Are there plans to support multimodal MTP models in the future?

**Is your feature request related to a problem? Please describe.**
A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]

Tag the [@mcore-oncall](https://github.com/orgs/NVIDIA/teams/mcore-oncall)
to get oncall's attention to this issue.

**Describe the solution you'd like**
A clear and concise description of what you want to happen.

**Describe alternatives you've considered**
A clear and concise description of any alternative solutions or features you've considered.

**Additional context**
Add any other context or screenshots about the feature request here.

**“MTP currently does not support multimodal models.”**

```
self.megatron_model_meta = get_megatron_model_meta(args.hf_model_type)
self.visual = None
if args.mtp_num_layers:
raise ValueError('MTP currently does not support multimodal models.')
```
Are there plans to support multimodal MTP models in the future?