Suggestion to add TEs

### Did you like the remote VAE solution?

I do... it's helpful when training/finetuning models, makes the infrastructure easier to set up.

### What can be improved about the current solution?

Adding TEs would be very helpful for a complete solution for auxiliary model off-loading during training.
Consider caching, then it could further simplify model fine-tuning setups.

### What other VAEs you would like to see if the pilot goes well?

StepVideo VAE: https://huggingface.co/stepfun-ai/stepvideo-t2v/tree/main/vae
HunYuan CLIP (for Stepvideo): https://huggingface.co/stepfun-ai/stepvideo-t2v/tree/main/hunyuan_clip
TE for LuminaVision2: [Gemma-2-2B](https://huggingface.co/google/gemma-2-2b)

### Notify the members of the team

@hlky @sayakpaul

The issue does not name files or tests; begin by locating the existing remote VAE solution and its model off-loading entry points. Clarify the scope for adding the listed text encoders and caching, then identify the relevant model-loading tests; done should cover the agreed auxiliary models and caching behavior.

Scritto dal modello di indicizzazione a partire dal testo della issue.