kuberay/ray-operator/test/e2erayservice/testdata/rayservice.autoscaling.yaml at d8248a1bbc0c80e290f586d7e44040c4fe68aa07 · ray-project/kuberay · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
apiVersion: ray.io/v1
kind: RayService
metadata:
  name: test-rayservice
spec:
  serveConfigV2: |
    applications:
      - name: no_ops
        route_prefix: /
        import_path: microbenchmarks.no_ops:app_builder
        args:
          num_forwards: 0
        runtime_env:
          working_dir: https://github.com/ray-project/serve_workloads/archive/a9f184f4d9ddb7f9a578502ae106470f87a702ef.zip
        deployments:
          - name: NoOp
            autoscaling_config:
              metrics_interval_s: 0.2
              min_replicas: 1
              max_replicas: 14
              look_back_period_s: 2
              downscale_delay_s: 5
              upscale_delay_s: 2
              target_ongoing_requests: 1
            graceful_shutdown_timeout_s: 5
            ray_actor_options:
              num_cpus: 0.5
  rayClusterConfig:
    rayVersion: "2.52.0"
    enableInTreeAutoscaling: true
    autoscalerOptions:
      idleTimeoutSeconds: 60
    headGroupSpec:
      rayStartParams:
        num-cpus: "0"
      template:
        spec:
          containers:
            - name: ray-head
              image: rayproject/ray:2.52.0
              resources:
                requests:
                  cpu: "1"
                  memory: 1G
                limits:
                  memory: 2G
              ports:
                - containerPort: 6379
                  name: gcs-server
                - containerPort: 8265
                  name: dashboard
                - containerPort: 10001
                  name: client
                - containerPort: 8000
                  name: serve
    workerGroupSpecs:
      - replicas: 0
        minReplicas: 0
        maxReplicas: 5
        groupName: small-group
        template:
          spec:
            containers:
              - name: ray-worker
                image: rayproject/ray:2.52.0
                resources:
                  requests:
                    cpu: "300m"
                    memory: "1G"
                  limits:
                    memory: "1G"