Monitor Inference Jobs

​

Introduction

ZEDEDA Edge Inference Services creates background jobs when you import models from external providers or copy models between organizations. These jobs run asynchronously and can take several minutes to complete, depending on model size and network conditions. In the new console, inference jobs are tracked in the shared Inference > Monitor > Jobs page rather than in a dedicated inference jobs view.

​

Prerequisites

• You have access to ZEDEDA Edge Inference Services. See Organizations, Users, and Roles.
• You have started at least one model import from the Providers page.

​

View Inference Jobs

When you import a model from a provider, ZEDEDA Edge Inference Services automatically navigates you to the Jobs page. To return to the Jobs page at any time:

1. In the sidebar, select Infrastructure.
2. Select Inference > Monitor > Jobs.

The Jobs page lists all background jobs in your organization, including model imports triggered from Edge Inference Services.

​

Job Columns

The Jobs list includes the following columns:

​

Job Statuses

​

Troubleshoot a Failed Import Job

If a model import job shows a Failed status:

1. Select the job row to view the job details and error message.
2. Verify that the source provider is reachable by testing the provider connection on the Providers page. Testing a provider connection requires the Super Admin role.
3. Confirm that the model path and version are correct.
4. Check that your credentials have sufficient permissions to read the model from the provider.
5. Retry the failed job. Only Failed jobs can be retried. File-upload jobs and organization copies cannot be retried; start a new import from the Providers page instead.

​

In This Section

• Edge Inference Services Overview
• Inference Dashboard
• Inference Quick Start
• Access and Navigate Edge Inference Services
• Organizations, Users, and Roles
• Manage Providers
  • Manage Providers Using Jupyter Notebook Integration
• Manage Models
  • Manage Models Using Jupyter Notebook Integration
  • Benchmark Models and Manage Device Pools
  • Monitor Benchmark Runs and Interpret Results
• Submit Model Deployment Requests
• Approve and Validate Models
• Monitor Inference Jobs
• Use ZEIA to Query and Operate Your Fleet
• Use Prevalidated Agents
  • Use the Faulty Printed Circuit Board Detection Agent
  • Use the Autonomous Retail Billing Agent
• Inference Troubleshooting