[Pytorch] [NCCL EP] Allow zero tokens for an EP rank in eager mode

[YangFei1990]

Description

For eager mode, there could be case where certain EP ranks do not receive any token, based on the routing strategy. This PR relax the constraint to allow such behavior.

Fixes # (issue)

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)
• 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 refactoring

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

[YangFei1990]

/te-ci L1

[greptile-apps]

Greptile Summary

Allows eager expert-parallel ranks to pass zero-element tensors with null data pointers into NCCL EP descriptors.

• Relaxes tensor descriptor validation only when the tensor has zero elements.
• Adds a distributed eager-mode forward/backward regression test where nonzero ranks receive no tokens.

Confidence Score: 5/5

The PR appears safe to merge, with the relaxed validation constrained to empty tensors and covered by an end-to-end eager expert-parallel regression test.

Non-empty tensors still require valid data pointers, while the new distributed test exercises null-backed empty receive tensors through forward dispatch, combine, and backward execution.

Important Files Changed

Filename	Overview
transformer_engine/common/ep/ep_backend.cpp	Safely narrows the non-null data requirement by exempting zero-element tensors while retaining validation for non-empty tensors.
tests/pytorch/distributed/run_ep.py	Adds CI-reachable eager-mode coverage for zero-token ranks across dispatch, weighted expert processing, combine, and backward propagation.

_{Reviews (1): Last reviewed commit: "[pre-commit.ci] auto fixes from pre-comm..." | Re-trigger Greptile}