nebari-config-aws-gpu-example.yaml

provider: aws
namespace: internal
nebari_version: 2024.1.1rc5
project_name: XXXX
domain: XXXX
certificate:
  type: lets-encrypt
  acme_email: XXXX
  acme_server: XXXX
ci_cd:
  type: none
terraform_state:
  type: remote
security:
  keycloak:
    initial_root_password: _sanitized_
  authentication:
    type: password
storage:
  conda_store: 1000Gi
default_images:
  jupyterhub: quay.io/nebari/nebari-jupyterhub:main-f941abc-20240122
  jupyterlab: quay.io/nebari/nebari-jupyterlab:main-f941abc-20240122
  dask_worker: quay.io/nebari/nebari-dask-worker:main-f941abc-20240122
jhub_apps:
  enabled: true
theme:
  jupyterhub:
    hub_title: Welcome to XXXX
    hub_subtitle: ""
    welcome: >
      <div style='display: block; max-width: 800px; padding: 20px; border: 1px solid gray; text-align: left; margin: auto auto; background-color: #fcf8e3'>
        XXX
        <br /><br />
      </div>
    logo: "XXX"
    primary_color: "#2E5084"
    primary_color_dark: "#192C48"
    secondary_color: "#5B5F63"
    secondary_color_dark: "#242628"
    accent_color: "#E1E3E4"
    accent_color_dark: "#212121"
    text_color: "#212121"
    h1_color: "#212121"
    h2_color: "#212121"
    navbar_text_color: "#E6E6E6"
    navbar_hover_color: "#67C8F2"
    navbar_color: "#212121"
amazon_web_services:
  region: us-gov-west-1
  kubernetes_version: '1.26'
  node_groups:
    general:
      instance: m5.2xlarge
      min_nodes: 2
      max_nodes: 5
    user:
      instance: m5.xlarge
      min_nodes: 0
      max_nodes: 50
      single_subnet: false
    worker:
      instance: m5.xlarge
      min_nodes: 1
      max_nodes: 50
      single_subnet: false
    gpu-tesla-g4:
      instance: g4dn.xlarge
      min_nodes: 0
      max_nodes: 5
      single_subnet: false
      gpu: true
    gpu-tesla-g4-4x:
      instance: g4dn.12xlarge
      min_nodes: 0
      max_nodes: 5
      single_subnet: false
      gpu: true
    gpu-tesla-g3-2x:
      instance: g3.8xlarge
      min_nodes: 0
      max_nodes: 5
      single_subnet: false
      gpu: true
profiles:
  jupyterlab:
  - display_name: Micro Instance
    access: yaml
    groups:
    - developer
    - admin
    description: Stable environment with 0.5-1 cpu / 0.5-1 GB ram
    kubespawner_override:
      cpu_limit: 1
      cpu_guarantee: 0.5
      mem_limit: 1G
      mem_guarantee: 0.5G
      node_selector:
        "eks.amazonaws.com/nodegroup": "user"
  - display_name: Small Instance
    description: Stable environment with 1.5-2 cpu / 6-8 GB ram
    default: true
    kubespawner_override:
      cpu_limit: 2
      cpu_guarantee: 1.5
      mem_limit: 8G
      mem_guarantee: 6G
      node_selector:
        "eks.amazonaws.com/nodegroup": "user"
  - display_name: Medium Instance
    description: Stable environment with 3-4 cpu / 12-16 GB ram
    kubespawner_override:
      cpu_limit: 4
      cpu_guarantee: 3
      mem_limit: 16G
      mem_guarantee: 12G
      node_selector:
        "eks.amazonaws.com/nodegroup": "user"
  - display_name: G4 GPU Instance 1x
    access: yaml
    groups:
    - gpu-access
    description: 4 cpu / 16GB RAM / 1 Nvidia T4 GPU (16 GB GPU RAM)
    kubespawner_override:
      image: quay.io/nebari/nebari-jupyterlab-gpu:main-f941abc-20240122
      cpu_limit: 4
      cpu_guarantee: 3
      mem_limit: 16G
      mem_guarantee: 10G
      extra_pod_config:
        volumes:
        - name: "dshm"
          emptyDir:
            medium: "Memory"
            sizeLimit: "2Gi"
      extra_container_config:
        volumeMounts:
        - name: "dshm"
          mountPath: "/dev/shm"
      extra_resource_limits:
        nvidia.com/gpu: 1
      node_selector:
        beta.kubernetes.io/instance-type: "g4dn.xlarge"
  - display_name: G4 GPU Instance 4x
    access: yaml
    groups:
    - gpu-access
    description: 48 cpu / 192GB RAM / 4 Nvidia T4 GPU (64 GB GPU RAM)
    kubespawner_override:
      image: quay.io/nebari/nebari-jupyterlab-gpu:main-f941abc-20240122
      cpu_limit: 48
      cpu_guarantee: 40
      mem_limit: 192G
      mem_guarantee: 150G
      extra_pod_config:
        volumes:
        - name: "dshm"
          emptyDir:
            medium: "Memory"
            sizeLimit: "2Gi"
      extra_container_config:
        volumeMounts:
        - name: "dshm"
          mountPath: "/dev/shm"
      extra_resource_limits:
        nvidia.com/gpu: 4
      node_selector:
        beta.kubernetes.io/instance-type: "g4dn.12xlarge"
  - display_name: G3 GPU Instance 2x
    access: yaml
    groups:
    - gpu-access
    description: 32 cpu / 244GB RAM / 2 Nvidia Tesla M60 GPU (16 GB GPU RAM)
    kubespawner_override:
      image: quay.io/nebari/nebari-jupyterlab-gpu:main-f941abc-20240122
      cpu_limit: 32
      cpu_guarantee: 30
      mem_limit: 244G
      mem_guarantee: 200G
      extra_pod_config:
        volumes:
        - name: "dshm"
          emptyDir:
            medium: "Memory"
            sizeLimit: "2Gi"
      extra_container_config:
        volumeMounts:
        - name: "dshm"
          mountPath: "/dev/shm"
      extra_resource_limits:
        nvidia.com/gpu: 2
      node_selector:
        beta.kubernetes.io/instance-type: "g3.8xlarge"

jupyterlab:
  idle_culler:
    terminal_cull_inactive_timeout: 120
    kernel_cull_idle_timeout: 120
    server_shutdown_no_activity_timeout: 120