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

Inherits:

Struct

Object
Struct
Aws::SageMaker::Types::ProductionVariant

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.

Constant Summary collapse

SENSITIVE =

[]

Instance Attribute Summary collapse

#accelerator_type ⇒ String
This parameter is no longer supported.
#capacity_reservation_config ⇒ Types::ProductionVariantCapacityReservationConfig
Settings for the capacity reservation for the compute instances that SageMaker AI reserves for an endpoint.
#container_startup_health_check_timeout_in_seconds ⇒ Integer
The timeout value, in seconds, for your inference container to pass health check by SageMaker Hosting.
#core_dump_config ⇒ Types::ProductionVariantCoreDumpConfig
Specifies configuration for a core dump from the model container when the process crashes.
#enable_ssm_access ⇒ Boolean
You can use this parameter to turn on native Amazon Web Services Systems Manager (SSM) access for a production variant behind an endpoint.
#inference_ami_version ⇒ String
Specifies an option from a collection of preconfigured Amazon Machine Image (AMI) images.
#initial_instance_count ⇒ Integer
Number of instances to launch initially.
#initial_variant_weight ⇒ Float
Determines initial traffic distribution among all of the models that you specify in the endpoint configuration.
#instance_pools ⇒ Array<Types::InstancePool>
A list of instance pools for the production variant.
#instance_type ⇒ String
The ML compute instance type.
#managed_instance_scaling ⇒ Types::ProductionVariantManagedInstanceScaling
Settings that control the range in the number of instances that the endpoint provisions as it scales up or down to accommodate traffic.
#model_data_download_timeout_in_seconds ⇒ Integer
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.
#model_name ⇒ String
The name of the model that you want to host.
#routing_config ⇒ Types::ProductionVariantRoutingConfig
Settings that control how the endpoint routes incoming traffic to the instances that the endpoint hosts.
#serverless_config ⇒ Types::ProductionVariantServerlessConfig
The serverless configuration for an endpoint.
#variant_instance_provision_timeout_in_seconds ⇒ Integer
The timeout value, in seconds, for provisioning instances for the production variant.
#variant_name ⇒ String
The name of the production variant.
#volume_size_in_gb ⇒ Integer
The size, in GB, of the ML storage volume attached to individual inference instance associated with the production variant.

Instance Attribute Details

#accelerator_type ⇒ `String`

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)

# File 'lib/aws-sdk-sagemaker/types.rb', line 47376

class ProductionVariant < Struct.new(
  :variant_name,
  :model_name,
  :initial_instance_count,
  :instance_type,
  :instance_pools,
  :variant_instance_provision_timeout_in_seconds,
  :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,
  :capacity_reservation_config)
  SENSITIVE = []
  include Aws::Structure
end

#capacity_reservation_config ⇒ `Types::ProductionVariantCapacityReservationConfig`

Settings for the capacity reservation for the compute instances that SageMaker AI reserves for an endpoint.

Returns:

(Types::ProductionVariantCapacityReservationConfig)

# File 'lib/aws-sdk-sagemaker/types.rb', line 47376

class ProductionVariant < Struct.new(
  :variant_name,
  :model_name,
  :initial_instance_count,
  :instance_type,
  :instance_pools,
  :variant_instance_provision_timeout_in_seconds,
  :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,
  :capacity_reservation_config)
  SENSITIVE = []
  include Aws::Structure
end

#container_startup_health_check_timeout_in_seconds ⇒ `Integer`

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.

Returns:

(Integer)

# File 'lib/aws-sdk-sagemaker/types.rb', line 47376

class ProductionVariant < Struct.new(
  :variant_name,
  :model_name,
  :initial_instance_count,
  :instance_type,
  :instance_pools,
  :variant_instance_provision_timeout_in_seconds,
  :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,
  :capacity_reservation_config)
  SENSITIVE = []
  include Aws::Structure
end

#core_dump_config ⇒ `Types::ProductionVariantCoreDumpConfig`

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

Returns:

(Types::ProductionVariantCoreDumpConfig)

# File 'lib/aws-sdk-sagemaker/types.rb', line 47376

class ProductionVariant < Struct.new(
  :variant_name,
  :model_name,
  :initial_instance_count,
  :instance_type,
  :instance_pools,
  :variant_instance_provision_timeout_in_seconds,
  :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,
  :capacity_reservation_config)
  SENSITIVE = []
  include Aws::Structure
end

#enable_ssm_access ⇒ `Boolean`

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)

# File 'lib/aws-sdk-sagemaker/types.rb', line 47376

class ProductionVariant < Struct.new(
  :variant_name,
  :model_name,
  :initial_instance_count,
  :instance_type,
  :instance_pools,
  :variant_instance_provision_timeout_in_seconds,
  :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,
  :capacity_reservation_config)
  SENSITIVE = []
  include Aws::Structure
end

#inference_ami_version ⇒ `String`

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

* CUDA version: 12.2

al2-ami-sagemaker-inference-gpu-2-1 : * Accelerator: GPU

* NVIDIA driver version: 535

* CUDA version: 12.2

* NVIDIA Container Toolkit with disabled CUDA-compat mounting

al2-ami-sagemaker-inference-gpu-3-1 : * Accelerator: GPU

* NVIDIA driver version: 550

* CUDA version: 12.4

* NVIDIA Container Toolkit with disabled CUDA-compat mounting

al2023-ami-sagemaker-inference-gpu-4-1 : * Accelerator: GPU

* NVIDIA driver version: 580

* CUDA version: 13.0

* NVIDIA Container Toolkit with disabled CUDA-compat mounting

al2-ami-sagemaker-inference-neuron-2 : * Accelerator: Inferentia2 and Trainium

* Neuron driver version: 2.19

Returns:

(String)

# File 'lib/aws-sdk-sagemaker/types.rb', line 47376

class ProductionVariant < Struct.new(
  :variant_name,
  :model_name,
  :initial_instance_count,
  :instance_type,
  :instance_pools,
  :variant_instance_provision_timeout_in_seconds,
  :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,
  :capacity_reservation_config)
  SENSITIVE = []
  include Aws::Structure
end

#initial_instance_count ⇒ `Integer`

Number of instances to launch initially.

Returns:

(Integer)

# File 'lib/aws-sdk-sagemaker/types.rb', line 47376

class ProductionVariant < Struct.new(
  :variant_name,
  :model_name,
  :initial_instance_count,
  :instance_type,
  :instance_pools,
  :variant_instance_provision_timeout_in_seconds,
  :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,
  :capacity_reservation_config)
  SENSITIVE = []
  include Aws::Structure
end

#initial_variant_weight ⇒ `Float`

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)

# File 'lib/aws-sdk-sagemaker/types.rb', line 47376

class ProductionVariant < Struct.new(
  :variant_name,
  :model_name,
  :initial_instance_count,
  :instance_type,
  :instance_pools,
  :variant_instance_provision_timeout_in_seconds,
  :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,
  :capacity_reservation_config)
  SENSITIVE = []
  include Aws::Structure
end

#instance_pools ⇒ `Array<Types::InstancePool>`

A list of instance pools for the production variant. Each instance pool specifies an instance type and its priority for provisioning. Use instance pools to configure heterogeneous endpoints that deploy models across multiple instance types.

Returns:

(Array<Types::InstancePool>)

# File 'lib/aws-sdk-sagemaker/types.rb', line 47376

class ProductionVariant < Struct.new(
  :variant_name,
  :model_name,
  :initial_instance_count,
  :instance_type,
  :instance_pools,
  :variant_instance_provision_timeout_in_seconds,
  :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,
  :capacity_reservation_config)
  SENSITIVE = []
  include Aws::Structure
end

#instance_type ⇒ `String`

The ML compute instance type.

Returns:

(String)

# File 'lib/aws-sdk-sagemaker/types.rb', line 47376

class ProductionVariant < Struct.new(
  :variant_name,
  :model_name,
  :initial_instance_count,
  :instance_type,
  :instance_pools,
  :variant_instance_provision_timeout_in_seconds,
  :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,
  :capacity_reservation_config)
  SENSITIVE = []
  include Aws::Structure
end

#managed_instance_scaling ⇒ `Types::ProductionVariantManagedInstanceScaling`

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

Returns:

(Types::ProductionVariantManagedInstanceScaling)

# File 'lib/aws-sdk-sagemaker/types.rb', line 47376

class ProductionVariant < Struct.new(
  :variant_name,
  :model_name,
  :initial_instance_count,
  :instance_type,
  :instance_pools,
  :variant_instance_provision_timeout_in_seconds,
  :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,
  :capacity_reservation_config)
  SENSITIVE = []
  include Aws::Structure
end

#model_data_download_timeout_in_seconds ⇒ `Integer`

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)

# File 'lib/aws-sdk-sagemaker/types.rb', line 47376

class ProductionVariant < Struct.new(
  :variant_name,
  :model_name,
  :initial_instance_count,
  :instance_type,
  :instance_pools,
  :variant_instance_provision_timeout_in_seconds,
  :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,
  :capacity_reservation_config)
  SENSITIVE = []
  include Aws::Structure
end

#model_name ⇒ `String`

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

Returns:

(String)

# File 'lib/aws-sdk-sagemaker/types.rb', line 47376

class ProductionVariant < Struct.new(
  :variant_name,
  :model_name,
  :initial_instance_count,
  :instance_type,
  :instance_pools,
  :variant_instance_provision_timeout_in_seconds,
  :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,
  :capacity_reservation_config)
  SENSITIVE = []
  include Aws::Structure
end

#routing_config ⇒ `Types::ProductionVariantRoutingConfig`

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

Returns:

(Types::ProductionVariantRoutingConfig)

# File 'lib/aws-sdk-sagemaker/types.rb', line 47376

class ProductionVariant < Struct.new(
  :variant_name,
  :model_name,
  :initial_instance_count,
  :instance_type,
  :instance_pools,
  :variant_instance_provision_timeout_in_seconds,
  :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,
  :capacity_reservation_config)
  SENSITIVE = []
  include Aws::Structure
end

#serverless_config ⇒ `Types::ProductionVariantServerlessConfig`

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

Returns:

(Types::ProductionVariantServerlessConfig)

# File 'lib/aws-sdk-sagemaker/types.rb', line 47376

class ProductionVariant < Struct.new(
  :variant_name,
  :model_name,
  :initial_instance_count,
  :instance_type,
  :instance_pools,
  :variant_instance_provision_timeout_in_seconds,
  :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,
  :capacity_reservation_config)
  SENSITIVE = []
  include Aws::Structure
end

#variant_instance_provision_timeout_in_seconds ⇒ `Integer`

The timeout value, in seconds, for provisioning instances for the production variant. When SageMaker encounters an insufficient capacity error while provisioning instances, it retries with the next instance pool (if configured) or waits until the timeout expires. This timeout applies only to capacity provisioning and does not include the time for model download or container startup.

Valid values: 300 to 3600.

Returns:

(Integer)

# File 'lib/aws-sdk-sagemaker/types.rb', line 47376

class ProductionVariant < Struct.new(
  :variant_name,
  :model_name,
  :initial_instance_count,
  :instance_type,
  :instance_pools,
  :variant_instance_provision_timeout_in_seconds,
  :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,
  :capacity_reservation_config)
  SENSITIVE = []
  include Aws::Structure
end

#variant_name ⇒ `String`

The name of the production variant.

Returns:

(String)

# File 'lib/aws-sdk-sagemaker/types.rb', line 47376

class ProductionVariant < Struct.new(
  :variant_name,
  :model_name,
  :initial_instance_count,
  :instance_type,
  :instance_pools,
  :variant_instance_provision_timeout_in_seconds,
  :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,
  :capacity_reservation_config)
  SENSITIVE = []
  include Aws::Structure
end

#volume_size_in_gb ⇒ `Integer`

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)

# File 'lib/aws-sdk-sagemaker/types.rb', line 47376

class ProductionVariant < Struct.new(
  :variant_name,
  :model_name,
  :initial_instance_count,
  :instance_type,
  :instance_pools,
  :variant_instance_provision_timeout_in_seconds,
  :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,
  :capacity_reservation_config)
  SENSITIVE = []
  include Aws::Structure
end

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

Overview

Constant Summary collapse

Instance Attribute Summary collapse

Instance Attribute Details

#accelerator_type ⇒ String

#capacity_reservation_config ⇒ Types::ProductionVariantCapacityReservationConfig

#container_startup_health_check_timeout_in_seconds ⇒ Integer

#core_dump_config ⇒ Types::ProductionVariantCoreDumpConfig

#enable_ssm_access ⇒ Boolean

#inference_ami_version ⇒ String

#initial_instance_count ⇒ Integer

#initial_variant_weight ⇒ Float

#instance_pools ⇒ Array<Types::InstancePool>

#instance_type ⇒ String

#managed_instance_scaling ⇒ Types::ProductionVariantManagedInstanceScaling

#model_data_download_timeout_in_seconds ⇒ Integer

#model_name ⇒ String

#routing_config ⇒ Types::ProductionVariantRoutingConfig

#serverless_config ⇒ Types::ProductionVariantServerlessConfig

#variant_instance_provision_timeout_in_seconds ⇒ Integer

#variant_name ⇒ String

#volume_size_in_gb ⇒ Integer

#accelerator_type ⇒ `String`

#capacity_reservation_config ⇒ `Types::ProductionVariantCapacityReservationConfig`

#container_startup_health_check_timeout_in_seconds ⇒ `Integer`

#core_dump_config ⇒ `Types::ProductionVariantCoreDumpConfig`

#enable_ssm_access ⇒ `Boolean`

#inference_ami_version ⇒ `String`

#initial_instance_count ⇒ `Integer`

#initial_variant_weight ⇒ `Float`

#instance_pools ⇒ `Array<Types::InstancePool>`

#instance_type ⇒ `String`

#managed_instance_scaling ⇒ `Types::ProductionVariantManagedInstanceScaling`

#model_data_download_timeout_in_seconds ⇒ `Integer`

#model_name ⇒ `String`

#routing_config ⇒ `Types::ProductionVariantRoutingConfig`

#serverless_config ⇒ `Types::ProductionVariantServerlessConfig`

#variant_instance_provision_timeout_in_seconds ⇒ `Integer`

#variant_name ⇒ `String`

#volume_size_in_gb ⇒ `Integer`