dashboards/nvidia-gpu/metadata.yaml

sample_dashboards:
  -
    category: NVIDIA GPUs
    id: nvidia-overview
    display_name: NVIDIA GPU Monitoring Overview (GCE & GKE)
    description: |-
      Displays GPU metrics for both GKE Nodes and GCE VMs.  GPU metrics for the GCE VMs require the Ops Agent to be installed.
  -
    category: NVIDIA GPUs
    id: nvidia-dcgm
    display_name: NVIDIA GPU Monitoring Advanced DCGM Metrics (GCE Only)
    description: |-
      Displays Advanced GPU metrics from NVIDIA Datacenter GPU Manager (DCGM).  This requires a specific setup (e.g. installing DCGM, installing the Ops Agent, and configuring it to receive DCGM metrics).
    related_integrations:
      - id: dcgm
        platform: GCE
  -
    category: NVIDIA GPUs
    id: nvidia-dcgm-prometheus
    display_name: NVIDIA GPU Monitoring Advanced DCGM Metrics (GKE Only)
    description: |-
      Displays Advanced GPU metrics from NVIDIA Datacenter GPU Manager (DCGM).  This requires a specific setup (e.g. installing DCGM and DCGM exporter).
    related_integrations:
      - id: dcgm
        platform: GKE
  -
    category: NVIDIA GPUs
    id: nvidia-triton-prometheus
    display_name: NVIDIA Triton Inference Server (GKE Only)
    description: |-
      This dashboard has charts displaying throughput, latency, resource usage, errors, and other metrics for inference.
    related_integrations:
      - id: nvidia-triton
        platform: GKE