umerkayvyro

torch.load fails due to weights_only=True in PyTorch >=2.6 when loading quantized model

3

> When running `app/gradio_app.py`, loading the model via `FluxTransformer2DModel.from_pretrained(...)` fails with a `pickle.UnpicklingError` due to `weights_only=True` being the new default in PyTorch 2.6+. > > ### Error: > > ```...