Eugene Brodsky

> [...] (and wasn't really sure how cuda was even working as-is). My cuda Dockerfile uses the [nvidia/cuda ubuntu image](https://hub.docker.com/r/nvidia/cuda/tags) as a base, not the python base image [...] @fat-tire:...

> Does runpod use podman or [docker](https://docs.runpod.io/serverless-ai/custom-apis/worker-image-creation)? Runpod uses Kubernetes as far as I can tell (so it's `containerd` most likely), but generally any OCI-compliant image should work equally well...

I don't know `podman` at all, sadly, just looked over some of the docs... but this is very curious indeed if the `nvidia/cuda` based images work correctly for you, but...

Great to hear you got it working! If there was a way to run this without installing the nvidia driver into the image, that would be ideal, in my opinion....

@fat-tire I'm going to close this PR as outdated - we'll have it for reference if/when implementing Podman support, as discussed in #3587

Could you please clarify - it does not *enable* the filter for you, but the issue is that it downloads the model?

Thanks. When implementing this we need to provide an option to install the nsfw filter model if the user decides to enable it at a later point.

Not sure if :+1: s are tracked on this issue, but I can reproduce this exactly. Poetry version 1.1.4.

@lstein are you able to test this? I do not have access to a system with an AMD GPU, and not sure if anyone else on the team does...

@Rubonnek thanks again for the contribution. we're refactoring the Docker setup quite heavily in #3587 . Would you be interested in reviewing / testing that PR and implementing your ROCm...