Serverless Inference — sagemaker 2.247.0 documentation (original) (raw)

This module contains classes related to Amazon Sagemaker Serverless Inference

This module contains code related to the ServerlessInferenceConfig class.

Codes are used for configuring serverless inference endpoint. Use it when deploying the model to the endpoints.

class sagemaker.serverless.serverless_inference_config.ServerlessInferenceConfig(memory_size_in_mb=2048, max_concurrency=5, provisioned_concurrency=None)

Bases: object

Configuration object passed in when deploying models to Amazon SageMaker Endpoints.

This object specifies configuration related to serverless endpoint. Use this configuration when trying to create serverless endpoint and make serverless inference

Initialize a ServerlessInferenceConfig object for serverless inference configuration.

Parameters:

• memory_size_in_mb (int) – Optional. The memory size of your serverless endpoint. Valid values are in 1 GB increments: 1024 MB, 2048 MB, 3072 MB, 4096 MB, 5120 MB, or 6144 MB. If no value is provided, Amazon SageMaker will choose the default value for you. (Default: 2048)
• max_concurrency (int) – Optional. The maximum number of concurrent invocations your serverless endpoint can process. If no value is provided, Amazon SageMaker will choose the default value for you. (Default: 5)
• provisioned_concurrency (int) – Optional. The provisioned concurrency of your serverless endpoint. If no value is provided, Amazon SageMaker will not apply provisioned concucrrency to your Serverless endpoint. (Default: None)