Fix: isvc resource config name in inferenceservice configmap (kserve#4215)

Signed-off-by: Sukumar Gaonkar <sgaonkar4@bloomberg.net>
Co-authored-by: Dan Sun <dsun20@bloomberg.net>

Author: sukumargaonkar

charts/kserve-resources/README.md

@@ -63,10 +63,10 @@ $ helm install kserve oci://ghcr.io/kserve/charts/kserve --version v0.15.0-rc0
 | kserve.controller.tolerations | list | `[]` | A list of Kubernetes Tolerations, if required. For more information, see [Toleration v1 core](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.27/#toleration-v1-core).  For example:   tolerations:   - key: foo.bar.com/role     operator: Equal     value: master     effect: NoSchedule |
 | kserve.controller.topologySpreadConstraints | list | `[]` | A list of Kubernetes TopologySpreadConstraints, if required. For more information, see [Topology spread constraint v1 core](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.27/#topologyspreadconstraint-v1-core  For example:   topologySpreadConstraints:   - maxSkew: 2     topologyKey: topology.kubernetes.io/zone     whenUnsatisfiable: ScheduleAnyway     labelSelector:       matchLabels:         app.kubernetes.io/instance: kserve-controller-manager         app.kubernetes.io/component: controller |
 | kserve.controller.webhookServiceAnnotations | object | `{}` | Optional additional annotations to add to the webhook service. |
-| kserve.inferenceservice.resources.limits.cpu | string | `"100m"` |  |
-| kserve.inferenceservice.resources.limits.memory | string | `"256Mi"` |  |
-| kserve.inferenceservice.resources.requests.cpu | string | `"100m"` |  |
-| kserve.inferenceservice.resources.requests.memory | string | `"256Mi"` |  |
+| kserve.inferenceservice.resources.limits.cpu | string | `"1"` |  |
+| kserve.inferenceservice.resources.limits.memory | string | `"2Gi"` |  |
+| kserve.inferenceservice.resources.requests.cpu | string | `"1"` |  |
+| kserve.inferenceservice.resources.requests.memory | string | `"2Gi"` |  |
 | kserve.localmodel.agent.affinity | object | `{}` |  |
 | kserve.localmodel.agent.hostPath | string | `"/mnt/models"` |  |
 | kserve.localmodel.agent.image | string | `"kserve/kserve-localmodelnode-agent"` |  |

charts/kserve-resources/templates/configmap.yaml

@@ -609,7 +609,7 @@ data:
       "autoMountServiceAccountToken": {{ .Values.kserve.security.autoMountServiceAccountToken }}
     }
 
-  inferenceservice: |-
+  inferenceService: |-
     {
       "resource": {
         "cpuLimit": "{{ .Values.kserve.inferenceservice.resources.limits.cpu }}",

charts/kserve-resources/values.yaml

@@ -445,8 +445,8 @@ kserve:
   inferenceservice:
     resources:
       limits:
-        cpu: 100m
-        memory: 256Mi
+        cpu: "1"
+        memory: "2Gi"
       requests:
-        cpu: 100m
-        memory: 256Mi
+        cpu: "1"
+        memory: "2Gi"

config/configmap/inferenceservice.yaml

@@ -682,7 +682,7 @@ data:
       "autoMountServiceAccountToken": true
     }
     
-  inferenceservice: |-
+  inferenceService: |-
     {
       "resource": {
           "cpuLimit": "1",

pkg/apis/serving/v1beta1/inference_service_defaults.go

@@ -33,10 +33,11 @@ import (
 	logf "sigs.k8s.io/controller-runtime/pkg/log"
 	"sigs.k8s.io/controller-runtime/pkg/webhook"
 
+	"k8s.io/client-go/kubernetes/scheme"
+
 	"github.com/kserve/kserve/pkg/apis/serving/v1alpha1"
 	"github.com/kserve/kserve/pkg/constants"
 	"github.com/kserve/kserve/pkg/utils"
-	"k8s.io/client-go/kubernetes/scheme"
 )
 
 var (
@@ -84,8 +85,6 @@ func setResourceRequirementDefaults(config *InferenceServicesConfig, requirement
 		}
 	}
 
-	logf.Log.Info("Setting default resource requirements -----------------", "requests", requirements.Requests, "limits", requirements.Limits)
-
 	if requirements.Limits == nil {
 		requirements.Limits = v1.ResourceList{}
 	}
@@ -94,6 +93,8 @@ func setResourceRequirementDefaults(config *InferenceServicesConfig, requirement
 			requirements.Limits[k] = v
 		}
 	}
+
+	logf.Log.Info("Setting default resource requirements ", "requests", requirements.Requests, "limits", requirements.Limits)
 }
 
 func (d *InferenceServiceDefaulter) Default(ctx context.Context, obj runtime.Object) error {