Automated Scheduling for Model Endpoint

Automated Scheduling for Model Endpoint

The Automated Scheduling feature allows users to define specific times for automatically starting or stopping Model Endpoint. This helps optimize cloud usage, reduce unnecessary costs, and ensure that compute resources are only active when needed.

Schedule Creation

You can create schedules to automatically start or stop a Model Endpoint at specific times.  
  1. Log in to the platform, go to the Inference section, and select your target model endpoint.  
  2. Navigate to Scheduler Tab: Inside the endpoint detail view, click on the Scheduler tab.  
  3. Create a New Schedule: Click the "+" button and provide the following inputs:  
    1. Action: Choose Start or Stop  
    2. Interval type: Select Daily, Weekly, or Monthly  
    3. Time: Set the desired execution time in UTC  
  4. User Options: Both a web-based interface and API are available for schedule configuration.  

Schedule Management  

Managing your existing schedules is straightforward.  
  1. View Schedules: All scheduled actions for the endpoint are listed in the Scheduler tab for quick reference.  
  2. Delete: You can update the action, time, or recurrence, or remove a schedule entirely when it's no longer needed.

Access Control & Auditability  

To ensure security and compliance, schedule access is tightly controlled.  
  1. Who Can Schedule: Only users with the dev or admin role have permission to create, modify, or delete schedules.  
  2. Audit Logging: All schedule-related changes are recorded in the platform’s audit logs, including:  
    1. User who made the change  
    2. Timestamp  

    • Related Articles

    • Manage a model endpoint

      This guide will walk you through the key features and steps involved in deploying your models, optimizing costs through undeployment, and removing endpoints when they are no longer needed. After creating a model endpoint, follow these steps to ...

    • Automated Scheduling for Notebook Instance

      The Automated Scheduling feature allows users to define specific times for automatically starting or stopping Notebook Instances. This helps optimize cloud usage, reduce unnecessary costs, and ensure that compute resources are only active when ...

    • Whitelist IPs for Model Endpoint

      The Whitelist IP feature enhances the security of Model Endpoints by allowing customers to define a list of trusted client IP addresses using CIDR notation. Only traffic from these authorized IPs is permitted to access the model endpoint, ensuring ...

    • Deploy a model endpoint with custom container

      In this section, you will learn how to deploy and serve your custom machine-learning models using a custom container in our Greennode AI Platform. Follow the steps below to configure and deploy your model for online prediction: Step 0: Import a model ...

    • Create an endpoint

      After training and registering the model, the online prediction component enables the deployment and serving of models to make real-time predictions or inferences on new data. This component provides endpoints or APIs that can be integrated into ...