mirror of
https://github.com/open-webui/open-webui.git
synced 2026-07-11 10:34:13 -05:00
[GH-ISSUE #19036] feat: Manage SGLang Models from within OpenWebUI #105747
Reference in New Issue
Block a user
Delete Branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @ntsarb on GitHub (Nov 8, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/19036
Check Existing Issues
Verify Feature Scope
Problem Description
Hello,
I deployed SGLang in a docker container in WSL2 Ubuntu 22.04 (Windows 11 Pro for Workstations host). OpenWebUI was also deployed in a container in the same docker environment (WSL2), and the two containers are connected to the same docker network (bridge). They expose their services to the host and network access between the containers and the host works as intended.
In the OpenWebUI Settings->Admin Settings->Connections, the SGLang service can be configured under the "OpenAI API" option.
What works:
I was successful with using a particular model that was loaded upon SGLang's launch.
What doesn't work:
OpenWebUI's functionality that allows for downloading new models and configuring them (Settings->Admin Settings->Models->Manage Models) does not work. It brings up a dialog box where I can select between the previously installed Ollama service and the newly installed SGLang service. When I select the SGLang service, I receive "Open WebUI: Server Connection Error".
It looks like this feature is specific to Ollama for now.
Desired Solution you'd like
Develop a generic user interface for managing models on any inference engine (for commonly used APIs), with implementations for different inference engines.
Alternatives Considered
No response
Additional Context
No response