1 Answer
- Newest
- Most votes
- Most comments
0
Hi,
As per my understanding you are looking for providing weight to your model so that you can can distribute the number of calls to the model.
To achieve this you can provide the value of weight for InitialVariantWeight while creating your endpoint config.
You can refer below article to provide weight while creating or updating the endpoints https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateEndpointConfig.html https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_UpdateEndpointWeightsAndCapacities.html#API_UpdateEndpointWeightsAndCapacities_RequestSyntax
Thanks
Relevant content
asked 3 years ago
asked 3 years ago
- AWS OFFICIALUpdated 2 years ago
