class QuantizedFluxTransformer2DModel(QuantizedDiffusersModel):
        base_class = FluxTransformer2DModel

    transformer = FluxTransformer2DModel.from_pretrained(
        'black-forest-labs/FLUX.1-Fill-dev', subfolder="transformer", torch_dtype=torch.bfloat16, 
    ).to("cuda")

    qtransformer = QuantizedFluxTransformer2DModel.quantize(transformer, weights=qfloat8) 

    # for param in qtransformer.parameters(): param.data = param.data.contiguous() # useless

    qtransformer.save_pretrained('fluxfill_transformer_fp8')