeight :: Maybe Double

  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.

• instanceType :: Maybe ProductionVariantInstanceType

  The ML compute instance type.

• modelDataDownloadTimeoutInSeconds :: Maybe Natural

  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.

• serverlessConfig :: Maybe ProductionVariantServerlessConfig

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

• volumeSizeInGB :: Maybe Natural

  The size, in GB, of the ML storage volume attached to individual inference instance associated with the production variant. Currenly only Amazon EBS gp2 storage volumes are supported.

• variantName :: Text

  The name of the production variant.

• modelName :: Text

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

Instances

FromJSON ProductionVariant

Defined in Amazonka.SageMaker.Types.ProductionVariant

Methods

parseJSON :: Value -> Parser ProductionVariant

parseJSONList :: Value -> Parser [ProductionVariant]

ToJSON ProductionVariant

Defined in Amazonka.SageMaker.Types.ProductionVariant

Methods

toJSON :: ProductionVariant -> Value

toEncoding :: ProductionVariant -> Encoding

toJSONList :: [ProductionVariant] -> Value

toEncodingList :: [ProductionVariant] -> Encoding

Generic ProductionVariant

Defined in Amazonka.SageMaker.Types.ProductionVariant

Associated Types

type Rep ProductionVariant :: Type -> Type

Methods

from :: ProductionVariant -> Rep ProductionVariant x

to :: Rep ProductionVariant x -> ProductionVariant

Read ProductionVariant

Defined in Amazonka.SageMaker.Types.ProductionVariant

Methods

readsPrec :: Int -> ReadS ProductionVariant

readList :: ReadS [ProductionVariant]

readPrec :: ReadPrec ProductionVariant

readListPrec :: ReadPrec [ProductionVariant]

Show ProductionVariant

Defined in Amazonka.SageMaker.Types.ProductionVariant

Methods

showsPrec :: Int -> ProductionVariant -> ShowS

show :: ProductionVariant -> String

showList :: [ProductionVariant] -> ShowS

NFData ProductionVariant

Defined in Amazonka.SageMaker.Types.ProductionVariant

Methods

rnf :: ProductionVariant -> ()

Eq ProductionVariant

Defined in Amazonka.SageMaker.Types.ProductionVariant

Methods

(==) :: ProductionVariant -> ProductionVariant -> Bool

(/=) :: ProductionVariant -> ProductionVariant -> Bool

Hashable ProductionVariant

Defined in Amazonka.SageMaker.Types.ProductionVariant

Methods

hashWithSalt :: Int -> ProductionVariant -> Int

hash :: ProductionVariant -> Int

type Rep ProductionVariant

Defined in Amazonka.SageMaker.Types.ProductionVariant

type Rep ProductionVariant = D1 ('MetaData "ProductionVariant" "Amazonka.SageMaker.Types.ProductionVariant" "amazonka-sagemaker-2.0-9SyrKZ4KqhsL1qX9u3ILA3" 'False) (C1 ('MetaCons "ProductionVariant'" 'PrefixI 'True) (((S1 ('MetaSel ('Just "acceleratorType") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe ProductionVariantAcceleratorType)) :*: S1 ('MetaSel ('Just "containerStartupHealthCheckTimeoutInSeconds") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Natural))) :*: (S1 ('MetaSel ('Just "coreDumpConfig") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe ProductionVariantCoreDumpConfig)) :*: (S1 ('MetaSel ('Just "initialInstanceCount") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Natural)) :*: S1 ('MetaSel ('Just "initialVariantWeight") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Double))))) :*: ((S1 ('MetaSel ('Just "instanceType") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe ProductionVariantInstanceType)) :*: (S1 ('MetaSel ('Just "modelDataDownloadTimeoutInSeconds") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Natural)) :*: S1 ('MetaSel ('Just "serverlessConfig") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe ProductionVariantServerlessConfig)))) :*: (S1 ('MetaSel ('Just "volumeSizeInGB") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Natural)) :*: (S1 ('MetaSel ('Just "variantName") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 Text) :*: S1 ('MetaSel ('Just "modelName") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 Text))))))

newProductionVariant

Arguments

:: Text

$sel:variantName:ProductionVariant'

-> Text

$sel:modelName:ProductionVariant'

-> ProductionVariant

Create a value of ProductionVariant with all optional fields omitted.

Use generic-lens or optics to modify other optional fields.

The following record fields are available, with the corresponding lenses provided for backwards compatibility:

$sel:acceleratorType:ProductionVariant', productionVariant_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.

$sel:containerStartupHealthCheckTimeoutInSeconds:ProductionVariant', productionVariant_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.

$sel:coreDumpConfig:ProductionVariant', productionVariant_coreDumpConfig - Specifies configuration for a core dump from the model container when the process crashes.

$sel:initialInstanceCount:ProductionVariant', productionVariant_initialInstanceCount - Number of instances to launch initially.

$sel:initialVariantWeight:ProductionVariant', productionVariant_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.

$sel:instanceType:ProductionVariant', productionVariant_instanceType - The ML compute instance type.

$sel:modelDataDownloadTimeoutInSeconds:ProductionVariant', productionVariant_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.

$sel:serverlessConfig:ProductionVariant', productionVariant_serverlessConfig - The serverless configuration for an endpoint. Specifies a serverless endpoint configuration instead of an instance-based endpoint configuration.

$sel:volumeSizeInGB:ProductionVariant', productionVariant_volumeSizeInGB - The size, in GB, of the ML storage volume attached to individual inference instance associated with the production variant. Currenly only Amazon EBS gp2 storage volumes are supported.

$sel:variantName:ProductionVariant', productionVariant_variantName - The name of the production variant.

$sel:modelName:ProductionVariant', productionVariant_modelName - The name of the model that you want to host. This is the name that you specified when creating the model.

productionVariant_acceleratorType :: Lens' ProductionVariant (Maybe ProductionVariantAcceleratorType)

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.

productionVariant_containerStartupHealthCheckTimeoutInSeconds :: Lens' ProductionVariant (Maybe Natural)

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.

productionVariant_coreDumpConfig :: Lens' ProductionVariant (Maybe ProductionVariantCoreDumpConfig)

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

productionVariant_initialInstanceCount :: Lens' ProductionVariant (Maybe Natural)

Number of instances to launch initially.

productionVariant_initialVariantWeight :: Lens' ProductionVariant (Maybe Double)

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.

productionVariant_instanceType :: Lens' ProductionVariant (Maybe ProductionVariantInstanceType)

The ML compute instance type.

productionVariant_modelDataDownloadTimeoutInSeconds :: Lens' ProductionVariant (Maybe Natural)

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.

productionVariant_serverlessConfig :: Lens' ProductionVariant (Maybe ProductionVariantServerlessConfig)

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

productionVariant_volumeSizeInGB :: Lens' ProductionVariant (Maybe Natural)

The size, in GB, of the ML storage volume attached to individual inference instance associated with the production variant. Currenly only Amazon EBS gp2 storage volumes are supported.

productionVariant_variantName :: Lens' ProductionVariant Text

The name of the production variant.

productionVariant_modelName :: Lens' ProductionVariant Text

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