ElasticInference / Client / describe_accelerator_types

describe_accelerator_types#

ElasticInference.Client.describe_accelerator_types()#

Describes the accelerator types available in a given region, as well as their characteristics, such as memory and throughput.

February 15, 2023: Starting April 15, 2023, AWS will not onboard new customers to Amazon Elastic Inference (EI), and will help current customers migrate their workloads to options that offer better price and performance. After April 15, 2023, new customers will not be able to launch instances with Amazon EI accelerators in Amazon SageMaker, Amazon ECS, or Amazon EC2. However, customers who have used Amazon EI at least once during the past 30-day period are considered current customers and will be able to continue using the service.

See also: AWS API Documentation

Request Syntax

response = client.describe_accelerator_types()
Return type:

dict

Returns:

Response Syntax

{
    'acceleratorTypes': [
        {
            'acceleratorTypeName': 'string',
            'memoryInfo': {
                'sizeInMiB': 123
            },
            'throughputInfo': [
                {
                    'key': 'string',
                    'value': 123
                },
            ]
        },
    ]
}

Response Structure

  • (dict) –

    • acceleratorTypes (list) –

      The available accelerator types.

      • (dict) –

        The details of an Elastic Inference Accelerator type.

        • acceleratorTypeName (string) –

          The name of the Elastic Inference Accelerator type.

        • memoryInfo (dict) –

          The memory information of the Elastic Inference Accelerator type.

          • sizeInMiB (integer) –

            The size in mebibytes of the Elastic Inference Accelerator type.

        • throughputInfo (list) –

          The throughput information of the Elastic Inference Accelerator type.

          • (dict) –

            A throughput entry for an Elastic Inference Accelerator type.

            • key (string) –

              The throughput value of the Elastic Inference Accelerator type. It can assume the following values: TFLOPS16bit: the throughput expressed in 16bit TeraFLOPS. TFLOPS32bit: the throughput expressed in 32bit TeraFLOPS.

            • value (integer) –

              The throughput value of the Elastic Inference Accelerator type.

Exceptions