Fix converting only float type tensors in Lite

[awaelchli]

What does this PR do?

Fixes #10371

Lite converts inputs automatically to the target precision (32, 16, bf16). However, so far this happened unconditionally for all tensor types, when in reality this only makes sense for floating point tensors. This PR restricts this conversion to float tensors only, both for input and output of the wrapped model-forward.

Test fails on master (i.e., without the fix applied).

Does your PR introduce any breaking changes? If yes, please list them.

No

Before submitting

• Was this discussed/approved via a GitHub issue? (not for typos and docs)
• Did you read the contributor guideline, Pull Request section?
• Did you make sure your PR does only one thing, instead of bundling different changes together?
• Did you make sure to update the documentation with your changes? (if necessary)
• Did you write any new necessary tests? (not for typos and docs)
• Did you verify new and existing tests pass locally with your changes?
• Did you update the CHANGELOG? (not for typos, docs, test updates, or internal minor changes/refactorings)

PR review

Anyone in the community is free to review the PR once the tests have passed.
Before you start reviewing make sure you have read Review guidelines. In short, see the following bullet-list:

• Is this pull request ready for review? (if not, please submit in draft mode)
• Check that all items from Before submitting are resolved
• Make sure the title is self-explanatory and the description concisely explains the PR
• Add labels and milestones (and optionally projects) to the PR so it can be classified

Did you have fun?

I made sure I had fun coding 🙃

Part of #1 (it's a lie, this is just here to avoid noisy GitHub bot)

[carmocca]

We'll need to iterate on this but it's okay for now