[MPS] Some of the `DPTForDepthEstimation` ops are not supported on MPS

[anton-l]

To reproduce, remove the mps skips in StableDiffusiondepth2imgPipelineFastTests:

diffusers/tests/pipelines/stable_diffusion_2/test_stable_diffusion_depth.py

Line 154 in cd91fc0

@unittest.skipIf(torch_device == "mps", reason="The depth model does not support MPS yet")

This is probably solvable on the transformers side, but opening an issue here too to keep track of the testing :)

[patrickvonplaten]

This would be nice to fix indeed!

[pcuenca]

Thanks @anton-l, I'll take a look :)

[patrickvonplaten]

Gently reminder @pcuenca :-)

[github-actions]

This issue has been automatically marked as stale because it has not had recent activity. If you think this still needs to be addressed please comment on this thread.

Please note that issues that do not follow the contributing guidelines are likely to be ignored.