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.

用户使用 vLLM 在 Intel XPU(Arc GPU)的 Docker 容器中运行 vllm serve 命令时出现此错误。复现环境:基于 Intel oneAPI / PyTorch 2.12.0+xpu 的 Docker 自定义镜像,Level Zero 驱动可正常检测到 2 张 GPU(






![[Bug]: [ERROR][Exception]: Exceptions from Trio nursery](https://www.chat-gpts.plus/wp-content/uploads/2026/07/12545-a5895cec-768x403.jpg)

