runtime error

Deep Learning Container License. By pulling and using the container, you accept the terms and conditions of this license: https://developer.nvidia.com/ngc/nvidia-deep-learning-container-license A copy of this license is made available in this container at /NGC-DL-CONTAINER-LICENSE for your convenience. WARNING: The NVIDIA Driver was not detected. GPU functionality will not be available. Use the NVIDIA Container Toolkit to start this container with GPU support; see https://docs.nvidia.com/datacenter/cloud-native/ . *** Welcome to KoboldCpp - Version 1.65 === !!! IMPORTANT WARNING !!! === You are using one or more OUTDATED config files or launch flags! The flags --smartcontext, --hordeconfig and --sdconfig have been DEPRECATED, and MAY be REMOVED in future! They will still work for now, but you SHOULD switch to the updated flags instead, to avoid future issues! New flags are: --hordemodelname --hordeworkername --hordekey --hordemaxctx --hordegenlen --sdmodel --sdthreads --sdquant --sdclamped For more information on these flags, please check --help >>> If you are using the GUI launcher, simply re-saving your config again will get rid of this warning. === !!! IMPORTANT WARNING !!! === Preloading saved story default.json into server... Saved story preloaded. Attempting to use CuBLAS library for faster prompt ingestion. A compatible CuBLAS will be required. Initializing dynamic library: koboldcpp_cublas.so Traceback (most recent call last): File "/opt/koboldcpp/./koboldcpp.py", line 3415, in <module> main(parser.parse_args(),start_server=True) File "/opt/koboldcpp/./koboldcpp.py", line 3059, in main init_library() # Note: if blas does not exist and is enabled, program will crash. File "/opt/koboldcpp/./koboldcpp.py", line 273, in init_library handle = ctypes.CDLL(os.path.join(dir_path, libname)) File "/usr/lib/python3.10/ctypes/__init__.py", line 374, in __init__ self._handle = _dlopen(self._name, mode) OSError: libcuda.so.1: cannot open shared object file: No such file or directory

Container logs: