Distributed GPU Cluster Infrastructure

EverestQ Cloud & Cluster

Scale inference across hundreds of GPU compute nodes with automated heartbeats, circuit breaker edge gateways (:9000), and Kubernetes HPA auto-scaling.

k8s/everestq-cluster.yamlyaml

apiVersion: apps/v1
kind: Deployment
metadata:
  name: everestq-worker-pool
spec:
  replicas: 4
  selector:
    matchLabels:
      app: everestq-worker
  template:
    metadata:
      labels:
        app: everestq-worker
    spec:
      containers:
      - name: worker
        image: everestq/engine:v0.1.0
        args: ["eq-worker", "--cloud-api", "http://eq-cloud:8080"]
        resources:
          limits:
            nvidia.com/gpu: 1