Dgrad ReduceScatter overlap fix

[vasunvidia]

Description

Please include a brief summary of the changes, relevant motivation and context.

This PR fixes 2 bugs in enabling DGRAD-RS overlap.

Type of change

• [ ] Documentation change (change only to the documentation, either a fix or a new content)
• [x] 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)
• [ ] Infra/Build change
• [ ] Code refractor

Changes

Please list the changes introduced in this PR:

• Fix a bug which assumes DGRAD-RS overlap always uses pipeline method. The fix is to use TP config to add the layer to the correct method list.
• ring_exchange RS uses main_stream for last GEMM chunk. But the send/recv streams wait for stream_compute during last chunk. The fix is to use stream_compute for last chunk and use main stream for reduction kernel.

Checklist:

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

[timmoon10]

/te-ci pytorch

[ksivaman]

Could you resolve the conflicts? @vasunvidia

[ksivaman]

/te-ci pytorch