fix: address PR review feedback — SystemExit, AUTO device, thread timing

- Catch SystemExit from add_openvino_libs_to_path() so a missing
  OpenVINO installation never causes a hard exit on Windows
- Replace hard-coded GPU+FP16 with AUTO:GPU,NPU,CPU device priority,
  letting OpenVINO pick the best available accelerator
- Extract shared OPENVINO_PROVIDER_CONFIG constant to avoid
  duplication between _onnx_enhancer and face_swapper
- Defer thread-suggestion evaluation until after execution_providers
  is assigned, fixing a latent timing bug that affected OpenVINO,
  CUDA, and DML thread hints

modules/core.py

@@ -58,7 +58,7 @@ def parse_args() -> None:
     program.add_argument('--live-resizable', help='The live camera frame is resizable', dest='live_resizable', action='store_true', default=False)
     program.add_argument('--max-memory', help='maximum amount of RAM in GB', dest='max_memory', type=int, default=suggest_max_memory())
     program.add_argument('--execution-provider', help='execution provider', dest='execution_provider', default=[suggest_default_execution_provider()], choices=suggest_execution_providers(), nargs='+')
-    program.add_argument('--execution-threads', help='number of execution threads', dest='execution_threads', type=int, default=suggest_execution_threads())
+    program.add_argument('--execution-threads', help='number of execution threads', dest='execution_threads', type=int, default=None)
     program.add_argument('-v', '--version', action='version', version=f'{modules.metadata.name} {modules.metadata.version}')
 
     # register deprecated args
@@ -90,6 +90,12 @@ def parse_args() -> None:
     modules.globals.execution_threads = args.execution_threads
     modules.globals.lang = args.lang
 
+    # The argparse default (None) avoids evaluating suggest_execution_threads()
+    # before providers are decoded, and deprecated-arg overrides above may
+    # have already set execution_threads.
+    if modules.globals.execution_threads is None:
+        modules.globals.execution_threads = suggest_execution_threads()
+
     #for ENHANCER tumblers:
     for enhancer_key in ('face_enhancer', 'face_enhancer_gpen256', 'face_enhancer_gpen512'):
         modules.globals.fp_ui[enhancer_key] = enhancer_key in args.frame_processor

modules/processors/frame/_onnx_enhancer.py

@@ -20,6 +20,11 @@ IS_APPLE_SILICON = platform.system() == "Darwin" and platform.machine() == "arm6
 # Limit concurrent ONNX calls to avoid VRAM exhaustion on multi-face frames
 THREAD_SEMAPHORE = threading.Semaphore(min(max(1, (os.cpu_count() or 1)), 8))
 
+# OpenVINO provider configuration.
+# AUTO:GPU,NPU,CPU lets OpenVINO try the best available device in priority
+# order (Intel GPU → NPU → CPU). 
+OPENVINO_PROVIDER_CONFIG = ("OpenVINOExecutionProvider", {"device_type": "AUTO:GPU,NPU,CPU"})
+
 
 def build_provider_config(providers=None):
     """Wrap raw provider name strings with optimised CUDA / CoreML options.
@@ -51,13 +56,8 @@ def build_provider_config(providers=None):
                 },
             ))
         elif p == "OpenVINOExecutionProvider":
-            # Prefer Intel GPU with FP16 precision when available.
-            # NB: GPU_FP16 is deprecated since OpenVINO 2025.4 — use
-            # device_type="GPU" + precision="FP16" instead.
-            config.append((
-                "OpenVINOExecutionProvider",
-                {"device_type": "GPU", "precision": "FP16"},
-            ))
+            # AUTO lets OpenVINO select the best device
+            config.append(OPENVINO_PROVIDER_CONFIG)
         else:
             config.append(p)
     return config

modules/processors/frame/face_swapper.py

@@ -271,10 +271,10 @@ def get_face_swapper() -> Any:
                         # fastest on modern GPUs (Blackwell/sm_120).
                         providers_config.append(p)
                     elif p == "OpenVINOExecutionProvider":
-                        providers_config.append((
-                            "OpenVINOExecutionProvider",
-                            {"device_type": "GPU", "precision": "FP16"},
-                        ))
+                        from modules.processors.frame._onnx_enhancer import (
+                            OPENVINO_PROVIDER_CONFIG,
+                        )
+                        providers_config.append(OPENVINO_PROVIDER_CONFIG)
                     else:
                         providers_config.append(p)
                 FACE_SWAPPER = insightface.model_zoo.get_model(

run.py

@@ -39,7 +39,7 @@ if sys.platform == "win32":
             add_openvino_libs_to_path,
         )
         add_openvino_libs_to_path()
-    except (ImportError, FileNotFoundError):
+    except (ImportError, FileNotFoundError, SystemExit):
         pass  # OpenVINO not installed — no-op
 
 # On Linux, pre-load NVIDIA shared libraries (cuDNN, cuBLAS, nvrtc...) shipped