Rancher not passing GPU to Plex POD


My GPU is working fine on my host machine. I am able to run commands with NO probs:

docker run nvidia/cuda:11.5.0-base-ubuntu20.04 nvidia-smi -L

But when I spin up a plex container and exec shell into it. I am unable to run nvidia-smi from inside the container and when plex transcodes videos, it is unable to see the GPU.
I am running nvidia-device-plugin-daemonset within my K3S cluster via Rancher’s GUI and it is showing active

Here is my docker version:

$ docker version
Client: Docker Engine - Community
 Version:           20.10.12
 API version:       1.41
 Git commit:        e91ed57
 Built:             Mon Dec 13 11:45:33 2021
 OS/Arch:           linux/amd64
 Context:           default
 Experimental:      true

Server: Docker Engine - Community
  Version:          20.10.12
  API version:      1.41 (minimum version 1.12)
  Go version:       go1.16.12
  Git commit:       459d0df
  Built:            Mon Dec 13 11:43:42 2021
  OS/Arch:          linux/amd64
  Experimental:     false
  Version:          1.6.8
  GitCommit:        9cd3357b7fd7218e4aec3eae239db1f68a5a6ec6
  Version:          1.1.4
  GitCommit:        v1.1.4-0-g5fd4c4d
  Version:          0.19.0
  GitCommit:        de40ad0

Plex itself works fine, I spun it up using linuxserver.io. But it is unable to use my GPU.
What else could I try?