This is a dedicated watch page for a single video.
Scenario: Marchand Pharmaceutical, a medical research corporation led by Michael Marchand, has leveraged its resources to study and implement partial data from Dr. Jonathan Drew’s research. Michael has successfully configured both an existing model and a new model as online deployments. To ensure that a percentage of invocations are duplicated across both models, Michael must use the appropriate parameter within the ManagedOnlineEndpoint class in the Azure Machine Learning Python SDK v2. Question: Which parameter should Michael specify to distribute the invocation load between both models?