Multi threads with Sagemaker multi-model-endpoint

Hey,
I am using the sklearn multi-model-endpoint.
On the load test, I see that the endpoint serving one by one request and not more.
It is possible to manage more than **one** request (according to the instance type and the number of cores) at the moment per instance with Sagemaker? how?

Thanks

The issue names a scikit-learn SageMaker multi-model endpoint but no repository file or test. Start by locating the relevant endpoint example and reviewing how serving and request concurrency are configured. Done means establishing whether concurrent requests are supported for the stated instance and documenting the applicable configuration or limitation.

Written by the indexing model from the issue text.