amd的显卡，rocm7.1

[gqyalh]

在尝试启动大模型的时候报下面的异常
VLLM_USE_MODELSCOPE=true vllm serve deepseek-ai/DeepSeek-R1-Distill-Llama-70B --tensor-parallel-size 2 --max-model-len 32768 --enforce-eager
INFO 11-20 18:08:10 [init.py:220] No platform detected, vLLM is running on UnspecifiedPlatform
WARNING 11-20 18:08:11 [_custom_ops.py:20] Failed to import from vllm._C with ImportError('libcudart.so.12: cannot open shared object file: No such file or directory')
Traceback (most recent call last):
File "/home/gqy/miniconda3/envs/vllm/bin/vllm", line 7, in
sys.exit(main())
^^^^^^
File "/home/gqy/miniconda3/envs/vllm/lib/python3.12/site-packages/vllm/entrypoints/cli/main.py", line 46, in main
cmd.subparser_init(subparsers).set_defaults(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/gqy/miniconda3/envs/vllm/lib/python3.12/site-packages/vllm/entrypoints/cli/serve.py", line 70, in subparser_init
serve_parser = make_arg_parser(serve_parser)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/gqy/miniconda3/envs/vllm/lib/python3.12/site-packages/vllm/entrypoints/openai/cli_args.py", line 263, in make_arg_parser
parser = AsyncEngineArgs.add_cli_args(parser)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/gqy/miniconda3/envs/vllm/lib/python3.12/site-packages/vllm/engine/arg_utils.py", line 1714, in add_cli_args
parser = EngineArgs.add_cli_args(parser)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/gqy/miniconda3/envs/vllm/lib/python3.12/site-packages/vllm/engine/arg_utils.py", line 919, in add_cli_args
vllm_kwargs = get_kwargs(VllmConfig)
^^^^^^^^^^^^^^^^^^^^^^
File "/home/gqy/miniconda3/envs/vllm/lib/python3.12/site-packages/vllm/engine/arg_utils.py", line 281, in get_kwargs
return copy.deepcopy(_compute_kwargs(cls))
^^^^^^^^^^^^^^^^^^^^
File "/home/gqy/miniconda3/envs/vllm/lib/python3.12/site-packages/vllm/engine/arg_utils.py", line 182, in _compute_kwargs
default = field.default_factory()
^^^^^^^^^^^^^^^^^^^^^^^
File "/home/gqy/miniconda3/envs/vllm/lib/python3.12/site-packages/pydantic/_internal/_dataclasses.py", line 121, in init
s.pydantic_validator.validate_python(ArgsKwargs(args, kwargs), self_instance=s)
File "/home/gqy/miniconda3/envs/vllm/lib/python3.12/site-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.