Move hami deploy_isolator.sh to hack/hami folder

Signed-off-by: dttung2905 <ttdao.2015@accountancy.smu.edu.sg>

Author: dttung2905

…rd_party_integrations/deploy_isolator.sh hack/hami/deploy_isolator.shhack/third_party_integrations/deploy_isolator.sh renamed to hack/hami/deploy_isolator.sh hack/third_party_integrations/deploy_isolator.sh renamed to hack/hami/deploy_isolator.sh

@@ -2,8 +2,8 @@
 # Copyright 2026 NVIDIA CORPORATION
 # SPDX-License-Identifier: Apache-2.0
 #
-# Installs kai-resource-isolator with kai-vgpu-monitor enabled so hamicore e2e
-# can scrape hami_* per-container VRAM metrics on :9394.
+# Installs kai-resource-isolator with kai-vgpu-monitor enabled for HAMi/hamicore
+# e2e (see --test-hami in hack/setup-e2e-cluster.sh).
 #
 # Overrides (optional):
 #   ISOLATOR_CHART_REF       OCI ref or local chart path

hack/run-e2e-kind.sh

@@ -11,6 +11,7 @@ GOBIN=${GOPATH}/bin
 
 # Parse named parameters
 TEST_THIRD_PARTY_INTEGRATIONS="false"
+TEST_HAMI="false"
 LOCAL_IMAGES_BUILD="false"
 PRESERVE_CLUSTER="false"
 
@@ -20,6 +21,10 @@ while [[ $# -gt 0 ]]; do
       TEST_THIRD_PARTY_INTEGRATIONS="true"
       shift
       ;;
+    --test-hami)
+      TEST_HAMI="true"
+      shift
+      ;;
     --local-images-build)
       LOCAL_IMAGES_BUILD="true"
       shift
@@ -29,8 +34,9 @@ while [[ $# -gt 0 ]]; do
       shift
       ;;
     -h|--help)
-      echo "Usage: $0 [--test-third-party-integrations] [--local-images-build] [--preserve-cluster]"
+      echo "Usage: $0 [--test-third-party-integrations] [--test-hami] [--local-images-build] [--preserve-cluster]"
       echo "  --test-third-party-integrations: Install third party operators for compatibility testing"
+      echo "  --test-hami: Enable HAMi/hamicore integration (binder hamicore plugin + kai-resource-isolator)"
       echo "  --local-images-build: Build and use local images instead of pulling from registry"
       echo "  --preserve-cluster: Keep the kind cluster after running the test suite"
       exit 0
@@ -48,6 +54,9 @@ SETUP_ARGS=""
 if [ "$TEST_THIRD_PARTY_INTEGRATIONS" = "true" ]; then
     SETUP_ARGS="$SETUP_ARGS --test-third-party-integrations"
 fi
+if [ "$TEST_HAMI" = "true" ]; then
+    SETUP_ARGS="$SETUP_ARGS --test-hami"
+fi
 if [ "$LOCAL_IMAGES_BUILD" = "true" ]; then
     SETUP_ARGS="$SETUP_ARGS --local-images-build"
 fi

hack/setup-e2e-cluster.sh

@@ -31,6 +31,7 @@ trap cleanup EXIT
 
 # Parse named parameters
 TEST_THIRD_PARTY_INTEGRATIONS=${TEST_THIRD_PARTY_INTEGRATIONS:-"false"}
+TEST_HAMI=${TEST_HAMI:-"false"}
 LOCAL_IMAGES_BUILD=${LOCAL_IMAGES_BUILD:-"false"}
 INSTALL_VPA=${INSTALL_VPA:-"false"}
 SKIP_KAI_INSTALL=${SKIP_KAI_INSTALL:-"false"}
@@ -41,6 +42,10 @@ while [[ $# -gt 0 ]]; do
       TEST_THIRD_PARTY_INTEGRATIONS="true"
       shift
       ;;
+    --test-hami)
+      TEST_HAMI="true"
+      shift
+      ;;
     --local-images-build)
       LOCAL_IMAGES_BUILD="true"
       shift
@@ -62,8 +67,9 @@ while [[ $# -gt 0 ]]; do
       shift 2
       ;;
     -h|--help)
-      echo "Usage: $0 [--test-third-party-integrations] [--local-images-build] [--install-vpa] [--skip-kai-install] [--feature-config <config>] [--kind-config <path>]"
+      echo "Usage: $0 [--test-third-party-integrations] [--test-hami] [--local-images-build] [--install-vpa] [--skip-kai-install] [--feature-config <config>] [--kind-config <path>]"
       echo "  --test-third-party-integrations: Install third party operators for compatibility testing"
+      echo "  --test-hami: Enable HAMi/hamicore integration (binder hamicore plugin + kai-resource-isolator)"
       echo "  --local-images-build: Build and use local images instead of pulling from registry"
       echo "  --install-vpa: Install Vertical Pod Autoscaler and metrics-server"
       echo "  --skip-kai-install: Prepare the cluster (and images/chart with --local-images-build) without installing KAI (e.g. for gitops e2e tests)"
@@ -79,6 +85,17 @@ while [[ $# -gt 0 ]]; do
   esac
 done
 
+# Extra helm --set flags for HAMi/hamicore. Kind e2e has no nvidia RuntimeClass, so clear
+# the defaults that would otherwise reject GPU-fraction pods at admission.
+HAMI_HELM_SETS=()
+if [ "$TEST_HAMI" = "true" ]; then
+  HAMI_HELM_SETS+=(
+    --set "binder.plugins.hamicore.enabled=true"
+    --set "binder.resourceReservation.runtimeClassName="
+    --set "admission.gpuFractionRuntimeClassName="
+  )
+fi
+
 if [[ -n "$KIND_CONFIG" && "$FEATURE_CONFIG" != "default" ]]; then
   echo "--feature-config cannot be used together with --kind-config"
   exit 1
@@ -147,9 +164,6 @@ if [ "$TEST_THIRD_PARTY_INTEGRATIONS" = "true" ]; then
     ${REPO_ROOT}/hack/third_party_integrations/deploy_knative.sh
     ${REPO_ROOT}/hack/third_party_integrations/deploy_lws.sh
     ${REPO_ROOT}/hack/third_party_integrations/deploy_jobset.sh
-    # HAMi-core / GPU-sharing isolation + optional VRAM metrics (:9394).
-    # Soft-gated in hamicore e2e when the webhook / monitor are absent.
-    ${REPO_ROOT}/hack/third_party_integrations/deploy_isolator.sh
 fi
 
 # Build and install kai-scheduler
@@ -207,7 +221,8 @@ if [ "$LOCAL_IMAGES_BUILD" = "true" ]; then
     else
         helm upgrade -i kai-scheduler ./charts/kai-scheduler-$PACKAGE_VERSION.tgz -n kai-scheduler --create-namespace \
         --values ${REPO_ROOT}/hack/kai-scheduler-fake-npe-values.yaml \
-        --set "global.gpuSharing=true" --set "global.registry=localhost:30100" --set "prometheus.enabled=true" --debug --wait
+        --set "global.gpuSharing=true" --set "global.registry=localhost:30100" --set "prometheus.enabled=true" \
+        "${HAMI_HELM_SETS[@]}" --debug --wait
         rm -rf ./charts/kai-scheduler-$PACKAGE_VERSION.tgz
     fi
     cd ${REPO_ROOT}/hack
@@ -216,7 +231,8 @@ elif [ "$SKIP_KAI_INSTALL" = "true" ]; then
 else
     helm upgrade -i kai-scheduler oci://ghcr.io/kai-scheduler/kai-scheduler/kai-scheduler -n kai-scheduler --create-namespace \
         --values ${REPO_ROOT}/hack/kai-scheduler-fake-npe-values.yaml \
-        --set "global.gpuSharing=true" --set "prometheus.enabled=true" --wait --version "$PACKAGE_VERSION"
+        --set "global.gpuSharing=true" --set "prometheus.enabled=true" \
+        "${HAMI_HELM_SETS[@]}" --wait --version "$PACKAGE_VERSION"
 fi
 
 if [ "$SKIP_KAI_INSTALL" != "true" ]; then
@@ -225,4 +241,11 @@ if [ "$SKIP_KAI_INSTALL" != "true" ]; then
     kubectl create rolebinding fake-status-updater --clusterrole=pods-patcher --serviceaccount=gpu-operator:status-updater -n kai-resource-reservation
 fi
 
+# HAMi resource isolation (kai-resource-isolator). Deeper than third-party CRD
+# operators: paired with binder hamicore helm values above. Soft-gated in
+# hamicore e2e when the webhook / monitor are absent.
+if [ "$TEST_HAMI" = "true" ]; then
+    ${REPO_ROOT}/hack/hami/deploy_isolator.sh
+fi
+
 echo "Cluster setup complete. Cluster name: $CLUSTER_NAME"

test/e2e/suites/integrations/third_party/hamicore/hamicore_test.go

@@ -241,7 +241,7 @@ var _ = Describe("HAMi-core resource isolation", Ordered, func() {
 			if !isKaiVGPUMonitorInstalled(ctx, testCtx.KubeClientset) {
 				Skip(fmt.Sprintf(
 					"kai-vgpu-monitor DaemonSet %q not found in namespace %q; "+
-						"install via hack/third_party_integrations/deploy_isolator.sh",
+						"install via hack/hami/deploy_isolator.sh (--test-hami)",
 					kaiVGPUMonitorDaemonSetName, kaiResourceIsolatorNamespace,
 				))
 			}