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.

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

• ElasticInference.Client.exceptions.InternalServerException