Fix Wan2.1-T2V-14B H100 example

[Uxito-Ada]

Summary

Fixes #9 .

This PR fixes the Wan2.1-T2V-14B H100 example so it can successfully load weights and handle NCCL timed-out with multi-GPU.

Motivation

#9 and ParallelWorker:Parallel Worker denoise process timeout as well as RuntimeError: unable to open shared memory object.

Type of Change

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• Performance improvement
• Code refactoring
• Documentation update
• Other (please describe):

Changes Made

As above.

Testing

• Unit tests pass (pytest tests/)
• Manual testing performed
• Benchmarks added/updated (if applicable)

Test commands:

python examples/wan_video/wan21_14b_text_to_video_h100.py --gpu_num 2 --prompt "A cat playing"

Checklist

• Code follows the project's coding standards (ruff)
• Pre-commit hooks pass (pre-commit run --all-files)
• All tests pass (pytest tests/)
• New tests added for new functionality
• Documentation updated (README, CLAUDE.md, docstrings)
• Commit messages are clear and descriptive
• PR title follows the convention: [TYPE] Brief description

Related Issues

Fixes #9

Additional Notes

GPU Architecture Support

• SM80 (Ampere, Ada Lovelace)
• SM90 (Hopper H100)
• SM100+ (Blackwell)

Performance Impact

no

[lzx1413]

LGTM