AI Model Management

Upload, version, and remotely deploy AI model files to inference containers running on WEDA Nodes.

📄️ Overview

Understand how WEDA uploads, versions, and deploys AI model files from the cloud to inference containers running on WEDA Nodes.

Register a model, upload an edition via TUS, deploy it to WEDA Node devices, and check deployment status through the AI Model Management API.

Mount the secured volume on a WEDA Node so your inference container can read a deployed AI model file.