mkdocs.yml

site_name: Run:ai Documentation Library
site_url: https://docs.run.ai/
copyright: Copyright © 2020 - 2024 Run:ai
repo_url: https://github.com/run-ai/docs/
edit_uri: edit/v2.16/docs/
docs_dir: docs 
theme: 
  name: material
  custom_dir: overrides
  language: en
  favicon: images/favicon.ico
  logo: images/RUNAI-LOGO-DIGITAL-2C_WP.svg
  features:
    - navigation.indexes
    - navigation.tabs
    - navigation.tabs.sticky
    - search.highlight
    - content.code.annotate
    - content.tabs.link
    - search.suggest
    - content.action.edit
    - navigation.top
    - toc.follow
    - navigation.path
    - content.code.copy

  icon:
    edit: material/pencil 
    view: material/eye
extra_css:
  - stylesheets/extra.css
  
# strict: true   
 
markdown_extensions:
  - footnotes
#  - markdown_include.include
  - pymdownx.highlight:
      anchor_linenums: true
  - pymdownx.inlinehilite
  - pymdownx.snippets:
      base_path: ["docs/snippets", "docs/admin"]
  - pymdownx.superfences:
      custom_fences:
        - name: mermaid
          class: mermaid
          format: !!python/name:pymdownx.superfences.fence_code_format
  - pymdownx.tabbed:
      alternate_style: true
  - pymdownx.details 
  - admonition
  - attr_list
  - meta
  - tables
  - toc:
      permalink: True 
  - pymdownx.emoji:
      emoji_index: !!python/name:material.extensions.emoji.twemoji
      emoji_generator: !!python/name:material.extensions.emoji.to_svg
extra:
  social:
    - icon: fontawesome/brands/twitter
      link: https://twitter.com/runailabs
    - icon: fontawesome/brands/linkedin
      link: https://linkedin.com/company/runailabs/
  analytics:
    provider: google
    property: UA-122651141-1
  version:
    provider: mike

plugins:
  - mike:
      version_selector: true
      canonical_version: null
  - search:
      lang: en
  - git-revision-date-localized:
      enable_creation_date: true
      type: timeago
  - glightbox:
      zoomable: true
      draggable: true
      skip_classes:
        - skip-lightbox
  - minify:
      minify_html: true
  - redirects:
      redirect_maps:
        'Administrator/Cluster-Setup/cluster-prerequisites.md' : 'admin/runai-setup/cluster-setup/cluster-prerequisites.md'
        'Administrator/Researcher-Setup/cli-install.md' : 'admin/researcher-setup/cli-install.md'
        'Administrator/Cluster-Setup/cluster-install.md' : 'admin/runai-setup/cluster-setup/cluster-install.md'
        'Administrator/Cluster-Setup/cluster-upgrade.md' : 'admin/runai-setup/cluster-setup/cluster-upgrade.md'
        'Administrator/Cluster-Setup/customize-cluster-install.md' : 'admin/runai-setup/cluster-setup/customize-cluster-install.md'
      #  'Administrator/integration/mlflow.md' : 'admin/integration/mlflow.md'
        'admin/runai-setup/self-hosted/k8s/ui.md' : 'admin/runai-setup/self-hosted/k8s/backend.md'
        'admin/runai-setup/advanced/overview.md' : 'admin/runai-setup/config/overview.md'
        'admin/runai-setup/advanced/node-roles.md' : 'admin/runai-setup/config/node-roles.md'
        'admin/runai-setup/advanced/researcher-authentication.md' : 'admin/runai-setup/authentication/sso.md'
        'admin/runai-setup/advanced/sso.md' : 'admin/runai-setup/authentication/sso.md'
        'admin/runai-setup/advanced/access-roles.md' : 'admin/runai-setup/config/access-roles.md'
        'admin/runai-setup/advanced/allow-external-access-to-containers.md' : 'admin/runai-setup/config/allow-external-access-to-containers.md'
        'admin/runai-setup/advanced/non-root-containers.md' : 'admin/runai-setup/config/non-root-containers.md'
        'admin/runai-setup/advanced/cli-admin-install.md' : 'admin/runai-setup/config/cli-admin-install.md'
        'admin/runai-setup/advanced/dr.md' : 'admin/runai-setup/config/dr.md'
        'admin/runai-setup/advanced/node-downtime.md' : 'admin/runai-setup/maintenance/node-downtime.md'
        'admin/runai-setup/advanced/alert-monitoring.md' : 'admin/runai-setup/maintenance/alert-monitoring.md'
        'admin/runai-setup/config/researcher-authentication.md' : 'admin/runai-setup/authentication/researcher-authentication.md'
        'admin/runai-setup/config/sso.md' : 'admin/runai-setup/authentication/sso.md'
        'admin/runai-setup/cluster-setup/cluster-troubleshooting.md' : 'admin/troubleshooting/troubleshooting.md'
        'admin/runai-setup/cluster-setup/nvidia.md' : 'admin/runai-setup/cluster-setup/cluster-prerequisites.md'
        'admin/runai-setup/self-hosted/ocp/ocp-dependencies.md'  : 'admin/runai-setup/self-hosted/ocp/preparations.md'
        'admin/runai-setup/cluster-setup/researcher-authentication.md' : 'admin/runai-setup/authentication/sso.md'
        'admin/researcher-setup/cli-troubleshooting.md' : 'admin/troubleshooting/troubleshooting.md'
        'developer/deprecated/inference/submit-via-yaml.md' : 'developer/cluster-api/other-resources.md'
        'Researcher/researcher-library/rl-hpo-support.md' : 'Researcher/scheduling/hpo.md'
        'Researcher/researcher-library/researcher-library-overview.md' : 'Researcher/scheduling/hpo.md'

nav:
  - Home: 
    - 'Overview': 'index.md'
    - 'System Components' : 'home/components.md'
    - 'Whats New' :
      - 'home/whats-new-2-16.md'
      - 'Version 2.15' : 'home/whats-new-2-15.md'
      - 'Version 2.13' : 'home/whats-new-2-13.md'
      - 'Version 2.9' : 'home/whats-new-2-9.md'
      - 'Version 2.8' : 'home/whats-new-2-8.md'
    - 'Data Privacy' : 'home/data-privacy-details.md'
  - 'Administrator' :
    - 'Overview' : 'admin/overview-administrator.md'
    - 'Run:ai Setup' : 
      - 'Installation Types' : 'admin/runai-setup/installation-types.md'
      - 'Classic (SaaS)' :
        - 'Introduction' : 'admin/runai-setup/cluster-setup/cluster-setup-intro.md'
        - 'Prerequisites' : 'admin/runai-setup/cluster-setup/cluster-prerequisites.md'
        - 'Cluster Install' : 'admin/runai-setup/cluster-setup/cluster-install.md'
        - 'Customize Installation' : 'admin/runai-setup/cluster-setup/customize-cluster-install.md'
        - 'Cluster Upgrade' : 'admin/runai-setup/cluster-setup/cluster-upgrade.md'
        - 'Cluster Delete' : 'admin/runai-setup/cluster-setup/cluster-delete.md'
        - 'Kubernetes Install' : 'admin/runai-setup/cluster-setup/install-k8s.md'  
        - 'NVIDIA DGX Bundle' : 'admin/runai-setup/cluster-setup/dgx-bundle.md'  
      - 'Self-hosted' : 
        - 'Overview' : 'admin/runai-setup/self-hosted/overview.md'
        - 'Kubernetes-based' :
          - 'Prerequisites' : 'admin/runai-setup/self-hosted/k8s/prerequisites.md'
          - 'Preparations' : 'admin/runai-setup/self-hosted/k8s/preparations.md'
          - 'Install Control Plane' : 'admin/runai-setup/self-hosted/k8s/backend.md'
          - 'Install a Cluster' : 'admin/runai-setup/self-hosted/k8s/cluster.md'
          - 'Install additional Clusters' : 'admin/runai-setup/self-hosted/k8s/additional-clusters.md'
          - 'Manually Create Projects' : 'admin/runai-setup/self-hosted/k8s/project-management.md'
          - 'Next Steps' : 'admin/runai-setup/self-hosted/k8s/next-steps.md'
          - 'Upgrade' : 'admin/runai-setup/self-hosted/k8s/upgrade.md'
          - 'Uninstall' : 'admin/runai-setup/self-hosted/k8s/uninstall.md'
        - 'OpenShift-based' :
          - 'Prerequisites' : 'admin/runai-setup/self-hosted/ocp/prerequisites.md'
          - 'Preparations' : 'admin/runai-setup/self-hosted/ocp/preparations.md'
          - 'Install Control Plane' : 'admin/runai-setup/self-hosted/ocp/backend.md'
          - 'Install a Cluster' : 'admin/runai-setup/self-hosted/ocp/cluster.md'
          - 'Install additional Clusters' : 'admin/runai-setup/self-hosted/ocp/additional-clusters.md'
          - 'Manually Create Projects' : 'admin/runai-setup/self-hosted/ocp/project-management.md'
          - 'Next Steps' : 'admin/runai-setup/self-hosted/ocp/next-steps.md'
          - 'Upgrade' : 'admin/runai-setup/self-hosted/ocp/upgrade.md'
          - 'Uninstall' : 'admin/runai-setup/self-hosted/ocp/uninstall.md'
      - 'Configuration' : 
        - 'Overview' : 'admin/runai-setup/config/overview.md'
        - 'Set Node Roles' : 'admin/runai-setup/config/node-roles.md'
        - 'Review Kubernetes Access provided to Run:ai' : 'admin/runai-setup/config/access-roles.md'
        - 'External access to Containers' : 'admin/runai-setup/config/allow-external-access-to-containers.md'
        - 'User Identity in Container' : 'admin/runai-setup/config/non-root-containers.md'
        - 'Install Administrator CLI' : 'admin/runai-setup/config/cli-admin-install.md'
        - 'Node Affinity with Cloud Node Pools' : 'admin/runai-setup/config/node-affinity-with-cloud-node-pools.md'
        - 'Local Certificate Authority' : 'admin/runai-setup/config/org-cert.md'
        - 'Backup & Restore' : 'admin/runai-setup/config/dr.md'
        - 'High Availability' : 'admin/runai-setup/config/ha.md'
        - 'Scaling' : 'admin/runai-setup/config/large-clusters.md'
      - 'Authentication' :
        - 'Overview' : 'admin/runai-setup/authentication/authentication-overview.md'
        - 'Access control' : 'admin/runai-setup/access-control/rbac.md'
        - 'Researcher Authentication' : 'admin/runai-setup/authentication/researcher-authentication.md'
        - 'Single Sign-On' : 'admin/runai-setup/authentication/sso.md'
      - 'Maintenance' : 
        - 'Node Downtime' : 'admin/runai-setup/maintenance/node-downtime.md'
        - 'Monitoring Cluster Health' : 'admin/runai-setup/maintenance/alert-monitoring.md'
        - 'Audit Log' : 'admin/runai-setup/maintenance/audit-log.md'
    - 'Researcher Setup' :
      - 'Introduction' : 'admin/researcher-setup/researcher-setup-intro.md'
      - 'Install the CLI' : 'admin/researcher-setup/cli-install.md'
    #  - 'Registry integration': 'admin/researcher-setup/registry-integration.md'
    #  - 'Use a Docker Registry with Credentials' : 'admin/researcher-setup/docker-registry-config.md'
      - 'Setup cluster wide PVC' : 'admin/researcher-setup/cluster-wide-pvc.md'
      - 'Group Nodes' : 'admin/researcher-setup/limit-to-node-group.md'
    #  - 'Messaging setup' : 'admin/researcher-setup/email-messaging.md'
    - 'Workloads' : 
      - 'admin/workloads/README.md'
      - 'Policies' :
        - 'admin/workloads/policies/README.md'
        - 'Former Policies' : 'admin/workloads/policies/policies.md'
        - 'Training Policy' : 'admin/workloads/policies/training-policy.md'
        - 'Workspaces Policy' : 'admin/workloads/policies/workspaces-policy.md'
      - 'Secrets' : 'admin/workloads/secrets.md'
      - 'Inference' : 'admin/workloads/inference-overview.md'
    - 'User Interface' :
      - 'Overview' : 'admin/admin-ui-setup/overview.md'
      - 'Users' : 'admin/admin-ui-setup/admin-ui-users.md'
      - 'Projects' : 'admin/admin-ui-setup/project-setup.md'
      - 'Departments' : 'admin/admin-ui-setup/department-setup.md'
      - 'Dashboard Analysis' : 'admin/admin-ui-setup/dashboard-analysis.md'
      - 'Jobs' : 'admin/admin-ui-setup/jobs.md'
      - 'Credentials' : 'admin/admin-ui-setup/credentials-setup.md'
      - 'Deployments' : 'admin/admin-ui-setup/deployments.md'
      - 'Templates': 'admin/admin-ui-setup/templates.md'
    - 'Troubleshooting' : 
      - 'Cluster Health' : 'admin/troubleshooting/cluster-health-check.md'
      - 'Troubleshooting' : 'admin/troubleshooting/troubleshooting.md'
      - 'Diagnostics' : 'admin/troubleshooting/diagnostics.md'
      - 'Alert Manager Alerts' :
        - 'admin/troubleshooting/alertmanager/README.md'
        - 'Runai Agent Cluster Info Push Rate Low' : 'admin/troubleshooting/alertmanager/RunaiAgentClusterInfoPushRateLow.md'
        - 'Runai Agent Pull Rate Low' : 'admin/troubleshooting/alertmanager/RunaiAgentPullRateLow.md'
        - 'Runai Container Memory Usage Critical' : 'admin/troubleshooting/alertmanager/RunaiContainerMemoryUsageCritical.md'
        - 'Runai Container Memory Usage Warning' : 'admin/troubleshooting/alertmanager/RunaiContainerMemoryUsageWarning.md'
        - 'Runai Container Restarting' : 'admin/troubleshooting/alertmanager/RunaiContainerRestarting.md'
        - 'Runai Cpu Usage Warning' : 'admin/troubleshooting/alertmanager/RunaiCpuUsageWarning.md'
        - 'Runai Critical Problem' : 'admin/troubleshooting/alertmanager/RunaiCriticalProblem.md'
        - 'Runai DaemonSet Rollout Stuck' : 'admin/troubleshooting/alertmanager/RunaiDaemonSetRolloutStuck.md'
        - 'Runai DaemonSet Unavailable On Nodes' : 'admin/troubleshooting/alertmanager/RunaiDaemonSetUnavailableOnNodes.md'
        - 'Runai Deployment Insufficient Replicas' : 'admin/troubleshooting/alertmanager/RunaiDeploymentInsufficientReplicas.md'
        - 'Runai Deployment NoAvailable Replicas' : 'admin/troubleshooting/alertmanager/RunaiDeploymentNoAvailableReplicas.md'
        - 'Runai Deployment Unavailable Replicas' : 'admin/troubleshooting/alertmanager/RunaiDeploymentUnavailableReplicas.md'
        - 'Runai Project Controller Reconcile Failure' : 'admin/troubleshooting/alertmanager/RunaiProjectControllerReconcileFailure.md'
        - 'Runai StatefulSet Insufficient Replicas' : 'admin/troubleshooting/alertmanager/RunaiStatefulSetInsufficientReplicas.md'
        - 'Runai StatefulSet No Available Replicas' : 'admin/troubleshooting/alertmanager/RunaiStatefulSetNoAvailableReplicas.md'
    - 'Best Practices' :
      - 'From Docker to Run:ai ' : 'admin/researcher-setup/docker-to-runai.md'
#    - 'Integrations' :
#      - 'JupyterHub' : 'admin/integration/jupyterhub.md'
#      - 'Airflow' : 'admin/integration/airflow.md' 
#      - 'MLflow' :   'admin/integration/mlflow.md'
#      - 'Kubeflow' : 'admin/integration/kubeflow.md'
#      - 'Seldon Core' : 'admin/integration/seldon.md'
#      - 'ClearML' : 'admin/integration/clearml.md'
#      - 'Argo Workflows'  : 'admin/integration/argo-workflows.md'
#      - 'KubeVirt (VM)' : 'admin/integration/kubevirt.md'
#      - 'Weights & Biases' : 'admin/integration/weights-and-biases.md'
#      - 'Event Messaging': 'admin/integration/messaging.md'
#      - 'DeepSpeed': 'admin/integration/deepspeed.md'
#      - 'Comet' : 'admin/integration/comet.md'
#      - 'Spark' : 'admin/integration/spark.md'
#      - 'Ray' : 'admin/integration/ray.md'
  - 'Researcher' :
    - 'Overview' : 'Researcher/overview-researcher.md'
    - 'Quickstart Guides' :
      - 'Run:ai Quickstart Guides' : 'Researcher/Walkthroughs/quickstart-overview.md'
      - 'Training' : 'Researcher/Walkthroughs/walkthrough-train.md'
      - 'Build' : 'Researcher/Walkthroughs/walkthrough-build.md'
      - 'Build with Connected Ports' : 'Researcher/Walkthroughs/walkthrough-build-ports.md'
      - 'GPU Fractions' : 'Researcher/Walkthroughs/walkthrough-fractions.md'
      - 'Distributed Training Workloads' : 'Researcher/Walkthroughs/walkthrough-distributed-training.md'
      - 'Hyperparameter Optimization' : 'Researcher/Walkthroughs/walkthrough-hpo.md'
      - 'Over-Quota, Basic Fairness & Bin-Packing' : 'Researcher/Walkthroughs/walkthrough-overquota.md'
      - 'Queue Fairness' : 'Researcher/Walkthroughs/walkthrough-queue-fairness.md'
      - 'Inference' : 'Researcher/Walkthroughs/quickstart-inference.md'
      - 'Dynamic MIG' : 'Researcher/Walkthroughs/quickstart-mig.md'
    - 'User Interface' :
      - 'Workspaces' :
        - 'Introduction' : 'Researcher/user-interface/workspaces/overview.md'
        - 'Building Blocks' : 
          - 'Overview' : 'Researcher/user-interface/workspaces/blocks/building-blocks.md'
          - 'Environments' : 'Researcher/user-interface/workspaces/blocks/environments.md'
          - 'Compute Resources': 'Researcher/user-interface/workspaces/blocks/compute.md'
          - 'Data Sources' : 'Researcher/user-interface/workspaces/blocks/datasources.md'
        - 'Creation' :
            - 'Create an Environment' : 'Researcher/user-interface/workspaces/create/create-env.md'
            - 'Create a Compute Resource' : 'Researcher/user-interface/workspaces/create/create-compute.md'
            - 'Create a Data Source' :  'Researcher/user-interface/workspaces/create/create-ds.md'
            - 'Create a Workspace' :  'Researcher/user-interface/workspaces/create/workspace-v2.md'
        - 'Statuses' :  'Researcher/user-interface/workspaces/statuses.md'
      - 'Trainings' : 'Researcher/user-interface/trainings.md'
    - 'CLI Reference' :
      - 'Introduction' : 'Researcher/cli-reference/Introduction.md'
      - 'runai attach' : 'Researcher/cli-reference/runai-attach.md'
      - 'runai bash' : 'Researcher/cli-reference/runai-bash.md'
      - 'runai config' : 'Researcher/cli-reference/runai-config.md'
      - 'runai delete' : 'Researcher/cli-reference/runai-delete.md'
      - 'runai describe' : 'Researcher/cli-reference/runai-describe.md'
      - 'runai exec' : 'Researcher/cli-reference/runai-exec.md'
      - 'runai list' : 'Researcher/cli-reference/runai-list.md'
      - 'runai login' : 'Researcher/cli-reference/runai-login.md'
      - 'runai logout' : 'Researcher/cli-reference/runai-logout.md'
      - 'runai logs' : 'Researcher/cli-reference/runai-logs.md'
      - 'runai port-forward' : 'Researcher/cli-reference/runai-port-forwarding.md'
      - 'runai resume' : 'Researcher/cli-reference/runai-resume.md'
      - 'runai submit' : 'Researcher/cli-reference/runai-submit.md'
      - 'runai submit-dist mpi' : 'Researcher/cli-reference/runai-submit-dist-mpi.md'
      - 'runai submit-dist pytorch' : 'Researcher/cli-reference/runai-submit-dist-pytorch.md'
      - 'runai submit-dist tf' : 'Researcher/cli-reference/runai-submit-dist-TF.md'
      - 'runai submit-dist xgboost' : 'Researcher/cli-reference/runai-submit-dist-xgboost.md'
      - 'runai suspend' : 'Researcher/cli-reference/runai-suspend.md'
      - 'runai top node' : 'Researcher/cli-reference/runai-top-node.md'
      # - 'runai top job' : 'Researcher/cli-reference/runai-top-job.md'
      - 'runai update' : 'Researcher/cli-reference/runai-update.md'
      - 'runai version' : 'Researcher/cli-reference/runai-version.md'
      - 'runai whoami' : 'Researcher/cli-reference/runai-whoami.md'
    - 'Best Practices' :
      - 'Bare-Metal to Docker Images' : 'Researcher/best-practices/bare-metal-to-docker-images.md'
      - 'Convert a Workload to Run Unattended' : 'Researcher/best-practices/convert-to-unattended.md'
      - 'Save Deep Learning Checkpoints' : 'Researcher/best-practices/save-dl-checkpoints.md'
      - 'Environment Variables' : 'Researcher/best-practices/env-variables.md'
    - 'Scheduling' :
      - 'The Run:ai Scheduler' : 'Researcher/scheduling/the-runai-scheduler.md'
      - 'Allocation of GPU Fractions' : 'Researcher/scheduling/fractions.md'
      - 'Dynamic GPU Fractions': 'Researcher/scheduling/dynamic-gpu-fractions.md'
      - 'GPU Time Slicing' : 'Researcher/scheduling/GPU-time-slicing-scheduler.md'
      - 'Allocation of CPU and Memory' : 'Researcher/scheduling/allocation-of-cpu-and-memory.md'
      - 'Job Statuses' : 'Researcher/scheduling/job-statuses.md'
      - 'Scheduling Strategies' : 'Researcher/scheduling/strategies.md'
      - 'Scheduling workloads to AWS placement groups' : 'Researcher/scheduling/schedule-to-aws-groups.md'
      - 'Using Node Pools' : 'Researcher/scheduling/using-node-pools.md'
      - 'Hyperparameter Optimization' : 'Researcher/scheduling/hpo.md'
    - 'Tools' :
      - 'Visual Studio Code' : 'Researcher/tools/dev-vscode.md'    
      - 'PyCharm' : 'Researcher/tools/dev-pycharm.md'    
      - 'X11 & PyCharm' : 'Researcher/tools/dev-x11forward-pycharm.md'  
      - 'Jupyter Notebook' :  'Researcher/tools/dev-jupyter.md'
      - 'TensorBoard' :  'Researcher/tools/dev-tensorboard.md'  
    - 'Use Cases' : 'Researcher/use-cases.md'
  - 'Developer' :
    - 'Overview' : 'developer/overview-developer.md'
    - 'API Authentication' : 'developer/rest-auth.md'
    - 'Cluster API' :
      - 'Workloads Overview' : 'developer/cluster-api/workload-overview-dev.md'
      - 'Submit Workload via YAML'  : 'developer/cluster-api/submit-yaml.md'
      - 'Submit Workload via HTTP/REST'  : 'developer/cluster-api/submit-rest.md'
      - 'Submit CRON job via YAML'  : 'developer/cluster-api/submit-cron-yaml.md'
      - 'Kubernetes Workloads'  : 'developer/cluster-api/other-resources.md'
      - 'Reference' :
        - 'Training Workloads' : 'developer/cluster-api/reference/training.md'
        - 'Interactive Workloads' : 'developer/cluster-api/reference/interactive.md'
        - 'Distributed Training Workloads' : 'developer/cluster-api/reference/distributed.md'
        - 'Inference Workloads' : 'developer/cluster-api/reference/inference.md'
    - 'Control Plane API' : 'developer/admin-rest-api/overview.md'
    - 'Metrics API' : 
      - 'Metrics' : 'developer/metrics/metrics.md'
    - 'Deprecated APIs' :
      - 'Researcher API' : 
        - 'REST API' : 'developer/deprecated/researcher-rest-api/overview.md'
        - 'Kubernetes API' : 
          - 'Overview' : 'developer/deprecated/k8s-api/overview.md'
          - 'Submit a Job via YAML' : 'developer/deprecated/k8s-api/launch-job-via-yaml.md'
          - 'Submit a Job via Kubernetes API' : 'developer/deprecated/k8s-api/launch-job-via-kubernetes-api.md'
      - 'Inference API' :
        - 'Overview' : 'developer/deprecated/inference/overview.md' 
        - 'Setup' : 'developer/deprecated/inference/setup.md' 
        - 'Submit via CLI' : 'developer/deprecated/inference/submit-via-cli.md'