Export an MLX model for the iOS demo build (pytorch#22297)

## Problem

The mv3 demo app is gaining an MLX option. Its Xcode project will bundle
`mv3_mlx.pte`, so the iOS CI job that stages models for the demo has to
produce
that file, or the build fails on a missing resource.

## Change

Lower the model to MLX inline, the same way the script already drives
the
portable, Core ML and XNNPACK exports (there is no generic `examples/`
entry
point that takes a model name and lowers it to MLX). The same export is
added to
both iOS scripts.

The check reads the delegates directly off the program and fails unless
the model
produced an MLX delegate. The MLX partitioner only logs a warning when
it
delegates nothing and still returns a valid program, so without this a
model with
no MLX delegate would be staged under an MLX name and the demo would
still pass on
the portable kernels. The check runs before the file is written.

## Landing order

This change must land first. It produces `mv3_mlx.pte`; the demo change
consumes
it. The scripts clone the demo's default branch, so if the demo landed
first its
project would require a model this script does not yet produce and the
iOS build
would break.

## Test Plan

Ran the lowering and the delegate check against a delegated model: the
count is 1
and the file is written; a non-delegated program gives 0 and the check
fails
before writing anything. Runtime execution of the staged model is not
exercised
here; delegate presence is.

Co-authored-by: PyTorch Bot <pytorchbot@users.noreply.github.com>

Author: shoumikhin

.ci/scripts/test_ios_ci.sh

@@ -49,6 +49,43 @@ python3 -m examples.portable.scripts.export --model_name="$MODEL_NAME" --segment
 python3 -m examples.apple.coreml.scripts.export --model_name="$MODEL_NAME"
 python3 -m examples.xnnpack.aot_compiler --model_name="$MODEL_NAME" --delegate
 
+# No generic examples/ entry point takes a model name and lowers it to MLX, so do
+# it here. Lowering is ahead of time and imports no mlx runtime package. Assert MLX
+# claimed the graph before writing: the partitioner only warns when it delegates
+# nothing, so without this a program with no MLX delegate would be staged.
+python3 - "$MODEL_NAME" <<'PY'
+import sys
+
+import torch
+from executorch.backends.mlx import MLXPartitioner
+from executorch.examples.models import MODEL_NAME_TO_MODEL
+from executorch.examples.models.model_factory import EagerModelFactory
+from executorch.exir import EdgeCompileConfig, to_edge_transform_and_lower
+
+model_name = sys.argv[1]
+model, example_inputs, _, _ = EagerModelFactory.create_model(
+    *MODEL_NAME_TO_MODEL[model_name]
+)
+program = to_edge_transform_and_lower(
+    torch.export.export(model.eval(), example_inputs),
+    partitioner=[MLXPartitioner()],
+    compile_config=EdgeCompileConfig(_skip_dim_order=True),
+).to_executorch()
+
+segments = sum(
+    delegate.id == "MLXBackend"
+    for plan in program.executorch_program.execution_plan
+    for delegate in plan.delegates
+)
+if segments == 0:
+    raise SystemExit(f"error: {model_name} produced no MLX delegate")
+
+path = f"{model_name}_mlx.pte"
+with open(path, "wb") as file:
+    program.write_to_file(file)
+print(f"{path}: {segments} MLX delegate segment(s)")
+PY
+
 mkdir -p "$APP_PATH/Resources/Models/MobileNet/"
 mv $MODEL_NAME*.pte "$APP_PATH/Resources/Models/MobileNet/"
 

scripts/test_ios.sh

@@ -66,6 +66,43 @@ python3 -m examples.portable.scripts.export --model_name="$MODEL_NAME"
 python3 -m examples.apple.coreml.scripts.export --model_name="$MODEL_NAME"
 python3 -m examples.xnnpack.aot_compiler --model_name="$MODEL_NAME" --delegate
 
+# No generic examples/ entry point takes a model name and lowers it to MLX, so do
+# it here. Assert MLX claimed the graph before writing: the partitioner only warns
+# when it delegates nothing. This needs the MLX backend built, which the installer
+# does only on Apple Silicon with the Metal compiler present.
+python3 - "$MODEL_NAME" <<'PY'
+import sys
+
+import torch
+from executorch.backends.mlx import MLXPartitioner
+from executorch.examples.models import MODEL_NAME_TO_MODEL
+from executorch.examples.models.model_factory import EagerModelFactory
+from executorch.exir import EdgeCompileConfig, to_edge_transform_and_lower
+
+model_name = sys.argv[1]
+model, example_inputs, _, _ = EagerModelFactory.create_model(
+    *MODEL_NAME_TO_MODEL[model_name]
+)
+program = to_edge_transform_and_lower(
+    torch.export.export(model.eval(), example_inputs),
+    partitioner=[MLXPartitioner()],
+    compile_config=EdgeCompileConfig(_skip_dim_order=True),
+).to_executorch()
+
+segments = sum(
+    delegate.id == "MLXBackend"
+    for plan in program.executorch_program.execution_plan
+    for delegate in plan.delegates
+)
+if segments == 0:
+    raise SystemExit(f"error: {model_name} produced no MLX delegate")
+
+path = f"{model_name}_mlx.pte"
+with open(path, "wb") as file:
+    program.write_to_file(file)
+print(f"{path}: {segments} MLX delegate segment(s)")
+PY
+
 mkdir -p "$APP_PATH/Resources/Models/MobileNet/"
 mv $MODEL_NAME*.pte "$APP_PATH/Resources/Models/MobileNet/"