Add combined-workflow and from-checkpoint diffusion tests

[CharlelieLrt]

PhysicsNeMo Pull Request

Description

Checklist

• I am familiar with the Contributing Guidelines.
• New or existing tests cover these changes.
• The documentation is up to date with these changes.
• The CHANGELOG.md is up to date with these changes.
• An issue is linked to this pull request.
• If I am implementing a new model or modifying any existing model, I have followed the Models Implementation Coding Standards.

Dependencies

Review Process

All PRs are reviewed by the PhysicsNeMo team before merging.

Depending on which files are changed, GitHub may automatically assign a maintainer for review.

We are also testing AI-based code review tools (e.g., Greptile), which may add automated comments with a confidence score.
This score reflects the AI’s assessment of merge readiness and is not a qualitative judgment of your work, nor is
it an indication that the PR will be accepted / rejected.

AI-generated feedback should be reviewed critically for usefulness.
You are not required to respond to every AI comment, but they are intended to help both authors and reviewers.
Please react to Greptile comments with 👍 or 👎 to provide feedback on their accuracy.

[greptile-apps]

Greptile Summary

This PR adds combined-workflow tests that exercise the realistic SDA recipe — EDMPreconditioner(backbone) wrapped inside MultiDiffusionModel2D paired with a consistently-parameterized EDMNoiseScheduler — and adds from-checkpoint variants for patch_x and fuse in the existing TestNonRegression class. Reference .pth and .mdlus files are committed alongside the new tests. The changes are purely additive test infrastructure with no modifications to production code.

Important Files Changed

Filename	Overview
test/diffusion/test_losses.py	Adds two new parametrized test classes (TestMSEDSMLossWithPreconditioner and TestWeightedMSEDSMLossWithPreconditioner) exercising the full EDMPreconditioner + EDMNoiseScheduler + loss pipeline; ref_file is redundantly assigned in both if/else branches.
test/diffusion/test_multi_diffusion_losses.py	Adds TestMSEDSMLossWithPreconditionedInnerModel and TestWeightedMSEDSMLossWithPreconditionedInnerModel for the realistic wrapping order (EDMPreconditioner inside MultiDiffusionModel2D); training loops are duplicated inline rather than using the existing _run_training_loop helper.
test/diffusion/test_multi_diffusion_models.py	Adds test_patch_x_from_checkpoint and test_fuse_from_checkpoint to TestNonRegression, and a new TestWithPreconditionedInnerModel class for EDMPreconditioner as the inner model; design is consistent with the existing test patterns.

_{Reviews (1): Last reviewed commit: "Add combined-workflow and from-checkpoin..." | Re-trigger Greptile}

[pzharrington]

New tests look good!

[CharlelieLrt]

/blossom-ci

[CharlelieLrt]

/blossom-ci