Class: Aws::SageMaker::Types::AcceleratorPartitionLayout

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

Overview

A layout of accelerator partitions for a production variant. On NVIDIA GPUs, the partitions are Multi-Instance GPU (MIG) instances. SageMaker applies the layout to every accelerator on the variant's instance type. You can't change the layout of a running endpoint. To use a different layout, create a new endpoint.

See Also:

Constant Summary collapse

SENSITIVE = 
[]

Instance Attribute Summary collapse

Instance Attribute Details

#accelerator_partition_types ⇒ Array<String>

The list of partition profiles to carve on each accelerator that this layout applies to. On NVIDIA GPUs these are Multi-Instance GPU (MIG) profiles, for example ["mig-3g.40gb", "mig-4g.40gb"]. The order of the profiles doesn't change how the accelerator is partitioned. However, when you update an endpoint, a layout with the same profiles in a different order counts as a different layout, and the update is rejected. Repeat a profile to request more than one partition of that size: for example, ["mig-3g.40gb", "mig-3g.40gb"] requests two mig-3g.40gb partitions.

Returns:

  • (Array<String>) 


906
907
908
909
910
 
# File 'gems/aws-sdk-sagemaker/lib/aws-sdk-sagemaker/types.rb', line 906

class AcceleratorPartitionLayout < Struct.new(
  :accelerator_partition_types)
  SENSITIVE = []
  include Aws::Structure
end