How to Scale AMD GPU Workloads on DOKS using KEDA

				
					apiVersion: v1
kind: ConfigMap
metadata:
 name: go-program
data:
 main.go: |
 package main

 import (
 "log"
 "net/http"
 "strconv"
 "github.com/prometheus/client_golang/prometheus"
 "github.com/prometheus/client_golang/prometheus/promhttp"
 )
 
 var customGauge = prometheus.NewGauge(prometheus.GaugeOpts{
 Name: "my_custom_gauge",
 Help: "This is a custom gauge metric",
 })

 func init() {
 prometheus.MustRegister(customGauge)
 }
 
 func handler(w http.ResponseWriter, r *http.Request) {
 value := r.URL.Query().Get("value")
 floatVal, err := strconv.ParseFloat(value, 64)
 if err != nil {
 http.Error(w, "Bad Request: invalid input", http.StatusBadRequest)
 return
 }
 customGauge.Set(floatVal)
 w.Write([]byte("Hello, from the handler!"))
 }

 func main() {
 http.HandleFunc("/", handler)
 http.Handle("/metrics", promhttp.Handler())
 log.Fatal(http.ListenAndServe(":8080", nil))
 }
---
apiVersion: apps/v1
kind: Deployment
metadata:
 name: go-from-configmap
spec:
 replicas: 1
 selector:
 matchLabels:
 app: go-from-configmap
 template:
 metadata:
 labels:
 app: go-from-configmap
 spec:
 nodeSelector:
 www.progressiverobot.com/gpu-brand: amd
 tolerations:
 - key: CriticalAddonsOnly
 operator: Exists
 - key: amd.com/gpu
 operator: Exists
 containers:
 - name: go-runner
 image: golang:1.24
 command: ["/bin/sh", "-c"]
 resources:
 requests:
 amd.com/gpu: "1"
 limits:
 amd.com/gpu: "1"
 ports:
 - containerPort: 8080
 args:
 - |
 set -e 
 cp /config/*.go /app/
 cd /app
 [ -f go.mod ] || go mod init temp
 go mod tidy 
 go run . 
 volumeMounts:
 - name: go-code
 mountPath: /config
 - name: app-dir
 mountPath: /app
 volumes:
 - name: go-code
 configMap:
 name: go-program
 - name: app-dir
 emptyDir: {}
---
apiVersion: v1
kind: Service
metadata:
 name: go-from-configmap
 labels:
 app: go-from-configmap
spec:
 selector:
 app: go-from-configmap
 ports:
 - name: metrics
 port: 8080
 targetPort: 8080
---
apiVersion: monitoring.coreos.com/v1
kind: ServiceMonitor
metadata:
 name: go-from-configmap
 labels:
 release: prometheus
spec:
 selector:
 matchLabels:
 app: go-from-configmap
 endpoints:
 - port: metrics
 path: /metrics
 interval: 30s
 namespaceSelector:
 matchNames:
 - kube-system
---
apiVersion: keda.sh/v1alpha1
kind: ScaledObject
metadata:
 name: go-from-configmap
spec:
 scaleTargetRef:
 name: go-from-configmap
 pollingInterval: 30
 cooldownPeriod: 30
 minReplicaCount: 1
 maxReplicaCount: 8
 triggers:
 - type: prometheus
 metadata:
 serverAddress: http://prometheus-operated.kube-system.svc.cluster.local:9090
 metricName: my_custom_gauge
 threshold: '80'
 query: sum(my_custom_gauge{}) / sum(kube_deployment_status_replicas{deployment="go-from-configmap"})