Remote Hosting

[Jaster1999]

Search before asking

• I have searched the X-AnyLabeling Docs and issues and found no similar questions.

Question

is it possible to host x-anylabeling on a remote server with gpu and then access it somehow (e.g. via webui).

Additional

No response

[CVHub520]

Yes, it is now possible to use X-AnyLabeling with a remote server for GPU-accelerated inference! The X-AnyLabeling team has officially launched support for remote model inference service deployment. This means you can run the AI models on a powerful remote server (e.g., one with a GPU) while using the X-AnyLabeling desktop client on your local machine.

To set this up, you’ll need to deploy the dedicated inference server component provided by the project. All the details, including setup instructions and configuration guidance, are available in the official companion repository: https://github.com/CVHub520/X-AnyLabeling-Server.

Note that X-AnyLabeling itself remains a desktop application—it does not currently offer a web-based UI that you access through a browser. However, by connecting the desktop client to a remote inference server, you effectively offload the heavy GPU work to your server while keeping the annotation interface locally. This architecture gives you the performance benefits of server-side GPUs without requiring high-end hardware on your client machine.

For the latest updates or troubleshooting, be sure to check the server repository’s documentation or open an issue there if needed!