gpu version 1.2.0-arcface-r100-gpu

OSError: libcuda.so.1: cannot open shared object file: No such file or directory
comare-gpu-compreface-core-1 | {"severity": "WARNING", "message": "500 Internal Server Error: The server encountered an internal error and was unable to complete your request. Either the server is overloaded or there is an error in the application.", "request": {"method": "GET", "path": "/status", "filename": "", "api_key": "", "remote_addr": "172.28.0.6"}, "logger": "root", "module": "error_handling", "traceback": "Traceback (most recent call last):\n File \"/usr/local/lib/python3.8/dist-packages/flask/app.py\", line 2447, in wsgi_app\n response = self.full_dispatch_request()\n File \"/usr/local/lib/python3.8/dist-packages/flask/app.py\", line 1945, in full_dispatch_request\n self.try_trigger_before_first_request_functions()\n File \"/usr/local/lib/python3.8/dist-packages/flask/app.py\", line 1993, in try_trigger_before_first_request_functions\n func()\n File \"/app/ml/./src/_endpoints.py\", line 49, in init_model\n detector = managers.plugin_manager.detector\n File \"/usr/local/lib/python3.8/dist-packages/cached_property.py\", line 36, in __get__\n value = obj.__dict__[self.func.__name__] = self.func(obj)\n File \"/app/ml/./src/services/facescan/plugins/managers.py\", line 73, in detector\n return [pl for pl in self.plugins\n File \"/usr/local/lib/python3.8/dist-packages/cached_property.py\", line 36, in __get__\n value = obj.__dict__[self.func.__name__] = self.func(obj)\n File \"/app/ml/./src/services/facescan/plugins/managers.py\", line 66, in plugins\n pl_class = import_classes(pl_path)\n File \"/app/ml/./src/services/facescan/plugins/managers.py\", line 30, in import_classes\n return getattr(import_module(module, __package__), class_name)\n File \"/usr/lib/python3.8/importlib/__init__.py\", line 127, in import_module\n return _bootstrap._gcd_import(name[level:], package, level)\n File \"\", line 1014, in _gcd_import\n File \"\", line 991, in _find_and_load\n File \"\", line 975, in _find_and_load_unlocked\n File \"\", line 671, in _load_unlocked\n File \"\", line 848, in exec_module\n File \"\", line 219, in _call_with_frames_removed\n File \"/app/ml/./src/services/facescan/plugins/insightface/insightface.py\", line 27, in \n from src.services.facescan.plugins.insightface import helpers as insight_helpers\n File \"/app/ml/./src/services/facescan/plugins/insightface/helpers.py\", line 24, in \n import mxnet as mx\n File \"/usr/local/lib/python3.8/dist-packages/mxnet/__init__.py\", line 23, in \n from .context import Context, current_context, cpu, gpu, cpu_pinned\n File \"/usr/local/lib/python3.8/dist-packages/mxnet/context.py\", line 23, in \n from .base import classproperty, with_metaclass, _MXClassPropertyMetaClass\n File \"/usr/local/lib/python3.8/dist-packages/mxnet/base.py\", line 356, in \n _LIB = _load_lib()\n File \"/usr/local/lib/python3.8/dist-packages/mxnet/base.py\", line 347, in _load_lib\n lib = ctypes.CDLL(lib_path[0], ctypes.RTLD_LOCAL)\n File \"/usr/lib/python3.8/ctypes/__init__.py\", line 373, in __init__\n self._handle = _dlopen(self._name, mode)\nOSError: libcuda.so.1: cannot open shared object file: No such file or directory\n", "build_version": "dev"}

Start with src/_endpoints.py at init_model, then trace plugin loading through src/services/facescan/plugins/managers.py and the InsightFace files named in the traceback. Reproduce the 1.2.0-arcface-r100-gpu setup and inspect the MXNet import failure involving libcuda.so.1. Done means the /status endpoint initializes the detector without this error in the intended GPU environment.

Written by the indexing model from the issue text.