gpt3_mcore_te_tp2_zp_z3_resume_torch_dist_te_8experts2parallel_top2router broken after TE2.14

**Describe the bug**

Captured via CI run: https://github.com/NVIDIA/Megatron-LM/actions/runs/23531562829/job/68506373685?pr=4025

I would assume we need to update the checkpoint, but that's just a hunch I'm having.

**Steps/Code to reproduce bug**

Please list *minimal* steps or code snippet for us to be able to reproduce the bug.

A helpful guide on on how to craft a minimal bug report http://matthewrocklin.com/blog/work/2018/02/28/minimal-bug-reports.

**Expected behavior**

A clear and concise description of what you expected to happen.

**Additional context**

Add any other context about the problem here.