[MPS] Added zero check to inverse & fix for any op to avoid segfault issue

[DenisVieriu97]

Fixes empty placeholder error in inverse op. Change to any op should also resolve previously seen segfaults

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/94551

• 📄 Preview Python docs built from this PR
• 📄 Preview C++ docs built from this PR
• ❓ Need help or want to give feedback on the CI? Visit the bot commands wiki or our office hours

Note: Links to docs will display an error until the docs builds have been completed.

❗ 2 Active SEVs

There are 2 currently active SEVs. If your PR is affected, please view them below:

• ROCm jobs fail to access AMD apt repo
• MacOS M1 CPU/MPS tests are backlogged due to HW availability

❌ 1 Failures

As of commit ae8b966:

BROKEN TRUNK - The following jobs failed but were present on the merge base d8f4026:

• linux-bionic-py3.8-clang9 / test (dynamo, 1, 2, linux.2xlarge)

This comment was automatically generated by Dr. CI and updates every 15 minutes.

[DenisVieriu97]

@pytorchbot merge -f "Lint+MPS is green"

[pytorchmergebot]

Merge started

Your change will be merged immediately since you used the force (-f) flag, bypassing any CI checks (ETA: 1-5 minutes).

Learn more about merging in the wiki.

Questions? Feedback? Please reach out to the PyTorch DevX Team

Advanced Debugging

Check the merge workflow status
here

[malfet]

This would never return True, as library availability level is equal to host executable availability level, which if I'm not mistaken is setup for 11.0 for all Python builds shipped by Anaconda

[kulinseth]

Agreed, we didn't see this issue locally. But we will switch it out to a ObjC selector, in next PR.