runtime error

Exit code: 1. Reason: y:117] No CUDA runtime is found, using CUDA_HOME='/usr/local/cuda' Traceback (most recent call last): File "/usr/local/bin/vllm", line 10, in <module> sys.exit(main()) ^^^^^^ File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/cli/main.py", line 66, in main cmd.subparser_init(subparsers).set_defaults(dispatch_function=cmd.cmd) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/cli/serve.py", line 127, in subparser_init serve_parser = make_arg_parser(serve_parser) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.12/dist-packages/vllm/entrypoints/openai/cli_args.py", line 300, in make_arg_parser parser = AsyncEngineArgs.add_cli_args(parser) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.12/dist-packages/vllm/engine/arg_utils.py", line 2040, in add_cli_args parser = EngineArgs.add_cli_args(parser) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.12/dist-packages/vllm/engine/arg_utils.py", line 1153, in add_cli_args vllm_kwargs = get_kwargs(VllmConfig) ^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.12/dist-packages/vllm/engine/arg_utils.py", line 346, in get_kwargs return copy.deepcopy(_compute_kwargs(cls)) ^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.12/dist-packages/vllm/engine/arg_utils.py", line 258, in _compute_kwargs default = default.default_factory() ^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.12/dist-packages/pydantic/_internal/_dataclasses.py", line 121, in __init__ s.__pydantic_validator__.validate_python(ArgsKwargs(args, kwargs), self_instance=s) File "/usr/local/lib/python3.12/dist-packages/vllm/config/device.py", line 58, in __post_init__ raise RuntimeError( RuntimeError: Failed to infer device type, please set the environment variable `VLLM_LOGGING_LEVEL=DEBUG` to turn on verbose logging to help debug the issue.

Container logs: