Load DDUF file with Diffusers using mmap

DDUF support for diffusers is there and DDUF support mmap.

But diffusers example doesn't use or support mmap,

How can I load DDUF file to diffusers with mmap?

```
from diffusers import DiffusionPipeline
import torch

pipe = DiffusionPipeline.from_pretrained(
"DDUF/FLUX.1-dev-DDUF", dduf_file="FLUX.1-dev.dduf", torch_dtype=torch.bfloat16
).to("cuda")
image = pipe(
"photo a cat holding a sign that says Diffusers", num_inference_steps=50, guidance_scale=3.5
).images[0]
image.save("cat.png")
```

Start by tracing DiffusionPipeline.from_pretrained with the dduf_file argument and the existing DDUF mmap support. Determine how the example can load FLUX.1-dev.dduf through mmap, then verify the pipeline example still generates and saves the image as shown.

Scritto dal modello di indicizzazione a partire dal testo della issue.