#1. SSH RKE2 node
$ ssh <user>@<RKE2 node ip>

#2. 安裝 gcc 與 kernel-devel
$ sudo zypper mr -ea && \
sudo zypper -n in gcc kernel-devel nvidia-container-toolkit

#3. 安裝 nvidia driver
$ v="555.58.02" && \
curl -L -O https://us.download.nvidia.com/XFree86/Linux-x86_64/"$v"/NVIDIA-Linux-x86_64-"$v".run && \
sudo sh NVIDIA-Linux-x86_64-"$v".run

# 4. 重啟主機
$ sudo reboot

# 5. test 
$ nvidia-smi
Wed Jul  3 09:20:46 2024
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 555.58.02              Driver Version: 555.58.02      CUDA Version: 12.5     |
|-----------------------------------------+------------------------+----------------------+
| GPU  Name                 Persistence-M | Bus-Id          Disp.A | Volatile Uncorr. ECC |
| Fan  Temp   Perf          Pwr:Usage/Cap |           Memory-Usage | GPU-Util  Compute M. |
|                                         |                        |               MIG M. |
|=========================================+========================+======================|
|   0  NVIDIA GeForce RTX 4060 Ti     Off |   00000000:00:10.0 Off |                  N/A |
|  0%   47C    P8             15W /  165W |       4MiB /  16380MiB |      0%      Default |
|                                         |                        |                  N/A |
+-----------------------------------------+------------------------+----------------------+

+-----------------------------------------------------------------------------------------+
| Processes:                                                                              |
|  GPU   GI   CI        PID   Type   Process name                              GPU Memory |
|        ID   ID                                                               Usage      |
|=========================================================================================|
|  No running processes found                                                             |
+-----------------------------------------------------------------------------------------+

# 6. Update RKE2 Containerd Configuration
## 6.1. Check
$ ls -l /usr/bin/nvidia-container-runtime
-rwxr-xr-x 1 root root 4319136 Oct 20  2022 /usr/bin/nvidia-container-runtime

## 6.2. Backup 
$ sudo cp /var/lib/rancher/rke2/agent/etc/containerd/config.toml .

## 6.3. Update
$ sudo cp /var/lib/rancher/rke2/agent/etc/containerd/config.toml /var/lib/rancher/rke2/agent/etc/containerd/config.toml.tmpl

$ sudo nano -Yone /var/lib/rancher/rke2/agent/etc/containerd/config.toml.tmpl
## 將以下內容加到檔案的最後面
[plugins."io.containerd.grpc.v1.cri".containerd.runtimes."nvidia"]
  runtime_type = "io.containerd.runc.v2"
[plugins."io.containerd.grpc.v1.cri".containerd.runtimes."nvidia".options]
  BinaryName = "/usr/bin/nvidia-container-runtime"

## 6.4. 重啟主機
$ sudo reboot

name: nvidia
Index URL: https://helm.ngc.nvidia.com/nvidia

toolkit:
  enabled: true
  env:                                                 
    - name: CONTAINERD_CONFIG
      value: /var/lib/rancher/rke2/agent/etc/containerd/config.toml
    - name: CONTAINERD_SOCKET
      value: /run/k3s/containerd/containerd.sock

# 1. sample1
$ cat << EOF | kubectl create -f -
apiVersion: v1
kind: Pod
metadata:
  name: cuda-vectoradd
spec:
  restartPolicy: OnFailure
  runtimeClassName: nvidia
  containers:
  - name: cuda-vectoradd
    image: "nvidia/samples:vectoradd-cuda11.2.1"
    resources:
      limits:
         nvidia.com/gpu: 1
EOF

# 2. 測試成功 log 資訊
$ kubectl logs cuda-vectoradd
[Vector addition of 50000 elements]
Copy input data from the host memory to the CUDA device
CUDA kernel launch with 196 blocks of 256 threads
Copy output data from the CUDA device to the host memory
Test PASSED
Done

# 3. Delete Sample1 pod
$ kubectl delete pod cuda-vectoradd

# 4. sample2
$ cat << EOF | kubectl create -f -
apiVersion: v1
kind: Pod
metadata:
  name: nbody-gpu-benchmark
  namespace: default
spec:
  restartPolicy: OnFailure
  runtimeClassName: nvidia
  containers:
  - name: cuda-container
    image: nvcr.io/nvidia/k8s/cuda-sample:nbody
    args: ["nbody", "-gpu", "-benchmark"]
    resources:
      limits:
        nvidia.com/gpu: 1
    env:
    - name: NVIDIA_VISIBLE_DEVICES
      value: all
    - name: NVIDIA_DRIVER_CAPABILITIES
      value: all
EOF

# 5. 測試成功 log 資訊
$ kubectl logs nbody-gpu-benchmark
Run "nbody -benchmark [-numbodies=<numBodies>]" to measure performance.
        -fullscreen       (run n-body simulation in fullscreen mode)
        -fp64             (use double precision floating point values for simulation)
        -hostmem          (stores simulation data in host memory)
        -benchmark        (run benchmark to measure performance)
        -numbodies=<N>    (number of bodies (>= 1) to run in simulation)
        -device=<d>       (where d=0,1,2.... for the CUDA device to use)
        -numdevices=<i>   (where i=(number of CUDA devices > 0) to use for simulation)
        -compare          (compares simulation results running once on the default GPU and once on the CPU)
        -cpu              (run n-body simulation on the CPU)
        -tipsy=<file.bin> (load a tipsy model file for simulation)

NOTE: The CUDA Samples are not meant for performance measurements. Results may vary when GPU Boost is enabled.

> Windowed mode
> Simulation data stored in video memory
> Single precision floating point simulation
> 1 Devices used for simulation
MapSMtoCores for SM 8.9 is undefined.  Default to use 128 Cores/SM
MapSMtoArchName for SM 8.9 is undefined.  Default to use Ampere
GPU Device 0: "Ampere" with compute capability 8.9

> Compute 8.9 CUDA device: [NVIDIA GeForce RTX 4060 Ti]
34816 bodies, total time for 10 iterations: 19.339 ms
= 626.784 billion interactions per second
= 12535.677 single-precision GFLOP/s at 20 flops per interaction

# 6. Delete Sample2 pod
$ kubectl delete pod nbody-gpu-benchmark

name: openwebui
Index URL: https://helm.openwebui.com/

ingress:
  annotations: {}
  class: nginx
  enabled: true
  existingSecret: ''
  host: ollama.example.com
  tls: false

ollama:
  enabled: true
  fullnameOverride: open-webui-ollama
  ollama:
    gpu:
      enabled: true
      number: 1
      type: nvidia
    models:
      - llama3
  persistentVolume:
    enabled: true
  runtimeClassName: nvidia

openaiBaseApiUrl: open-webui-ollama.ollama.svc.cluster.local

persistence:
  accessModes:
    - ReadWriteOnce
  annotations: {}
  enabled: true
  existingClaim: ''
  selector: {}
  size: 2Gi
  storageClass: local-path

Variable Name: WEBUI_AUTH
Value: False

$ kubectl -n ollama get ing
NAME         CLASS   HOSTS                ADDRESS       PORTS   AGE
open-webui   nginx   ollama.example.com   172.20.0.52   80      2d17h