[PyTorch] Expose `multi_tensor_*` kernels

[yaox12]

Description

Expose multi_tensor_* kernels under transformer_engine.pytorch.optimizers to avoid importing transformer_engine_torch outside of TE.

Type of change

• [ ] Documentation change (change only to the documentation, either a fix or a new content)
• [ ] Bug fix (non-breaking change which fixes an issue)
• [x] New feature (non-breaking change which adds functionality)
• [ ] Breaking change (fix or feature that would cause existing functionality to not work as expected)

Checklist:

• [x] I have read and followed the contributing guidelines
• [x] The functionality is complete
• [x] I have commented my code, particularly in hard-to-understand areas
• [x] I have made corresponding changes to the documentation
• [x] My changes generate no new warnings
• [x] I have added tests that prove my fix is effective or that my feature works
• [x] New and existing unit tests pass locally with my changes

[yaox12]

Renaming transformer_engine_extensions to transformer_engine_torch makes me realize that we should avoid importing it outside of TE, so I expose these kernels to let MCore (or other framework) use them. cc @timmoon10

[timmoon10]

/te-ci pytorch

[yaox12]

@timmoon10 Please re-run the CI.

[timmoon10]

/te-ci pytorch