Hi Team,
I created a serving endpoint using the mlflow.deployments -> get_deploy_client -> create_endpoint. The endpoint was created successfully but it was not going to the ready state as the update failed with the error message being "Exceeded maximum time limit of 300 seconds to load the model".
My model artifact was larger in size and with maximum GPU configuration the issue was resolved. However, I do not want to utilize the maximum configuration, instead I wish to increase the timeout value. But I am having no clue about where to set this parameter. Please notice the attachments for reference and grateful when a solution shall be provided.
