docker run --gpus all 启动 registry.baidubce.com/paddlepaddle/0.8.0-cuda10.2-cudnn7-devel 镜像容器出错

[hq0749a]

windows
docker version:20.10.13
使用 --gpus all 替代 nvidia-docker
启动命令：
docker run --gpus all -p 9292:9292 --name test -dit registry.baidubce.com/paddlepaddle/serving:0.8.0-cuda10.2-cudnn7-devel bash
ERROR:
docker: Error response from daemon: failed to create shim: OCI runtime create failed: container_linux.go:380: starting container process caused: process_linux.go:545: container init caused: Running hook #0:: error running hook: exit status 1, stdout: , stderr: nvidia-container-cli: initialization error: load library failed: /usr/lib/wsl/drivers/nvlt.inf_amd64_b656a48cddc58650/libnvidia-ml.so.1: cannot open shared object file: no such file or directory: unknown.
请问这个如何解决，是这个镜像缺少cuda及cudnn相关驱动文件么

[TeslaZhao]

https://forums.developer.nvidia.com/t/hpl-ngc-container-libnvidia-ml-so-1-cannot-open-shared-object-file/191046