[MPS] Perf fixes. (#81951)
Fixes https://github.com/pytorch/pytorch/issues/81610
* Use fillBuffer() for zero_mps()
Fix minor bug in add_sub_template() with value=0.0
Change default value of use_scalar_value to false in getTensorsStringKey()
* Fallback to fill_scalar_mps() if buffer isn't contiguous.
* Fix high memory consumption in view ops
* Change commitAndWait to Commit in View Ops
Pull Request resolved: https://github.com/pytorch/pytorch/pull/81951
Approved by: https://github.com/razarmehr, https://github.com/albanD