fix: NaN assertion uses .all() instead of .any()

[Mr-Neutr0n]

Bug

The NaN assertion assert not torch.isnan(x).all() only triggers when ALL values are NaN. The intended check is to catch ANY NaN values, which requires .any().

Fix

Changed .all() to .any() so the assertion catches any NaN values.

[Mr-Neutr0n]

Quick ping on the one-line fix in ddpm.py that corrects the NaN assertion from .all() to .any(). As written, np.all() only flags a NaN if every element is NaN, so a partially NaN tensor would pass through undetected. Would a maintainer be able to take a look?

[Mr-Neutr0n]

Closing this one to tidy up my open pull requests.

It's been open around five months with no review activity, and I'd rather withdraw it than leave it sitting in your queue. Nothing needed from you, and no hard feelings at all.

If the fix is still wanted, this can be reopened, or I'm happy to redo it properly against current main. Apologies for the noise.