Description of changes: Underlying integration between sagemaker-inference-toolkit and multi-model-server doesn't allow a model to be named at load time when SAGEMAKER_MULTI_MODEL=false. It makes the endpoint to be named /prediction/model always. This PR adds a model_name to the model_server.start_model_server method to allow a name to be set.
Testing done:
Run testing code as per instructed.
Merge Checklist
Put an x in the boxes that apply. You can also fill these out after creating the PR. If you're unsure about any of them, don't hesitate to ask. We're here to help! This is simply a reminder of what we are going to look for before merging your pull request.
Issue #, if available:
Description of changes: Underlying integration between
sagemaker-inference-toolkitandmulti-model-serverdoesn't allow a model to be named at load time whenSAGEMAKER_MULTI_MODEL=false. It makes the endpoint to be named/prediction/modelalways. This PR adds amodel_nameto themodel_server.start_model_servermethod to allow a name to be set.Testing done:
Run testing code as per instructed.
Merge Checklist
Put an
xin the boxes that apply. You can also fill these out after creating the PR. If you're unsure about any of them, don't hesitate to ask. We're here to help! This is simply a reminder of what we are going to look for before merging your pull request.General
Tests
By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.