[Feature]: Remove torch.distributed from template_moe all_to_all

[greg-kwasniewski1]

🚀 The feature, motivation and pitch

Though never used, the path from torch_moe -> template_moe -> _template_moe_alltoall fallbacks to naive all-to-all using torch.distributed. Replace it with tensorrt_llm/_torch/auto_deploy/distributed/common.py

Alternatives

No response

Additional context

No response

Before submitting a new issue...

• Make sure you already searched for relevant issues, and checked the documentation and examples for answers to frequently asked questions.