test: Enable running the end to end tests on K8S clusters other than Kind

Dockerfile.epp

@@ -1,6 +1,6 @@
 ## Minimal runtime Dockerfile (microdnf-only, no torch, wrapper in site-packages)
-# Build Stage: using Go 1.25 image
-FROM quay.io/projectquay/golang:1.25 AS builder
+# Build Stage: using Go 1.24 image
+FROM quay.io/projectquay/golang:1.24 AS builder
 
 ARG TARGETOS
 ARG TARGETARCH

Makefile

@@ -8,19 +8,22 @@ TARGETOS ?= $(shell go env GOOS)
 TARGETARCH ?= $(shell go env GOARCH)
 PROJECT_NAME ?= llm-d-inference-scheduler
 SIDECAR_IMAGE_NAME ?= llm-d-routing-sidecar
+VLLM_SIMULATOR_IMAGE_NAME ?= llm-d-inference-sim
 SIDECAR_NAME ?= pd-sidecar
 IMAGE_REGISTRY ?= ghcr.io/llm-d
 IMAGE_TAG_BASE ?= $(IMAGE_REGISTRY)/$(PROJECT_NAME)
 EPP_TAG ?= dev
 export EPP_TAG
-IMG = $(IMAGE_TAG_BASE):$(EPP_TAG)
+export EPP_IMAGE ?= $(IMAGE_TAG_BASE):$(EPP_TAG)
 SIDECAR_TAG ?= dev
 export SIDECAR_TAG
 SIDECAR_IMAGE_TAG_BASE ?= $(IMAGE_REGISTRY)/$(SIDECAR_IMAGE_NAME)
-SIDECAR_IMG = $(SIDECAR_IMAGE_TAG_BASE):$(SIDECAR_TAG)
+export SIDECAR_IMAGE ?= $(SIDECAR_IMAGE_TAG_BASE):$(SIDECAR_TAG)
 NAMESPACE ?= hc4ai-operator
 VLLM_SIMULATOR_TAG ?= v0.6.1
 export VLLM_SIMULATOR_TAG
+VLLM_SIMULATOR_TAG_BASE ?= $(IMAGE_REGISTRY)/$(VLLM_SIMULATOR_IMAGE_NAME)
+export VLLM_SIMULATOR_IMAGE ?= $(VLLM_SIMULATOR_TAG_BASE):$(VLLM_SIMULATOR_TAG)
 
 # Map go arch to typos arch
 ifeq ($(TARGETARCH),amd64)
@@ -57,8 +60,8 @@ BUILD_REF ?= $(shell git describe --abbrev=0 2>/dev/null)
 SRC = $(shell find . -type f -name '*.go')
 
 # Internal variables for generic targets
-epp_IMAGE = $(IMG)
-sidecar_IMAGE = $(SIDECAR_IMG)
+epp_IMAGE = $(EPP_IMAGE)
+sidecar_IMAGE = $(SIDECAR_IMAGE)
 epp_NAME = epp
 sidecar_NAME = $(SIDECAR_NAME)
 epp_LDFLAGS = -ldflags="$(LDFLAGS)"
@@ -185,7 +188,7 @@ uninstall: uninstall-docker ## Default uninstall using Docker
 .PHONY: install-docker
 install-docker: check-container-tool ## Install app using $(CONTAINER_RUNTIME)
 	@echo "Starting container with $(CONTAINER_RUNTIME)..."
-	$(CONTAINER_RUNTIME) run -d --name $(PROJECT_NAME)-container $(IMG)
+	$(CONTAINER_RUNTIME) run -d --name $(PROJECT_NAME)-container $(EPP_IMAGE)
 	@echo "$(CONTAINER_RUNTIME) installation complete."
 	@echo "To use $(PROJECT_NAME), run:"
 	@echo "alias $(PROJECT_NAME)='$(CONTAINER_RUNTIME) exec -it $(PROJECT_NAME)-container /app/$(PROJECT_NAME)'"
@@ -230,12 +233,12 @@ uninstall-k8s: check-kubectl check-kustomize check-envsubst ## Uninstall from Ku
 
 .PHONY: install-openshift
 install-openshift: check-kubectl check-kustomize check-envsubst ## Install on OpenShift
-	@echo $$PROJECT_NAME $$NAMESPACE $$IMAGE_TAG_BASE $$VERSION
+	@echo $$PROJECT_NAME $$NAMESPACE $$EPP_IMAGE
 	@echo "Creating namespace $(NAMESPACE)..."
 	kubectl create namespace $(NAMESPACE) 2>/dev/null || true
 	@echo "Deploying common resources from deploy/ ..."
 	# Build and substitute the base manifests from deploy, then apply them
-	kustomize build deploy/environments/openshift-base | envsubst '$$PROJECT_NAME $$NAMESPACE $$IMAGE_TAG_BASE $$VERSION' | kubectl apply -n $(NAMESPACE) -f -
+	kustomize build deploy/environments/openshift-base | envsubst '$$PROJECT_NAME $$NAMESPACE $$EPP_IMAGE' | kubectl apply -n $(NAMESPACE) -f -
 	@echo "Waiting for pod to become ready..."
 	sleep 5
 	@POD=$$(kubectl get pod -l app=$(PROJECT_NAME)-statefulset -n $(NAMESPACE) -o jsonpath='{.items[0].metadata.name}'); \
@@ -246,9 +249,9 @@ install-openshift: check-kubectl check-kustomize check-envsubst ## Install on Op
 .PHONY: uninstall-openshift
 uninstall-openshift: check-kubectl check-kustomize check-envsubst ## Uninstall from OpenShift
 	@echo "Removing resources from OpenShift..."
-	kustomize build deploy/environments/openshift-base | envsubst '$$PROJECT_NAME $$NAMESPACE $$IMAGE_TAG_BASE $$VERSION' | kubectl delete --force -f - || true
+	kustomize build deploy/environments/openshift-base | envsubst '$$PROJECT_NAME $$NAMESPACE $$EPP_IMAGE' | kubectl delete --force -f - || true
 	# @if kubectl api-resources --api-group=route.openshift.io | grep -q Route; then \
-	#   envsubst '$$PROJECT_NAME $$NAMESPACE $$IMAGE_TAG_BASE $$VERSION' < deploy/openshift/route.yaml | kubectl delete --force -f - || true; \
+	#   envsubst '$$PROJECT_NAME $$NAMESPACE $$EPP_IMAGE' < deploy/openshift/route.yaml | kubectl delete --force -f - || true; \
 	# fi
 	@POD=$$(kubectl get pod -l app=$(PROJECT_NAME)-statefulset -n $(NAMESPACE) -o jsonpath='{.items[0].metadata.name}'); \
 	echo "Deleting pod: $$POD"; \
@@ -260,18 +263,18 @@ uninstall-openshift: check-kubectl check-kustomize check-envsubst ## Uninstall f
 .PHONY: install-rbac
 install-rbac: check-kubectl check-kustomize check-envsubst ## Install RBAC
 	@echo "Applying RBAC configuration from deploy/rbac..."
-	kustomize build deploy/environments/openshift-base/rbac | envsubst '$$PROJECT_NAME $$NAMESPACE $$IMAGE_TAG_BASE $$VERSION' | kubectl apply -f -
+	kustomize build deploy/environments/openshift-base/rbac | envsubst '$$PROJECT_NAME' | kubectl apply -f -
 
 .PHONY: uninstall-rbac
 uninstall-rbac: check-kubectl check-kustomize check-envsubst ## Uninstall RBAC
 	@echo "Removing RBAC configuration from deploy/rbac..."
-	kustomize build deploy/environments/openshift-base/rbac | envsubst '$$PROJECT_NAME $$NAMESPACE $$IMAGE_TAG_BASE $$VERSION' | kubectl delete -f - || true
+	kustomize build deploy/environments/openshift-base/rbac | envsubst '$$PROJECT_NAME' | kubectl delete -f - || true
 
 ##@ Environment
 .PHONY: env
 env: ## Print environment variables
 	@echo "IMAGE_TAG_BASE=$(IMAGE_TAG_BASE)"
-	@echo "IMG=$(IMG)"
+	@echo "EPP_IMAGE=$(EPP_IMAGE)"
 	@echo "CONTAINER_RUNTIME=$(CONTAINER_RUNTIME)"
 
 .PHONY: check-typos
@@ -390,7 +393,9 @@ env-dev-kind: ## Run under kind ($(KIND_CLUSTER_NAME))
 		CLUSTER_NAME=$(KIND_CLUSTER_NAME) \
 		GATEWAY_HOST_PORT=$(KIND_GATEWAY_HOST_PORT) \
 		IMAGE_REGISTRY=$(IMAGE_REGISTRY) \
-		EPP_TAG=$(EPP_TAG) \
+		EPP_IMAGE=$(EPP_IMAGE) \
+		VLLM_SIMULATOR_IMAGE=${VLLM_SIMULATOR_IMAGE} \
+		SIDECAR_IMAGE=${SIDECAR_IMAGE} \
 		./scripts/kind-dev-env.sh; \
 	fi
 

deploy/components/inference-gateway/deployments.yaml

@@ -18,7 +18,7 @@ spec:
       terminationGracePeriodSeconds: 130
       containers:
       - name: epp
-        image: ghcr.io/llm-d/llm-d-inference-scheduler:latest
+        image: ${EPP_IMAGE}
         imagePullPolicy: IfNotPresent
         args:
         - --pool-name

deploy/components/inference-gateway/kustomization.yaml

@@ -18,7 +18,3 @@ resources:
 - deployments.yaml
 - gateways.yaml
 - httproutes.yaml
-
-images:
-- name: ghcr.io/llm-d/llm-d-inference-scheduler
-  newTag: ${EPP_TAG}

deploy/components/vllm-sim-pd/deployments.yaml

@@ -17,7 +17,7 @@ spec:
     spec:
       containers:
       - name: vllm
-        image: ghcr.io/llm-d/llm-d-inference-sim:latest
+        image: ${VLLM_SIMULATOR_IMAGE}
         imagePullPolicy: IfNotPresent
         args:
         - "--port=8000"
@@ -71,7 +71,7 @@ spec:
     spec:
       initContainers:
       - name: routing-sidecar
-        image: ghcr.io/llm-d/llm-d-routing-sidecar:latest
+        image: ${SIDECAR_IMAGE}
         imagePullPolicy: IfNotPresent
         args:
         - "--port=8000"
@@ -112,7 +112,7 @@ spec:
               fieldPath: status.podIP
       containers:
       - name: vllm
-        image: ghcr.io/llm-d/llm-d-inference-sim:latest
+        image: ${VLLM_SIMULATOR_IMAGE}
         imagePullPolicy: IfNotPresent
         args:
         - "--port=8200"

deploy/components/vllm-sim-pd/kustomization.yaml

@@ -10,9 +10,3 @@ kind: Kustomization
 
 resources:
 - deployments.yaml
-
-images:
-- name: ghcr.io/llm-d/llm-d-inference-sim
-  newTag: ${VLLM_SIMULATOR_TAG}
-- name: ghcr.io/llm-d/llm-d-routing-sidecar
-  newTag: ${SIDECAR_TAG}

deploy/components/vllm-sim/deployments.yaml

@@ -16,7 +16,7 @@ spec:
     spec:
       initContainers:
       - name: routing-sidecar
-        image: ghcr.io/llm-d/llm-d-routing-sidecar:latest
+        image: ${SIDECAR_IMAGE}
         imagePullPolicy: IfNotPresent
         args:
         - "--port=8000"
@@ -57,7 +57,7 @@ spec:
               fieldPath: status.podIP
       containers:
       - name: vllm
-        image: ghcr.io/llm-d/llm-d-inference-sim:latest
+        image: ${VLLM_SIMULATOR_IMAGE}
         imagePullPolicy: IfNotPresent
         args:
         - "--port=8200"

deploy/components/vllm-sim/kustomization.yaml

@@ -11,9 +11,3 @@ kind: Kustomization
 resources:
 - deployments.yaml
 
-images:
-- name: ghcr.io/llm-d/llm-d-inference-sim
-  newTag: ${VLLM_SIMULATOR_TAG}
-- name: ghcr.io/llm-d/llm-d-routing-sidecar
-  newTag: ${SIDECAR_TAG}
-

deploy/environments/openshift-base/common/patch-statefulset.yaml

@@ -16,5 +16,5 @@ spec:
       serviceAccountName: operator-controller-manager
       containers:
         - name: cmd
-          image: ${IMAGE_TAG_BASE}:${VERSION}
+          image: ${EPP_IMAGE}
           imagePullPolicy: Always

deploy/environments/openshift-base/kustomization.yaml

@@ -26,8 +26,7 @@ configMapGenerator:
 # Define the image to be updated.
 # images:
 # - name: ghcr.io/llm-d/placeholder
-#   newName: ghcr.io/llm-d/${IMAGE_TAG_BASE}
-#   newTag: ${VERSION}
+#   newName: ${EPP_IMAGE}
 patches:
 - path: common/patch-service.yaml
 - path: common/patch-statefulset.yaml

docs/create_new_filter.md

@@ -127,7 +127,7 @@ Once a filter is defined, it can be used to modify llm-d-inference-scheduler
 
 - Add the relevant import path (if defined outside this repository);
 - Add any desired configuration knobs (e.g., environment variables); and
-- Listing the new filter in the `LoadConfig()` function's `cfg.loadPluginInfo`
+- Listing the new filter in the `LoadConfigPhaseTwo()` function's `cfg.loadPluginInfo`
  list of available plugins.
 
 In the case of the llm-d-inference-scheduler, filters can be hooked into the
@@ -137,7 +137,7 @@ In the case of the llm-d-inference-scheduler, filters can be hooked into the
  environment variables):
 
 ```go 
-func (c *Config) LoadConfig() {
+func (c *Config) LoadConfigPhaseTwo() {
 	c.loadPluginInfo(c.DecodeSchedulerPlugins, false,
 		KVCacheScorerName, ..., ByLabelFilterName, ... )
 	c.loadPluginInfo(c.PrefillSchedulerPlugins, true, ... )

go.mod

@@ -25,7 +25,7 @@ require (
 	k8s.io/utils v0.0.0-20250820121507-0af2bda4dd1d
 	sigs.k8s.io/controller-runtime v0.22.4
 	sigs.k8s.io/gateway-api v1.4.0
-	sigs.k8s.io/gateway-api-inference-extension v1.1.0
+	sigs.k8s.io/gateway-api-inference-extension v0.0.0-20251119101812-bef80ca4dedd
 )
 
 require (
@@ -44,7 +44,7 @@ require (
 	github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f // indirect
 	github.com/dustin/go-humanize v1.0.1 // indirect
 	github.com/emicklei/go-restful/v3 v3.13.0 // indirect
-	github.com/envoyproxy/go-control-plane/envoy v1.35.0 // indirect
+	github.com/envoyproxy/go-control-plane/envoy v1.36.0 // indirect
 	github.com/envoyproxy/protoc-gen-validate v1.2.1 // indirect
 	github.com/evanphx/json-patch/v5 v5.9.11 // indirect
 	github.com/felixge/httpsnoop v1.0.4 // indirect
@@ -78,9 +78,9 @@ require (
 	github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 // indirect
 	github.com/prometheus/client_golang v1.23.2 // indirect
 	github.com/prometheus/client_model v0.6.2 // indirect
-	github.com/prometheus/common v0.67.1 // indirect
+	github.com/prometheus/common v0.67.2 // indirect
 	github.com/prometheus/procfs v0.17.0 // indirect
-	github.com/prometheus/prometheus v0.307.1 // indirect
+	github.com/prometheus/prometheus v0.307.3 // indirect
 	github.com/redis/go-redis/v9 v9.11.0 // indirect
 	github.com/spf13/cobra v1.9.1 // indirect
 	github.com/spf13/pflag v1.0.7 // indirect
@@ -108,14 +108,14 @@ require (
 	go.yaml.in/yaml/v2 v2.4.3 // indirect
 	go.yaml.in/yaml/v3 v3.0.4 // indirect
 	golang.org/x/exp v0.0.0-20250808145144-a408d31f581a // indirect
-	golang.org/x/mod v0.28.0 // indirect
-	golang.org/x/net v0.44.0 // indirect
-	golang.org/x/oauth2 v0.31.0 // indirect
-	golang.org/x/sys v0.36.0 // indirect
-	golang.org/x/term v0.35.0 // indirect
-	golang.org/x/text v0.29.0 // indirect
+	golang.org/x/mod v0.29.0 // indirect
+	golang.org/x/net v0.46.0 // indirect
+	golang.org/x/oauth2 v0.32.0 // indirect
+	golang.org/x/sys v0.37.0 // indirect
+	golang.org/x/term v0.36.0 // indirect
+	golang.org/x/text v0.30.0 // indirect
 	golang.org/x/time v0.13.0 // indirect
-	golang.org/x/tools v0.37.0 // indirect
+	golang.org/x/tools v0.38.0 // indirect
 	gomodules.xyz/jsonpatch/v2 v2.4.0 // indirect
 	google.golang.org/genproto/googleapis/api v0.0.0-20250929231259-57b25ae835d4 // indirect
 	google.golang.org/genproto/googleapis/rpc v0.0.0-20250922171735-9219d122eba9 // indirect