Report the MLX backend as unavailable on the iOS simulator

[shoumikhin]

Summary

Loading a model that delegates to MLX crashes the process on an iOS simulator instead of failing
cleanly. In the examples repository the demo app crashes on its MLX menu entry, and the llama and
image classifier tests crash with it.

The simulator's Metal device is real enough to build and dispatch a compute pipeline, but two of the
things MLX needs unconditionally are missing from it:

what MLX needs	what the simulator does
device.architecture	returns nothing, and MLX reads it without a null check
a shared storage heap	refused by an assertion inside Metal

The first faults during device construction. Bypassing it reaches the second, which aborts. Neither
is reachable as an error, so nothing downstream can report it.

is_available() is the interface's own answer to whether a backend can run here, and the runtime
already asks before loading a delegate, so returning false is enough to turn the crash into
Error::NotFound. MLX's own is_available() returns a constant and checks nothing, which is why
the answer has to come from here.

This does not make MLX work on the simulator. It makes the answer honest, so a caller gets an error
it can handle.

Test plan

The macro decides everything, so it is checked on all three targets it affects:

simulator   TARGET_OS_SIMULATOR 1   is_available() false
device      TARGET_OS_SIMULATOR 0   is_available() defers to MLX
macOS       TARGET_OS_SIMULATOR 0   is_available() defers to MLX

A real GPU is unaffected. Compiling the same function with the guard disabled returns true on the
simulator again, which is the crashing path, so the guard is doing the work.

Confirmed separately that a delegate whose backend reports unavailable makes load_method return
Error::NotFound rather than crash.

The include is explicit because an undefined macro is zero in #if, which would make the guard
silently do nothing while still compiling.

Follow-ups, not in this change

• The demo app's MLX menu entry should degrade rather than surface a load error, now that it gets
  one. That belongs in the examples repository.
• The image classifier test can assert this error on a simulator, which pins the boundary instead
  of leaving it untested.

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/22336

• 📄 Preview Python docs built from this PR

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

❌ You can merge normally! (1 Unrelated Failure), 4 Unclassified Failures

As of commit 825820c with merge base c27baa8 ():

UNCLASSIFIED FAILURES - DrCI could not classify the following jobs because the workflow did not run on the merge base. The failures may be pre-existing on trunk or introduced by this PR:

• MLX / test-mlx / test-mlx (gh) (this job did not run on the merge base, so DrCI cannot tell whether the failure is pre-existing)
  AssertionError: Slot for getitem already set to Slot(id_type=<IdType.Tensor: 1>, id_space=<IdSpace.Output: 3>, idx=0), trying to set to Slot(id_type=<IdType.Tensor: 1>, id_space=<IdSpace.Input: 2>, idx=3)
• MLX / test-mlx-dflash / test-mlx-dflash (gh) (this job did not run on the merge base, so DrCI cannot tell whether the failure is pre-existing)
  AssertionError: Slot for getitem already set to Slot(id_type=<IdType.Tensor: 1>, id_space=<IdSpace.Output: 3>, idx=0), trying to set to Slot(id_type=<IdType.Tensor: 1>, id_space=<IdSpace.Input: 2>, idx=2)
• MLX / test-mlx-qwen35-moe / test-mlx-qwen35-moe (gh) (this job did not run on the merge base, so DrCI cannot tell whether the failure is pre-existing)
  AssertionError: Slot for getitem_8 already set to Slot(id_type=<IdType.Tensor: 1>, id_space=<IdSpace.Output: 3>, idx=2), trying to set to Slot(id_type=<IdType.Tensor: 1>, id_space=<IdSpace.Input: 2>, idx=4)
• MLX / test-mlx-stories110m / test-mlx-stories110m (gh) (this job did not run on the merge base, so DrCI cannot tell whether the failure is pre-existing)
  AssertionError: Slot for getitem already set to Slot(id_type=<IdType.Tensor: 1>, id_space=<IdSpace.Output: 3>, idx=0), trying to set to Slot(id_type=<IdType.Tensor: 1>, id_space=<IdSpace.Input: 2>, idx=2)

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

👉 Rebase onto the `viable/strict` branch to avoid these failures

• pull / test-qnn-testsuite-linux / test-backend-linux (qnn, models) / linux-job (gh) (trunk failure)

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

[Copilot]

Copilot was unable to review this pull request because the user who requested the review has reached their quota limit.