Skip to main content
Version: 2.0

GPU Dashboard

GPU Dashboard is the operational view for an activated cluster. Use it after activation to confirm that GPU capacity is visible, identify unhealthy nodes, and inspect the resources used by model-serving workloads.

Before You Begin

  • The activation must have the Activated status.
  • Your account must be able to open the activation record.
  • A model-serving service must be running before service-level metrics appear.

Open GPU Dashboard

  1. In the Console, open BYO-GPU → Activate Cluster.
  2. Find an activation with the Activated status.
  3. In Actions, select the GPU Dashboard chart icon.

GPU Dashboard opens the cluster associated with that activation. If the chart icon is unavailable, wait for activation to finish or use Manage to resume the activation workflow.

Read the Cluster Overview

The overview brings four operational views together:

AreaWhat it tells youWhat to check
Real-time Resource UtilizationCurrent cluster capacity and utilization.Confirm the expected nodes and GPUs are reported.
Resource Utilization TrendsHow resource use changes over the selected time range.Look for sustained saturation or unexpected idle capacity.
Node ListHealth and utilization for individual machines.Open a node whose status or utilization differs from the rest.
Model ServingServices consuming the cluster.Open a service to investigate latency, throughput, cache, or availability.

Use the range control to switch between 1h, 6h, 24h, and 7d. The header shows when the oldest panel was last updated. Select Refresh when you need a new snapshot immediately.

Inspect a Node

Select a node from Node List to open its hardware view. Review:

  • Node overview and health.
  • GPU details and GPU utilization.
  • CPU and storage consumption.
  • Workloads currently assigned to each GPU.

If a node is missing, disconnected, or consistently saturated, resolve the infrastructure issue before increasing deployment replicas.

Inspect a Model-Serving Service

Select a service from Model Serving to open its service view. Depending on the serving engine and enabled metrics, the page can show:

  • End-to-end and inter-token latency.
  • Request rate and token throughput.
  • GPU and KV-cache efficiency.
  • Service availability.
  • Prefill/decode metrics for disaggregated serving.

Some engine-level metrics require the serving engine to expose metrics. An empty engine panel does not necessarily mean the service is unavailable; check the service status and request metrics together.

Verify the Result

The cluster is ready for model deployment when every expected node appears, the reported GPU capacity matches the activation plan, and no required node shows a connection or health problem. When a deployment is already running, confirm that its service also appears under Model Serving.

Troubleshooting

GPU Dashboard is not available

Confirm the activation status is Activated. For Activating records, select Manage and complete the remaining step.

A panel cannot load

Refresh the page. Dashboard panels load independently, so one unavailable metric source does not invalidate the remaining cluster data.

Capacity is lower than expected

Open Node List and compare every configured server. Then return to Activate Cluster to review the machine configuration and connection status.

Next Step

When cluster capacity and health are confirmed: