How to create a serverless endpoint configuration?

Question

based on the sample code provided here , https://docs.aws.amazon.com/sagemaker/latest/dg/serverless-endpoints-create.html#serverless-endpoints-create-config

I created a model via lambda, now when i try to create a serverless endpoint config (sample code below) , i keep getting -> parameter validation failed 
unknown parameter in` ProductVariants [ 0 ]:` "ServerlessConfig", must be one of : VairantName, ModelName, InitialInstanceCount , Instancetype...

```
response = client.create_endpoint_config(
   EndpointConfigName="endpoint-new",
   ProductionVariants=[
        {
            "ModelName": "MyModel",
            "VariantName": "AllTraffic",
            "ServerlessConfig": {
                "MemorySizeInMB": 2048,
                "MaxConcurrency": 10
            }
        } 
    ]
)
```

Accepted Answer

The cause might be that your SageMaker Python SDK is not updated to the latest version. Please make sure you update it to the latest version as well as the AWS SDK for Python (boto3). You can use pip:

```
pip install --upgrade boto3
pip install --upgrade sagemaker
```

For a sample notebook you can have a look [here](https://github.com/aws/amazon-sagemaker-examples/blob/main/serverless-inference/Serverless-Inference-Walkthrough.ipynb). More information on the documentation [page](https://sagemaker.readthedocs.io/en/stable/overview.html#sagemaker-serverless-inference).

Answer

Hi,

Can you confirm the version of boto3 that you are using? This error is likely to be caused because of an older version of boto3 that does not include capability for serverless inference.

Serverless inference was introduced in version 1.20.18

Hope this helps,

Georgios

How to create a serverless endpoint configuration?

Relevanter Inhalt