Class: Aws::SageMaker::Types::InferenceComponentComputeResourceRequirements

Inherits:

Struct

• Object
• Struct
• Aws::SageMaker::Types::InferenceComponentComputeResourceRequirements

Defined in:

gems/aws-sdk-sagemaker/lib/aws-sdk-sagemaker/types.rb

Overview

Defines the compute resources to allocate to run a model, plus any adapter models, that you assign to an inference component. These resources include CPU cores, accelerators, and memory.

See Also:

• AWS API Documentation

Constant Summary

SENSITIVE =

[]

Instance Attribute Summary

• #accelerator_partition_type ⇒ String

  The accelerator partition profile this inference component occupies; on NVIDIA GPUs this is a Multi-Instance GPU (MIG) profile such as mig-3g.40gb.

• #max_memory_required_in_mb ⇒ Integer

  The maximum MB of memory to allocate to run a model that you assign to an inference component.

• #min_memory_required_in_mb ⇒ Integer

  The minimum MB of memory to allocate to run a model that you assign to an inference component.

• #number_of_accelerator_devices_required ⇒ Float

  The number of accelerators to allocate to run a model that you assign to an inference component.

• #number_of_cpu_cores_required ⇒ Float

  The number of CPU cores to allocate to run a model that you assign to an inference component.

Instance Attribute Details

#accelerator_partition_type ⇒ String

The accelerator partition profile this inference component occupies; on NVIDIA GPUs this is a Multi-Instance GPU (MIG) profile such as mig-3g.40gb. It must be one of the partition profiles declared in the target endpoint's accelerator partition layout, and when set, NumberOfAcceleratorDevicesRequired must be 1. This field is required when the endpoint's production variant has an accelerator partition layout. For endpoints without a layout, omit this field to place the inference component on a whole accelerator.

Returns:

• (String)

# File 'gems/aws-sdk-sagemaker/lib/aws-sdk-sagemaker/types.rb', line 32316

class InferenceComponentComputeResourceRequirements < Struct.new(
  :number_of_cpu_cores_required,
  :number_of_accelerator_devices_required,
  :min_memory_required_in_mb,
  :max_memory_required_in_mb,
  :accelerator_partition_type)
  SENSITIVE = []
  include Aws::Structure
end

#max_memory_required_in_mb ⇒ Integer

The maximum MB of memory to allocate to run a model that you assign to an inference component.

Returns:

• (Integer)

# File 'gems/aws-sdk-sagemaker/lib/aws-sdk-sagemaker/types.rb', line 32316

class InferenceComponentComputeResourceRequirements < Struct.new(
  :number_of_cpu_cores_required,
  :number_of_accelerator_devices_required,
  :min_memory_required_in_mb,
  :max_memory_required_in_mb,
  :accelerator_partition_type)
  SENSITIVE = []
  include Aws::Structure
end

#min_memory_required_in_mb ⇒ Integer

The minimum MB of memory to allocate to run a model that you assign to an inference component.

Returns:

• (Integer)

# File 'gems/aws-sdk-sagemaker/lib/aws-sdk-sagemaker/types.rb', line 32316

class InferenceComponentComputeResourceRequirements < Struct.new(
  :number_of_cpu_cores_required,
  :number_of_accelerator_devices_required,
  :min_memory_required_in_mb,
  :max_memory_required_in_mb,
  :accelerator_partition_type)
  SENSITIVE = []
  include Aws::Structure
end

#number_of_accelerator_devices_required ⇒ Float

The number of accelerators to allocate to run a model that you assign to an inference component. Accelerators include GPUs and Amazon Web Services Inferentia.

Returns:

• (Float)

# File 'gems/aws-sdk-sagemaker/lib/aws-sdk-sagemaker/types.rb', line 32316

class InferenceComponentComputeResourceRequirements < Struct.new(
  :number_of_cpu_cores_required,
  :number_of_accelerator_devices_required,
  :min_memory_required_in_mb,
  :max_memory_required_in_mb,
  :accelerator_partition_type)
  SENSITIVE = []
  include Aws::Structure
end

#number_of_cpu_cores_required ⇒ Float

The number of CPU cores to allocate to run a model that you assign to an inference component.

Returns:

• (Float)

# File 'gems/aws-sdk-sagemaker/lib/aws-sdk-sagemaker/types.rb', line 32316

class InferenceComponentComputeResourceRequirements < Struct.new(
  :number_of_cpu_cores_required,
  :number_of_accelerator_devices_required,
  :min_memory_required_in_mb,
  :max_memory_required_in_mb,
  :accelerator_partition_type)
  SENSITIVE = []
  include Aws::Structure
end