Marvin

Long initial loading time.

1

It takes a few minutes and sometimes it never starts the model when trying to run it. The problem is with all models i am using, also with small ones...

No connection to Windows Ollama

7

# Bug Report ## Description Installed ollama on native windows and tested it. Installed open-webui in docker on server(same network as windows maschine) with the following command: `docker run -d...

Problems with python torch dependency

1

When I execute main.exe which I have built with github actions and cx_Freeze i am getting the following error: `Could not locate cudnn_ops_infer64_8.dll. Please make sure it is in your...

Response terminates prematurely when using Gemini 3 via LiteLLM

11

### Description When using gemini-3-flash-preview through a LiteLLM proxy, OpenCode stops processing the response as soon as the model triggers a tool call. The model provides a reasoning block and...