[GH-ISSUE #19036] feat: Manage SGLang Models from within OpenWebUI #18752

New Issue

GiteaMirror · 2026-04-20T00:57:35-05:00

GiteaMirror commented

2026-04-20 00:57:35 -05:00

Originally created by @ntsarb on GitHub (Nov 8, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/19036

Check Existing Issues

I have searched for all existing open AND closed issues and discussions for similar requests. I have found none that is comparable to my request.

Verify Feature Scope

I have read through and understood the scope definition for feature requests in the Issues section. I believe my feature request meets the definition and belongs in the Issues section instead of the Discussions.

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

Originally created by @ntsarb on GitHub (Nov 8, 2025). Original GitHub issue: https://github.com/open-webui/open-webui/issues/19036 ### Check Existing Issues - [x] I have searched for all existing **open AND closed** issues and discussions for similar requests. I have found none that is comparable to my request. ### Verify Feature Scope - [x] I have read through and understood the scope definition for feature requests in the Issues section. I believe my feature request meets the definition and belongs in the Issues section instead of the Discussions. ### 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_

GiteaMirror closed this issue