contrib/nvidia should support passing "--no-cgroups" to nvidia-container-cli.
Required for nerdctl run --gpus on rootless (on cgroup v1, at least).
Did you try rootless (on cgroup v1)?
I guess it needs setting no-cgroups = true
moby/moby#38729 (comment)
Originally posted by @AkihiroSuda in containerd/nerdctl#251 (comment)
It doesn't work as of now.
We might need to patch github.com/containerd/containerd/contrib/nvidia for allowing to pass --no-cgroup option to nvidia-container-cli.
Containerd doesn't use nvidia-container-runtime (instead, it executes nvidia-container-cli directly) so we cannot use /etc/nvidia-container-runtime/config.toml for nerdctl.
Originally posted by @ktock in containerd/nerdctl#251 (comment)
A very hacky workaround for this is to wrap nvidia-container-cli to forcefully specify --no-cgroups.
mkdir -p /opt/nvidia/bin
mv /usr/bin/nvidia-container-cli /opt/nvidia/bin/
cat <<'EOF' > /usr/bin/nvidia-container-cli
#!/bin/bash
/opt/nvidia/bin/nvidia-container-cli ${@:1:($#-1)} --no-cgroups ${@:$#}
EOF
Originally posted by @ktock in containerd/nerdctl#251 (comment)
contrib/nvidiashould support passing "--no-cgroups" tonvidia-container-cli.Required for
nerdctl run --gpuson rootless (on cgroup v1, at least).Discussion in containerd/nerdctl#251
Originally posted by @AkihiroSuda in containerd/nerdctl#251 (comment)
Originally posted by @ktock in containerd/nerdctl#251 (comment)
Originally posted by @ktock in containerd/nerdctl#251 (comment)