Class: Aws::SageMaker::Types::ProductionVariant

Inherits:
Struct
  • Object
show all
Includes:
Aws::Structure
Defined in:
lib/aws-sdk-sagemaker/types.rb

Overview

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].

[1]: docs.aws.amazon.com/sagemaker/latest/dg/model-ab-testing.html

Constant Summary collapse

SENSITIVE =
[]

Instance Attribute Summary collapse

Instance Attribute Details

#accelerator_typeString

This parameter is no longer supported. Elastic Inference (EI) is no longer available.

This parameter was used to specify the size of the EI instance to use for the production variant.

Returns:

  • (String)


37459
37460
37461
37462
37463
37464
37465
37466
37467
37468
37469
37470
37471
37472
37473
37474
37475
37476
37477
# File 'lib/aws-sdk-sagemaker/types.rb', line 37459

class ProductionVariant < Struct.new(
  :variant_name,
  :model_name,
  :initial_instance_count,
  :instance_type,
  :initial_variant_weight,
  :accelerator_type,
  :core_dump_config,
  :serverless_config,
  :volume_size_in_gb,
  :model_data_download_timeout_in_seconds,
  :container_startup_health_check_timeout_in_seconds,
  :enable_ssm_access,
  :managed_instance_scaling,
  :routing_config,
  :inference_ami_version)
  SENSITIVE = []
  include Aws::Structure
end

#container_startup_health_check_timeout_in_secondsInteger

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].

[1]: docs.aws.amazon.com/sagemaker/latest/dg/your-algorithms-inference-code.html#your-algorithms-inference-algo-ping-requests

Returns:

  • (Integer)


37459
37460
37461
37462
37463
37464
37465
37466
37467
37468
37469
37470
37471
37472
37473
37474
37475
37476
37477
# File 'lib/aws-sdk-sagemaker/types.rb', line 37459

class ProductionVariant < Struct.new(
  :variant_name,
  :model_name,
  :initial_instance_count,
  :instance_type,
  :initial_variant_weight,
  :accelerator_type,
  :core_dump_config,
  :serverless_config,
  :volume_size_in_gb,
  :model_data_download_timeout_in_seconds,
  :container_startup_health_check_timeout_in_seconds,
  :enable_ssm_access,
  :managed_instance_scaling,
  :routing_config,
  :inference_ami_version)
  SENSITIVE = []
  include Aws::Structure
end

#core_dump_configTypes::ProductionVariantCoreDumpConfig

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



37459
37460
37461
37462
37463
37464
37465
37466
37467
37468
37469
37470
37471
37472
37473
37474
37475
37476
37477
# File 'lib/aws-sdk-sagemaker/types.rb', line 37459

class ProductionVariant < Struct.new(
  :variant_name,
  :model_name,
  :initial_instance_count,
  :instance_type,
  :initial_variant_weight,
  :accelerator_type,
  :core_dump_config,
  :serverless_config,
  :volume_size_in_gb,
  :model_data_download_timeout_in_seconds,
  :container_startup_health_check_timeout_in_seconds,
  :enable_ssm_access,
  :managed_instance_scaling,
  :routing_config,
  :inference_ami_version)
  SENSITIVE = []
  include Aws::Structure
end

#enable_ssm_accessBoolean

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`.

Returns:

  • (Boolean)


37459
37460
37461
37462
37463
37464
37465
37466
37467
37468
37469
37470
37471
37472
37473
37474
37475
37476
37477
# File 'lib/aws-sdk-sagemaker/types.rb', line 37459

class ProductionVariant < Struct.new(
  :variant_name,
  :model_name,
  :initial_instance_count,
  :instance_type,
  :initial_variant_weight,
  :accelerator_type,
  :core_dump_config,
  :serverless_config,
  :volume_size_in_gb,
  :model_data_download_timeout_in_seconds,
  :container_startup_health_check_timeout_in_seconds,
  :enable_ssm_access,
  :managed_instance_scaling,
  :routing_config,
  :inference_ami_version)
  SENSITIVE = []
  include Aws::Structure
end

#inference_ami_versionString

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.*

Returns:

  • (String)


37459
37460
37461
37462
37463
37464
37465
37466
37467
37468
37469
37470
37471
37472
37473
37474
37475
37476
37477
# File 'lib/aws-sdk-sagemaker/types.rb', line 37459

class ProductionVariant < Struct.new(
  :variant_name,
  :model_name,
  :initial_instance_count,
  :instance_type,
  :initial_variant_weight,
  :accelerator_type,
  :core_dump_config,
  :serverless_config,
  :volume_size_in_gb,
  :model_data_download_timeout_in_seconds,
  :container_startup_health_check_timeout_in_seconds,
  :enable_ssm_access,
  :managed_instance_scaling,
  :routing_config,
  :inference_ami_version)
  SENSITIVE = []
  include Aws::Structure
end

#initial_instance_countInteger

Number of instances to launch initially.

Returns:

  • (Integer)


37459
37460
37461
37462
37463
37464
37465
37466
37467
37468
37469
37470
37471
37472
37473
37474
37475
37476
37477
# File 'lib/aws-sdk-sagemaker/types.rb', line 37459

class ProductionVariant < Struct.new(
  :variant_name,
  :model_name,
  :initial_instance_count,
  :instance_type,
  :initial_variant_weight,
  :accelerator_type,
  :core_dump_config,
  :serverless_config,
  :volume_size_in_gb,
  :model_data_download_timeout_in_seconds,
  :container_startup_health_check_timeout_in_seconds,
  :enable_ssm_access,
  :managed_instance_scaling,
  :routing_config,
  :inference_ami_version)
  SENSITIVE = []
  include Aws::Structure
end

#initial_variant_weightFloat

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:

  • (Float)


37459
37460
37461
37462
37463
37464
37465
37466
37467
37468
37469
37470
37471
37472
37473
37474
37475
37476
37477
# File 'lib/aws-sdk-sagemaker/types.rb', line 37459

class ProductionVariant < Struct.new(
  :variant_name,
  :model_name,
  :initial_instance_count,
  :instance_type,
  :initial_variant_weight,
  :accelerator_type,
  :core_dump_config,
  :serverless_config,
  :volume_size_in_gb,
  :model_data_download_timeout_in_seconds,
  :container_startup_health_check_timeout_in_seconds,
  :enable_ssm_access,
  :managed_instance_scaling,
  :routing_config,
  :inference_ami_version)
  SENSITIVE = []
  include Aws::Structure
end

#instance_typeString

The ML compute instance type.

Returns:

  • (String)


37459
37460
37461
37462
37463
37464
37465
37466
37467
37468
37469
37470
37471
37472
37473
37474
37475
37476
37477
# File 'lib/aws-sdk-sagemaker/types.rb', line 37459

class ProductionVariant < Struct.new(
  :variant_name,
  :model_name,
  :initial_instance_count,
  :instance_type,
  :initial_variant_weight,
  :accelerator_type,
  :core_dump_config,
  :serverless_config,
  :volume_size_in_gb,
  :model_data_download_timeout_in_seconds,
  :container_startup_health_check_timeout_in_seconds,
  :enable_ssm_access,
  :managed_instance_scaling,
  :routing_config,
  :inference_ami_version)
  SENSITIVE = []
  include Aws::Structure
end

#managed_instance_scalingTypes::ProductionVariantManagedInstanceScaling

Settings that control the range in the number of instances that the endpoint provisions as it scales up or down to accommodate traffic.



37459
37460
37461
37462
37463
37464
37465
37466
37467
37468
37469
37470
37471
37472
37473
37474
37475
37476
37477
# File 'lib/aws-sdk-sagemaker/types.rb', line 37459

class ProductionVariant < Struct.new(
  :variant_name,
  :model_name,
  :initial_instance_count,
  :instance_type,
  :initial_variant_weight,
  :accelerator_type,
  :core_dump_config,
  :serverless_config,
  :volume_size_in_gb,
  :model_data_download_timeout_in_seconds,
  :container_startup_health_check_timeout_in_seconds,
  :enable_ssm_access,
  :managed_instance_scaling,
  :routing_config,
  :inference_ami_version)
  SENSITIVE = []
  include Aws::Structure
end

#model_data_download_timeout_in_secondsInteger

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.

Returns:

  • (Integer)


37459
37460
37461
37462
37463
37464
37465
37466
37467
37468
37469
37470
37471
37472
37473
37474
37475
37476
37477
# File 'lib/aws-sdk-sagemaker/types.rb', line 37459

class ProductionVariant < Struct.new(
  :variant_name,
  :model_name,
  :initial_instance_count,
  :instance_type,
  :initial_variant_weight,
  :accelerator_type,
  :core_dump_config,
  :serverless_config,
  :volume_size_in_gb,
  :model_data_download_timeout_in_seconds,
  :container_startup_health_check_timeout_in_seconds,
  :enable_ssm_access,
  :managed_instance_scaling,
  :routing_config,
  :inference_ami_version)
  SENSITIVE = []
  include Aws::Structure
end

#model_nameString

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

Returns:

  • (String)


37459
37460
37461
37462
37463
37464
37465
37466
37467
37468
37469
37470
37471
37472
37473
37474
37475
37476
37477
# File 'lib/aws-sdk-sagemaker/types.rb', line 37459

class ProductionVariant < Struct.new(
  :variant_name,
  :model_name,
  :initial_instance_count,
  :instance_type,
  :initial_variant_weight,
  :accelerator_type,
  :core_dump_config,
  :serverless_config,
  :volume_size_in_gb,
  :model_data_download_timeout_in_seconds,
  :container_startup_health_check_timeout_in_seconds,
  :enable_ssm_access,
  :managed_instance_scaling,
  :routing_config,
  :inference_ami_version)
  SENSITIVE = []
  include Aws::Structure
end

#routing_configTypes::ProductionVariantRoutingConfig

Settings that control how the endpoint routes incoming traffic to the instances that the endpoint hosts.



37459
37460
37461
37462
37463
37464
37465
37466
37467
37468
37469
37470
37471
37472
37473
37474
37475
37476
37477
# File 'lib/aws-sdk-sagemaker/types.rb', line 37459

class ProductionVariant < Struct.new(
  :variant_name,
  :model_name,
  :initial_instance_count,
  :instance_type,
  :initial_variant_weight,
  :accelerator_type,
  :core_dump_config,
  :serverless_config,
  :volume_size_in_gb,
  :model_data_download_timeout_in_seconds,
  :container_startup_health_check_timeout_in_seconds,
  :enable_ssm_access,
  :managed_instance_scaling,
  :routing_config,
  :inference_ami_version)
  SENSITIVE = []
  include Aws::Structure
end

#serverless_configTypes::ProductionVariantServerlessConfig

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



37459
37460
37461
37462
37463
37464
37465
37466
37467
37468
37469
37470
37471
37472
37473
37474
37475
37476
37477
# File 'lib/aws-sdk-sagemaker/types.rb', line 37459

class ProductionVariant < Struct.new(
  :variant_name,
  :model_name,
  :initial_instance_count,
  :instance_type,
  :initial_variant_weight,
  :accelerator_type,
  :core_dump_config,
  :serverless_config,
  :volume_size_in_gb,
  :model_data_download_timeout_in_seconds,
  :container_startup_health_check_timeout_in_seconds,
  :enable_ssm_access,
  :managed_instance_scaling,
  :routing_config,
  :inference_ami_version)
  SENSITIVE = []
  include Aws::Structure
end

#variant_nameString

The name of the production variant.

Returns:

  • (String)


37459
37460
37461
37462
37463
37464
37465
37466
37467
37468
37469
37470
37471
37472
37473
37474
37475
37476
37477
# File 'lib/aws-sdk-sagemaker/types.rb', line 37459

class ProductionVariant < Struct.new(
  :variant_name,
  :model_name,
  :initial_instance_count,
  :instance_type,
  :initial_variant_weight,
  :accelerator_type,
  :core_dump_config,
  :serverless_config,
  :volume_size_in_gb,
  :model_data_download_timeout_in_seconds,
  :container_startup_health_check_timeout_in_seconds,
  :enable_ssm_access,
  :managed_instance_scaling,
  :routing_config,
  :inference_ami_version)
  SENSITIVE = []
  include Aws::Structure
end

#volume_size_in_gbInteger

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.

Returns:

  • (Integer)


37459
37460
37461
37462
37463
37464
37465
37466
37467
37468
37469
37470
37471
37472
37473
37474
37475
37476
37477
# File 'lib/aws-sdk-sagemaker/types.rb', line 37459

class ProductionVariant < Struct.new(
  :variant_name,
  :model_name,
  :initial_instance_count,
  :instance_type,
  :initial_variant_weight,
  :accelerator_type,
  :core_dump_config,
  :serverless_config,
  :volume_size_in_gb,
  :model_data_download_timeout_in_seconds,
  :container_startup_health_check_timeout_in_seconds,
  :enable_ssm_access,
  :managed_instance_scaling,
  :routing_config,
  :inference_ami_version)
  SENSITIVE = []
  include Aws::Structure
end