Kevin Knights

Results 2 comments of Kevin Knights

I know this was closed, but I'm getting the following error: `FP4 quantization state not initialized. Please call .cuda() or .to(device) on the LinearFP4 layer first.` Runner: Docker container using...

> Love to have this enhancement too, To me, Gradio is a framework to GUI-fy a function, FastAPI a framework to Web-API-fy a function, so if a Gradio app instance...