Skip to main content
Version: 3.4.0-rc.1

GPU Info Schema

This document defines the schema for the GET /gpu-info endpoint, which returns detailed information about GPU resources and usage across the cluster.

GPUInfoResponse​

Response for GET /gpu-info.

Properties​

PropertyTypeDescription
nodesNodeInfo[]List of nodes with GPU resources
podsPodInfo[]List of pods using GPU resources
prometheusMetricsbooleanWhether Prometheus metrics are available

NodeInfo Object​

PropertyTypeDescription
nodeNamestringName of the Kubernetes node
hostnamestringHostname of the node
totalVramMBnumberTotal VRAM available on the node in MB
usedVramMBnumberTotal VRAM used on the node in MB
gpusGPU[]List of GPUs on the node

GPU Object​

PropertyTypeDescription
idstringGPU ID (index)
uuidstringUnique UUID of the GPU
vramTotalMBnumberTotal VRAM of the GPU in MB
vramUsedMBnumberUsed VRAM of the GPU in MB
gpuTypestringType/Model of the GPU (e.g., "NVIDIA A100")

PodInfo Object​

PropertyTypeDescription
idstringPod ID (UID)
podNamestringName of the pod
nodeNamestringName of the node the pod is running on
gpuUsageGPUUsage[]List of GPU usage details for the pod

GPUUsage Object​

PropertyTypeDescription
idstringUUID of the GPU being used
vramUsedMBnumberAmount of VRAM used by the pod on this GPU in MB

Example​

{
"nodes": [
{
"nodeName": "gke-cluster-pool-1-12345",
"hostname": "node-1",
"totalVramMB": 81920,
"usedVramMB": 40960,
"gpus": [
{
"id": "0",
"uuid": "GPU-1234-5678-90ab-cdef",
"vramTotalMB": 40960,
"vramUsedMB": 20480,
"gpuType": "NVIDIA A100"
},
{
"id": "1",
"uuid": "GPU-aaaa-bbbb-cccc-dddd",
"vramTotalMB": 40960,
"vramUsedMB": 20480,
"gpuType": "NVIDIA A100"
}
]
}
],
"pods": [
{
"id": "pod-xyz-789",
"podName": "model-service-deployment-abc",
"nodeName": "gke-cluster-pool-1-12345",
"gpuUsage": [
{
"id": "GPU-1234-5678-90ab-cdef",
"vramUsedMB": 10240
}
]
}
],
"prometheusMetrics": true
}