[test_models_transformer_hunyuan_video] help us test torch.compile() for impactful models

[tongyu0924]

What does this PR do?

Part of #11430

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you read the contributor guideline?
• Did you read our philosophy doc (important for complex PRs)?
• Was this discussed/approved via a GitHub issue or the forum? Please add a link to it if that's the case.
• Did you make sure to update the documentation with your changes? Here are the
  documentation guidelines, and
  here are tips on formatting docstrings.
• Did you write any new necessary tests?

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

[sayakpaul]

Thanks for the PR! I just ran the tests but ran into errors: https://pastebin.com/A6c4gnwd.

@a-r-r-o-w possible to take a look when you have a moment?

[sayakpaul]

This can be done in a separate PR.

[a-r-r-o-w]

Yeah, our Hunyuan implementation is not compatible with torch.compile back from when we integrated it. I'll open a PR rewriting the attention mask implementation

[sayakpaul]

Reopening as this PR has the test case.

[sayakpaul]

I have run the tests and they also pass:

export RUN_SLOW=1
export RUN_COMPILE=1
pytest tests/models/transformers/test_models_transformer_hunyuan_video.py -k "test_torch_compile_recompilation_and_graph_break"

[sayakpaul]

Thanks!