feat: for z-image fp16 (Turing GPU) support

[devgdovg]

Motivation

• Make Nunchaku Z-Image-Turbo able to run fp16 dtype on Turing GPUs.

Modifications

• Modify various data type parameters when loading model.
• Add metric "int4-fp16" in z-image-turbo test workflow. (Run pytest -v tests/ -x -vv -k "nunchaku-z-image-turbo" on Turing GPU for verification)

Checklist

• Code is formatted using Pre-Commit hooks (run pre-commit run --all-files).
• Relevant unit tests are added in the tests/workflows directory following the guidance in the Contribution Guide.
• Reference images are uploaded to PR comments and URLs are added to test_cases.json.
• Additional test data (if needed) is registered in test_data/inputs.yaml.
• Additional models (if needed) are registered in scripts/download_models.py and test_data/models.yaml.
• Additional custom nodes (if needed) are added to .github/workflows/pr-test.yaml.
• For reviewers: If you're only helping merge the main branch and haven't contributed code to this PR, please remove yourself as a co-author when merging.
• Please feel free to join our Discord or WeChat to discuss your PR.

[devgdovg]

related pr in nunchaku project:
nunchaku-tech/nunchaku#833