feat: Update CoreML device support and server controls

- Replace 'mps' with 'coreml' as the identifier for Apple CoreML Execution Provider across the codebase.
- Remove Apple chip generation checks and ensure CoreML is available on all macOS arm64 devices.
- Adjust ONNX Runtime session creation to use default CoreML configurations without forcing 'MLProgram'.
- Implement support for MoGe-2 to utilize CoreML with static input shape requirements.
- Enhance server panel to display restart and stop controls consistently across running states, including 'BUSY'.
- Update UI tests to verify new behavior for server controls and cached model display.
- Bump blendjob dependency version to 0.1.16 in packaging tests and configurations.

src/anyimage/server/models/onnx_moge2.py

@@ -10,6 +10,9 @@ from .onnx_runtime import select_providers as select_providers
 ONNX_FILENAME = "model.onnx"
 MIN_TOKENS = 1200
 MAX_TOKENS = 3600
+COREML_PROVIDER_OPTIONS = {
+    "RequireStaticInputShapes": "1",
+}
 
 
 def is_onnx_model(model_directory):
@@ -18,7 +21,11 @@ def is_onnx_model(model_directory):
 
 def create_session(model_directory, requested_device="auto"):
     path = Path(model_directory) / ONNX_FILENAME
-    return create_runtime_session(path, requested_device)
+    return create_runtime_session(
+        path,
+        requested_device,
+        coreml_options=COREML_PROVIDER_OPTIONS,
+    )
 
 
 def normalized_view_plane_uv(width, height, dtype):

src/anyimage/server/models/onnx_runtime.py

@@ -1,12 +1,5 @@
 """Shared ONNX Runtime session helpers."""
 
-COREML_PROVIDER_OPTIONS = {
-    "ModelFormat": "MLProgram",
-    "MLComputeUnits": "ALL",
-    "RequireStaticInputShapes": "0",
-    "EnableOnSubgraphs": "0",
-}
-
 CUDA_PROVIDER_OPTIONS = {
     "arena_extend_strategy": "kSameAsRequested",
 }
@@ -17,14 +10,20 @@ def select_providers(requested, available):
     providers_for_device = {
         "cuda": ("CUDAExecutionProvider", "DmlExecutionProvider"),
         "directml": ("DmlExecutionProvider",),
-        "mps": ("CoreMLExecutionProvider",),
+        "coreml": ("CoreMLExecutionProvider",),
         "cpu": ("CPUExecutionProvider",),
     }
     if requested != "auto":
         candidates = providers_for_device[requested]
         for provider in candidates:
             if provider in available:
-                return [provider]
+                providers = [provider]
+                if (
+                    provider == "CoreMLExecutionProvider"
+                    and "CPUExecutionProvider" in available
+                ):
+                    providers.append("CPUExecutionProvider")
+                return providers
         if "CPUExecutionProvider" in available:
             return ["CPUExecutionProvider"]
         raise RuntimeError(
@@ -44,7 +43,12 @@ def select_providers(requested, available):
     return providers
 
 
-def create_session(path, requested_device="auto"):
+def create_session(
+    path,
+    requested_device="auto",
+    *,
+    coreml_options=None,
+):
     import onnxruntime
 
     providers = select_providers(
@@ -55,8 +59,8 @@ def create_session(path, requested_device="auto"):
     for provider in providers:
         if provider == "CUDAExecutionProvider":
             provider = (provider, dict(CUDA_PROVIDER_OPTIONS))
-        elif provider == "CoreMLExecutionProvider":
-            provider = (provider, dict(COREML_PROVIDER_OPTIONS))
+        elif provider == "CoreMLExecutionProvider" and coreml_options:
+            provider = (provider, dict(coreml_options))
         configured_providers.append(provider)
     return onnxruntime.InferenceSession(
         str(path),