Class: AWSCDK::Sagemaker::CfnEndpointConfig::ServerlessConfigProperty

Inherits:
Jsii::Struct
  • Object
show all
Defined in:
sagemaker/cfn_endpoint_config.rb

Overview

Specifies the serverless configuration for an endpoint variant.

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(max_concurrency:, memory_size_in_mb:, provisioned_concurrency: nil) ⇒ ServerlessConfigProperty

Returns a new instance of ServerlessConfigProperty.

Parameters:

  • max_concurrency (Numeric)

    The maximum number of concurrent invocations your serverless endpoint can process.

  • memory_size_in_mb (Numeric)

    The memory size of your serverless endpoint.

  • provisioned_concurrency (Numeric, nil) (defaults to: nil)

    The amount of provisioned concurrency to allocate for the serverless endpoint.



1810
1811
1812
1813
1814
1815
1816
1817
# File 'sagemaker/cfn_endpoint_config.rb', line 1810

def initialize(max_concurrency:, memory_size_in_mb:, provisioned_concurrency: nil)
  @max_concurrency = max_concurrency
  Jsii::Type.check_type(@max_concurrency, JSON.parse(Base64.strict_decode64("eyJwcmltaXRpdmUiOiJudW1iZXIifQ==")), "maxConcurrency")
  @memory_size_in_mb = memory_size_in_mb
  Jsii::Type.check_type(@memory_size_in_mb, JSON.parse(Base64.strict_decode64("eyJwcmltaXRpdmUiOiJudW1iZXIifQ==")), "memorySizeInMb")
  @provisioned_concurrency = provisioned_concurrency
  Jsii::Type.check_type(@provisioned_concurrency, JSON.parse(Base64.strict_decode64("eyJwcmltaXRpdmUiOiJudW1iZXIifQ==")), "provisionedConcurrency") unless @provisioned_concurrency.nil?
end

Instance Attribute Details

#max_concurrencyNumeric (readonly)

The maximum number of concurrent invocations your serverless endpoint can process.



1823
1824
1825
# File 'sagemaker/cfn_endpoint_config.rb', line 1823

def max_concurrency
  @max_concurrency
end

#memory_size_in_mbNumeric (readonly)

The memory size of your serverless endpoint.

Valid values are in 1 GB increments: 1024 MB, 2048 MB, 3072 MB, 4096 MB, 5120 MB, or 6144 MB.



1830
1831
1832
# File 'sagemaker/cfn_endpoint_config.rb', line 1830

def memory_size_in_mb
  @memory_size_in_mb
end

#provisioned_concurrencyNumeric? (readonly)

The amount of provisioned concurrency to allocate for the serverless endpoint.

Should be less than or equal to MaxConcurrency .

This field is not supported for serverless endpoint recommendations for Inference Recommender jobs. For more information about creating an Inference Recommender job, see CreateInferenceRecommendationsJobs .



1839
1840
1841
# File 'sagemaker/cfn_endpoint_config.rb', line 1839

def provisioned_concurrency
  @provisioned_concurrency
end

Class Method Details

.jsii_propertiesObject



1841
1842
1843
1844
1845
1846
1847
# File 'sagemaker/cfn_endpoint_config.rb', line 1841

def self.jsii_properties
  {
    :max_concurrency => "maxConcurrency",
    :memory_size_in_mb => "memorySizeInMb",
    :provisioned_concurrency => "provisionedConcurrency",
  }
end

Instance Method Details

#to_jsiiObject



1849
1850
1851
1852
1853
1854
1855
1856
1857
# File 'sagemaker/cfn_endpoint_config.rb', line 1849

def to_jsii
  result = {}
  result.merge!({
    "maxConcurrency" => @max_concurrency,
    "memorySizeInMb" => @memory_size_in_mb,
    "provisionedConcurrency" => @provisioned_concurrency,
  })
  result.compact
end