Class: AWSCDK::Sagemaker::CfnEndpointConfig::AsyncInferenceClientConfigProperty

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

Overview

Configures the behavior of the client used by SageMaker to interact with the model container during asynchronous inference.

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(max_concurrent_invocations_per_instance: nil) ⇒ AsyncInferenceClientConfigProperty

Returns a new instance of AsyncInferenceClientConfigProperty.

Parameters:

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

    The maximum number of concurrent requests sent by the SageMaker client to the model container.



653
654
655
656
# File 'sagemaker/cfn_endpoint_config.rb', line 653

def initialize(max_concurrent_invocations_per_instance: nil)
  @max_concurrent_invocations_per_instance = max_concurrent_invocations_per_instance
  Jsii::Type.check_type(@max_concurrent_invocations_per_instance, JSON.parse(Base64.strict_decode64("eyJwcmltaXRpdmUiOiJudW1iZXIifQ==")), "maxConcurrentInvocationsPerInstance") unless @max_concurrent_invocations_per_instance.nil?
end

Instance Attribute Details

#max_concurrent_invocations_per_instanceNumeric? (readonly)

The maximum number of concurrent requests sent by the SageMaker client to the model container.

If no value is provided, SageMaker will choose an optimal value for you.



664
665
666
# File 'sagemaker/cfn_endpoint_config.rb', line 664

def max_concurrent_invocations_per_instance
  @max_concurrent_invocations_per_instance
end

Class Method Details

.jsii_propertiesObject



666
667
668
669
670
# File 'sagemaker/cfn_endpoint_config.rb', line 666

def self.jsii_properties
  {
    :max_concurrent_invocations_per_instance => "maxConcurrentInvocationsPerInstance",
  }
end

Instance Method Details

#to_jsiiObject



672
673
674
675
676
677
678
# File 'sagemaker/cfn_endpoint_config.rb', line 672

def to_jsii
  result = {}
  result.merge!({
    "maxConcurrentInvocationsPerInstance" => @max_concurrent_invocations_per_instance,
  })
  result.compact
end