example.yaml

apiVersion: v1
kind: Pod
metadata:
  name: gpu-pod
spec:
  containers:
    - name: ubuntu-container
      image: ubuntu:18.04
      command: ["bash", "-c", "sleep 86400"]
      resources:
        limits:
          nvidia.com/gpu: 2 # requesting 2 vGPUs
          #nvidia.com/gpumem: 3000 # Each vGPU containers 3000M device memory
          nvidia.com/gpumem-percentage: 50 #Each vGPU containers 50% device memory of that GPU. Can not be used with nvidia.com/gpumem
          #nvidia.com/gpucores: 90 # Utilization limit of this vGPU is set to 50% of total GPU utilization 
          #nvidia.com/priority: 0 # We only have two priority class, 0(high) and 1(low), default: 1 
          #The utilization of high priority task won't be limited to resourceCores unless sharing GPU node with other high priority tasks.
          #The utilization of low priority task won't be limited to resourceCores if no other tasks sharing its GPU.
    - name: ubuntu-container0
      image: ubuntu:18.04
      command: ["bash", "-c", "sleep 86400"]
    - name: ubuntu-container1
      image: ubuntu:18.04
      command: ["bash", "-c", "sleep 86400"]
      resources:
        limits:
          nvidia.com/gpu: 2 # requesting 2 vGPUs
          nvidia.com/gpumem: 2000
          #nvidia.com/gpucores: 90