feat: add serverless config for keda.

Signed-off-by: X1aoZEOuO <[email protected]>

Author: X1aoZEOuO

docs/examples/serverless/basic.yaml

@@ -0,0 +1,76 @@
+apiVersion: llmaz.io/v1alpha1
+kind: OpenModel
+metadata:
+  name: qwen2-0--5b
+spec:
+  familyName: qwen2
+  source:
+    modelHub:
+      modelID: Qwen/Qwen2-0.5B-Instruct-GGUF
+      filename: qwen2-0_5b-instruct-q5_k_m.gguf
+---
+apiVersion: inference.llmaz.io/v1alpha1
+kind: Playground
+metadata:
+  name: qwen2-0--5b
+spec:
+  replicas: 0
+  modelClaim:
+    modelName: qwen2-0--5b
+  backendRuntimeConfig:
+    backendName: llamacpp
+    configName: default
+    args:
+      - -fa # use flash attention
+---
+apiVersion: gateway.networking.k8s.io/v1
+kind: GatewayClass
+metadata:
+  name: default-envoy-ai-gateway
+spec:
+  controllerName: gateway.envoyproxy.io/gatewayclass-controller
+---
+apiVersion: gateway.networking.k8s.io/v1
+kind: Gateway
+metadata:
+  name: default-envoy-ai-gateway
+spec:
+  gatewayClassName: default-envoy-ai-gateway
+  listeners:
+    - name: http
+      protocol: HTTP
+      port: 80
+---
+apiVersion: aigateway.envoyproxy.io/v1alpha1
+kind: AIGatewayRoute
+metadata:
+  name: default-envoy-ai-gateway
+spec:
+  schema:
+    name: OpenAI
+  targetRefs:
+    - name: default-envoy-ai-gateway
+      kind: Gateway
+      group: gateway.networking.k8s.io
+  rules:
+    - matches:
+        - headers:
+            - type: Exact
+              name: x-ai-eg-model
+              value: qwen2-0--5b
+      backendRefs:
+        - name: qwen2-0--5b
+---
+apiVersion: aigateway.envoyproxy.io/v1alpha1
+kind: AIServiceBackend
+metadata:
+  name: qwen2-0--5b
+spec:
+  timeouts:
+    request: 3m
+  schema:
+    name: OpenAI
+  backendRef:
+    name: qwen2-0--5b-lb
+    kind: Service
+    port: 8080

docs/examples/serverless/scaled-object.yaml

@@ -0,0 +1,21 @@
+apiVersion: keda.sh/v1alpha1
+kind: ScaledObject
+metadata:
+  name: qwen2-0--5b-scaler
+  namespace: default
+spec:
+  scaleTargetRef:
+    apiVersion: inference.llmaz.io/v1alpha1
+    kind: Playground
+    name: qwen2-0--5b
+  pollingInterval: 30
+  cooldownPeriod: 50
+  minReplicaCount: 0
+  maxReplicaCount: 3
+  triggers:
+  - type: prometheus
+    metadata:
+      serverAddress: http://prometheus-operated.llmaz-system.svc.cluster.local:9090
+      metricName: llamacpp:requests_processing
+      query: sum(llamacpp:requests_processing)
+      threshold: "0.2"

docs/examples/serverless/service-monitor.yaml

@@ -0,0 +1,18 @@
+apiVersion: monitoring.coreos.com/v1
+kind: ServiceMonitor
+metadata:
+  name: qwen2-0--5b-lb-monitor
+  namespace: llmaz-system
+  labels:
+    control-plane: controller-manager
+    app.kubernetes.io/name: servicemonitor
+spec:
+  namespaceSelector:
+    any: true
+  selector:
+    matchLabels:
+      llmaz.io/model-name: qwen2-0--5b
+  endpoints:
+    - port: http
+      path: /metrics
+      scheme: http