Receiving "docker: Error response from daemon: OCI runtime create failed" error while run docker with "--runtime nvidia"

I pull a Deepstream container from Nvidia containers:
docker pull
and for running this container I use this command as Nvidia suggest:

sudo docker run -it --rm --net=host --runtime nvidia -e DISPLAY=$DISPLAY -w /opt/nvidia/deepstream/deepstream-5.0 -v /tmp/.X11-unix/:/tmp/.X11-unix
and receive this error:

docker: Error response from daemon: OCI runtime create failed: container_linux.go:370: starting container process caused: process_linux.go:459: container init caused: Running hook #0:: error running hook: exit status 1, stdout: , stderr: nvidia-container-cli: initialization error: driver error: failed to process request: unknown.

I think nvidia container runtime does not work properly. But I have installed it via instruction in GitHub - NVIDIA/nvidia-container-runtime: NVIDIA container runtime

Is --runtime nvidia needed to run Deepstream container? If needed how could I resolve this problem?


May I know which JetPack version do you use first?

Please noted that the Jetson docker mounts libraries from the host.
So you will need to use the container built with the same software version.

If you are using JetPack4.4, please try our Deepstream 5.0 container below: