[Feature]: Sharing GPUs among all containers of a K8s pod

[yx-lamini]

Suggestion Description

main-container requests GPU, rocm-smi-exporter-sidecar is another container of the pod; we'd

apiVersion: v1
kind: Pod
metadata:
  name: {{ pod-name }}
  labels:
    exporter: rocm-smi
spec:
  containers:
  - name: main-container
    image: main-container-imamge:v1
    resources:
      limits:
        amd.com/gpu: {{ count }}
  # Add the following sidecar container to your pod
  - name: rocm-smi-exporter-sidecar
    image: rocm-smi-exporter
    args: ["lrocm-smi-exporter", "--port=9001"]
    imagePullPolicy: Always
    ports:
    - containerPort: 9001
      name: prometheus

Operating System

No response

GPU

No response

ROCm Component

No response

[emircanerkul]

Wow too old one, looks no luck to get community support? @yx-lamini

I try to share GPU across other pods but no luck so far. Is this even supported? I'm trying to run this https://github.com/k8s-at-home/charts/blob/master/charts/stable/games-on-whales/templates/common.yaml which includes additionalContainers request gpu.

[ivan-sirosh]

would be nice to implement it. as soon as I moved from intel to amd, I miss the gpu sharing between containers.