search

Seeed-Projects / jetson-examples

The jetson-examples repository by Seeed Studio offers a seamless, one-line command deployment to run vision AI and Generative AI models on the NVIDIA Jetson platform.
https://github.com/seeed-projects/jetson-examples
MIT License
38 stars 8 forks source link

docker: Error response from daemon: unknown or invalid runtime name: nvidia. #1

Open feiticeir0 opened 1 month ago

feiticeir0 commented 1 month ago

You can probably run into the following error when running the examples:

Found compatible container dustynv/llava:r36.2.0 (2023-12-18, 8.0GB) - would you like to pull it? [Y/n] y
dustynv/llava:r36.2.0
+ docker run --runtime nvidia -it --rm --network host --volume /tmp/argus_socket:/tmp/argus_socket --volume /etc/enctune.conf:/etc/enctune.conf --volume /etc/nv_tegra_release:/etc/nv_tegra_release --volume /tmp/nv_jetson_model:/tmp/nv_jetson_model --volume /var/run/dbus:/var/run/dbus --volume /var/run/avahi-daemon/socket:/var/run/avahi-daemon/socket --volume /var/run/docker.sock:/var/run/docker.sock --volume /home/feiticeir0/reComputer/jetson-containers/data:/data --device /dev/snd --device /dev/bus/usb --device /dev/i2c-0 --device /dev/i2c-1 --device /dev/i2c-2 --device /dev/i2c-4 --device /dev/i2c-5 --device /dev/i2c-7 --device /dev/i2c-9 -v /run/jtop.sock:/run/jtop.sock dustynv/llava:r36.2.0 python3 -m llava.serve.cli --model-path liuhaotian/llava-v1.5-7b --image-file /data/images/hoover.jpg
**docker: Error response from daemon: unknown or invalid runtime name: nvidia.**
See 'docker run --help'.
----example done----
Only Support `run` or `clean` for now. try `reComputer run llava` .

You shoud state that the nvidia-container-toolkit must be installed and configured. Here's the link for the instructions from the nvidia website: https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html

After installing it, all the examples should run

This is also an error when using dusty jetson-containers.

yuyoujiang commented 1 month ago

Hello feiticeir0, thank you very much for your feedback. You are right. If we want the container to run more consistently, we need to check the environment before running the container.

Perhaps we can refer here and edit the relevant actions into a script that runs automatically. https://www.jetson-ai-lab.com/tips_ssd-docker.html

We're going to fix this, but until then, you'll need to manually configure the run environmen. We also welcome the community to work together on this project, and Seeed may release a reward for this effort 😀. https://github.com/orgs/Seeed-Studio/projects/6/views/1

feiticeir0 commented 1 month ago

Hi @yuyoujiang ! Thank you for the reply. I just opened this issue to alert for this. Since this is using the dusty containers from NVIDIA, this issue also happens with theirs .

We also welcome the community to work together on this project, and Seeed may release a reward for this effort 😀. https://github.com/orgs/Seeed-Studio/projects/6/views/1

My name is already on this project - https://github.com/orgs/Seeed-Studio/projects/6/views/1?pane=issue&itemId=64891723 - I'm that guy !