CLASSIC
Containers
Clara Deploy Model Sync Daemon [Deprecated]

Clara Deploy Model Sync Daemon [Deprecated]

Description
Clara Deploy Model Sync Daemon
Publisher
NVIDIA
Latest Tag
0.8.1-2108.1
Modified
April 4, 2023
Compressed Size
169.96 MB
Multinode Support
No
Multi-Arch Support
No
0.8.1-2108.1 (Latest) Security Scan Results

Linux / amd64

Sorry, your browser does not support inline SVG.

Clara Deploy SDK is being consolidated into Clara Holoscan SDK

More info https://catalog.ngc.nvidia.com/orgs/nvidia/teams/clara/collections/claradeploy

Clara Model Sync Daemon

This asset requires the Clara Deploy SDK. Follow the instructions on the Clara Ansible page to install the Clara Deploy SDK.

Overview

The Model Sync Daemon for Clara Deploy SDK is designed to be a side car to inference server instances deployed by the Clara Deploy SDK. The daemon will communicate with a Model Repository service to download and organize models for the inference server. The daemon must be configured with a Model Catalog, Instance and Model Repository to function properly. Currently the Model Sync Daemon is fully managed by the Clara api server. Standalone operation is not recommended.

Definitions

Term Definition
Model catalog A abstract collection of Models. These model catalogs are managed by the Clara Inference Manager Service. This is idenfied by a unique identifier.
Instance A unique identifier used to to store the currently available models for a sync daemon instance back to the a Model Repository.

Requirements

This container requires Docker 18.09.2 or higher.

License

An End User License Agreement is included with the product. By pulling and using the Clara Deploy asset on NGC, you accept the terms and conditions of these licenses.

Third Party Licenses

Suggested Reading

Release Notes, the Getting Started Guide, and the SDK itself are available at the NVIDIA Developer forum.

For answers to any questions you may have about this release, visit the NVIDIA Devtalk forum.