Revert FLUX performance improvement that fails on MacOS (#7423)

## Summary

https://github.com/invoke-ai/InvokeAI/issues/7422

As reported in the above ticket, a recent FLUX performance improvement
caused a regression on MacOS. This PR reverts the offending part of the
change.

## Related Issues / Discussions

- Closes #7422 
- Original perf improvement:
https://github.com/invoke-ai/InvokeAI/pull/7399

## QA Instructions

I don't have a Mac capable of running this test, so trusting the report
in #7422 that this fixes the problem.

## Checklist

- [x] _The PR has a short but descriptive title, suitable for a
changelog_
- [x] _Tests added / updated (if applicable)_
- [x] _Documentation added / updated (if applicable)_
- [ ] _Updated `What's New` copy (if doing a release after this PR)_

invokeai/backend/flux/math.py

@@ -32,4 +32,4 @@ def apply_rope(xq: Tensor, xk: Tensor, freqs_cis: Tensor) -> tuple[Tensor, Tenso
     xk_ = xk.view(*xk.shape[:-1], -1, 1, 2)
     xq_out = freqs_cis[..., 0] * xq_[..., 0] + freqs_cis[..., 1] * xq_[..., 1]
     xk_out = freqs_cis[..., 0] * xk_[..., 0] + freqs_cis[..., 1] * xk_[..., 1]
-    return xq_out.view(*xq.shape), xk_out.view(*xk.shape)
+    return xq_out.view(*xq.shape).type_as(xq), xk_out.view(*xk.shape).type_as(xk)