Add support for WebGPU models

[Eldoprano]

We could support translate models running on WebGPU. That way users don't have to install an external program like Ollama or LMStudio to run their models.

Example of TranslateGemma running on webGPU: https://huggingface.co/spaces/webml-community/TranslateGemma-WebGPU

[koloved]

it seems far far better than current version, but isnt it slower?