Merge branch 'main' into version_json

Signed-off-by: Etai Lev Ran <elevran@gmail.com>

Author: elevran

.github/dependabot.yml

@@ -0,0 +1,44 @@
+version: 2
+updates:
+
+  # 1. Go module updates
+  - package-ecosystem: "gomod"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+    open-pull-requests-limit: 10
+    commit-message:
+      prefix: "deps(go)"
+    labels:
+      - "dependencies"
+      - "release-note-none"
+    groups:
+      go-dependencies:
+        patterns:
+          - "*"
+      kubernetes:
+        patterns:
+          - "k8s.io/*"
+          - "sigs.k8s.io/*"
+
+  # 2. GitHub Actions dependencies
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+    labels:
+      - "ci"
+      - "dependencies"
+    commit-message:
+      prefix: "deps(actions)"
+
+  # 3. Docker base image updates (e.g., for Dockerfile FROM lines)
+  - package-ecosystem: "docker"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+    labels:
+      - "dependencies"
+      - "docker"
+    commit-message:
+      prefix: "deps(docker)"

.github/workflows/md-link-check.yml

@@ -0,0 +1,26 @@
+name: Markdown Link Checker
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+  workflow_dispatch:
+
+jobs:
+  lychee:
+    name: Check Markdown Links
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Install lychee v0.18.1
+        run: |
+          curl -Ls https://github.com/lycheeverse/lychee/releases/download/lychee-v0.18.1/lychee-x86_64-unknown-linux-gnu.tar.gz | tar xz
+          sudo mv lychee /usr/local/bin
+
+      - name: Run lychee on Markdown files with config
+        run: |
+          find . -name "*.md" -print0 | xargs -0 lychee --config .lychee.toml --verbose --no-progress

.lychee.toml

@@ -0,0 +1,13 @@
+# Ignore transient failures on gnu.org (it sometimes refuses connections)
+exclude = [
+  "^https://www.gnu.org/software/make/?$"
+]
+
+# Timeout in seconds
+timeout = 20
+
+# Retry failed links (helpful for flaky sites)
+retry_count = 3
+
+# Accept non-200 status codes (429: rate limits)
+accept = [200, 429]

DEVELOPMENT.md

@@ -92,10 +92,15 @@ make env-dev-kind
 ```
 
 This will build images with your recent changes and load the new images to the
-cluster. Note that built image tag should be specified via the `EPP_TAG` environment variable so it is used in the deployment. For example:
+cluster. By default the image tag will be `dev`. It will also load `llm-d-inference-sim` image.
+
+**NOTE:** The built image tag can be specified via the `EPP_TAG` environment variable so it is used in the deployment. For example:
 
 ```console
 EPP_TAG=0.0.4 make env-dev-kind
+```
+
+**NOTE:** If you want to load a different tag of llm-d-inference-sim, you can use the environment variable `VLLM_SIMULATOR_TAG` to specify it.
 
 **NOTE**: If you are working on a MacOS with Apple Silicon, it is required to add
 the environment variable `GOOS=linux`.

Dockerfile

@@ -32,9 +32,9 @@ ENV GOOS=${TARGETOS:-linux}
 ENV GOARCH=${TARGETARCH}
 RUN go build -a -o bin/epp -ldflags="-extldflags '-L$(pwd)/lib'" cmd/epp/main.go cmd/epp/health.go
 
-# Use distroless as minimal base image to package the manager binary
-# Refer to https://github.com/GoogleContainerTools/distroless for more details
-FROM registry.access.redhat.com/ubi9/ubi:latest
+# Use ubi9 as a minimal base image to package the manager binary
+# Refer to https://catalog.redhat.com/software/containers/ubi9/ubi-minimal/615bd9b4075b022acc111bf5 for more details
+FROM registry.access.redhat.com/ubi9/ubi-minimal:latest
 WORKDIR /
 COPY --from=builder /workspace/bin/epp /app/epp
 USER 65532:65532

Makefile

@@ -4,11 +4,10 @@ SHELL := /usr/bin/env bash
 TARGETOS ?= $(shell go env GOOS)
 TARGETARCH ?= $(shell go env GOARCH)
 PROJECT_NAME ?= llm-d-inference-scheduler
-DEV_VERSION ?= 0.0.3
-PROD_VERSION ?= 0.0.2
 IMAGE_REGISTRY ?= ghcr.io/llm-d
 IMAGE_TAG_BASE ?= $(IMAGE_REGISTRY)/$(PROJECT_NAME)
-IMG = $(IMAGE_TAG_BASE):$(DEV_VERSION)
+EPP_TAG ?= dev
+IMG = $(IMAGE_TAG_BASE):$(EPP_TAG)
 NAMESPACE ?= hc4ai-operator
 
 CONTAINER_TOOL := $(shell { command -v docker >/dev/null 2>&1 && echo docker; } || { command -v podman >/dev/null 2>&1 && echo podman; } || echo "")
@@ -67,7 +66,7 @@ test-integration: download-tokenizer
 post-deploy-test: ## Run post deployment tests
 	echo Success!
 	@echo "Post-deployment tests passed."
-	
+
 .PHONY: lint
 lint: check-golangci-lint ## Run lint
 	@printf "\033[33;1m==== Running linting ====\033[0m\n"
@@ -82,48 +81,6 @@ build: check-go download-tokenizer ##
 
 ##@ Container Build/Push
 
-.PHONY: buildah-build
-	@if [ "$(BUILDER)" = "buildah" ]; then \
-	  echo "🔧 Buildah detected: Performing multi-arch build..."; \
-	  FINAL_TAG=$(IMG); \
-	  for arch in amd64; do \
-	    ARCH_TAG=$$FINAL_TAG-$$arch; \
-	    echo "📦 Building for architecture: $$arch"; \
-				buildah build \
-        			--arch=$$arch \
-        			--os=linux \
-        			--layers -t $(IMG)-$$arch . || exit 1; \
-	    echo "🚀 Pushing image: $(IMG)-$$arch"; \
-	    buildah push $(IMG)-$$arch docker://$(IMG)-$$arch || exit 1; \
-	  done; \
-	  echo "🧼 Removing existing manifest (if any)..."; \
-	  buildah manifest rm $$FINAL_TAG || true; \
-	  echo "🧱 Creating and pushing manifest list: $(IMG)"; \
-	  buildah manifest create $(IMG); \
-	  for arch in amd64; do \
-	    ARCH_TAG=$$FINAL_TAG-$$arch; \
-	    buildah manifest add $$FINAL_TAG $$ARCH_TAG; \
-	  done; \
-	  buildah manifest push --all $(IMG) docker://$(IMG); \
-	elif [ "$(BUILDER)" = "docker" ]; then \
-	  echo "🐳 Docker detected: Building with buildx..."; \
-	  sed -e '1 s/\(^FROM\)/FROM --platform=$${BUILDPLATFORM}/' Dockerfile > Dockerfile.cross; \
-	  - docker buildx create --use --name image-builder || true; \
-	  docker buildx use image-builder; \
-	  	  docker buildx build --push \
-      	  			--platform=$(PLATFORMS) \
-                      --tag $(IMG) -f Dockerfile.cross . || exit 1; \
-	  docker buildx rm image-builder || true; \
-	  rm Dockerfile.cross; \
-	elif [ "$(BUILDER)" = "podman" ]; then \
-	  echo "⚠️ Podman detected: Building single-arch image..."; \
-	  podman build -t $(IMG) . || exit 1; \
-	  podman push $(IMG) || exit 1; \
-	else \
-	  echo "❌ No supported container tool available."; \
-	  exit 1; \
-	fi
-
 .PHONY:	image-build
 image-build: check-container-tool ## Build Docker image ## Build Docker image using $(CONTAINER_TOOL)
 	@printf "\033[33;1m==== Building Docker image $(IMG) ====\033[0m\n"
@@ -181,7 +138,7 @@ install-k8s: check-kubectl check-kustomize check-envsubst ## Install on Kubernet
 	echo "Kubernetes installation complete."; \
 	echo "To use the app, run:"; \
 	echo "alias $(PROJECT_NAME)='kubectl exec -n $(NAMESPACE) -it $$POD -- /app/$(PROJECT_NAME)'"
-	
+
 .PHONY: uninstall-k8s
 uninstall-k8s: check-kubectl check-kustomize check-envsubst ## Uninstall from Kubernetes
 	export PROJECT_NAME=${PROJECT_NAME}
@@ -208,7 +165,7 @@ install-openshift: check-kubectl check-kustomize check-envsubst ## Install on Op
 	@POD=$$(kubectl get pod -l app=$(PROJECT_NAME)-statefulset -n $(NAMESPACE) -o jsonpath='{.items[0].metadata.name}'); \
 	echo "OpenShift installation complete."; \
 	echo "To use the app, run:"; \
-	echo "alias $(PROJECT_NAME)='kubectl exec -n $(NAMESPACE) -it $$POD -- /app/$(PROJECT_NAME)'" 
+	echo "alias $(PROJECT_NAME)='kubectl exec -n $(NAMESPACE) -it $$POD -- /app/$(PROJECT_NAME)'"
 
 .PHONY: uninstall-openshift
 uninstall-openshift: check-kubectl check-kustomize check-envsubst ## Uninstall from OpenShift
@@ -234,20 +191,25 @@ 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
 
+##@ Environment
+.PHONY: env
+env: ## Print environment variables
+	@echo "IMAGE_TAG_BASE=$(IMAGE_TAG_BASE)"
+	@echo "IMG=$(IMG)"
+	@echo "CONTAINER_TOOL=$(CONTAINER_TOOL)"
+
 ##@ Tools
 
 .PHONY: check-tools
 check-tools: \
   check-go \
   check-ginkgo \
   check-golangci-lint \
-  check-jq \
   check-kustomize \
   check-envsubst \
   check-container-tool \
   check-kubectl \
-  check-buildah \
-  check-podman
+  check-buildah
 	@echo "✅ All required tools are installed."
 
 .PHONY: check-go
@@ -265,11 +227,6 @@ check-golangci-lint:
 	@command -v golangci-lint >/dev/null 2>&1 || { \
 	  echo "❌ golangci-lint is not installed. Install from https://golangci-lint.run/usage/install/"; exit 1; }
 
-.PHONY: check-jq
-check-jq:
-	@command -v jq >/dev/null 2>&1 || { \
-	  echo "❌ jq is not installed. Install it from https://stedolan.github.io/jq/download/"; exit 1; }
-
 .PHONY: check-kustomize
 check-kustomize:
 	@command -v kustomize >/dev/null 2>&1 || { \
@@ -301,12 +258,6 @@ check-builder:
 		echo "✅ Using builder: $(BUILDER)"; \
 	fi
 
-.PHONY: check-podman
-check-podman:
-	@command -v podman >/dev/null 2>&1 || { \
-	  echo "⚠️  Podman is not installed. You can install it with:"; \
-	  echo "🔧 sudo apt install podman  OR  brew install podman"; exit 1; }
-
 ##@ Alias checking
 .PHONY: check-alias
 check-alias: check-container-tool
@@ -340,5 +291,10 @@ env-dev-kind: image-build
 	CLUSTER_NAME=$(KIND_CLUSTER_NAME) \
 	GATEWAY_HOST_PORT=$(KIND_GATEWAY_HOST_PORT) \
 	IMAGE_REGISTRY=$(IMAGE_REGISTRY) \
-	EPP_TAG=$(DEV_VERSION) \
+	EPP_TAG=$(EPP_TAG) \
 		./scripts/kind-dev-env.sh
+
+.PHONY: clean-env-dev-kind
+clean-env-dev-kind:
+	@echo "INFO: cleaning up kind cluster $(KIND_CLUSTER_NAME)"
+	kind delete cluster --name $(KIND_CLUSTER_NAME)

README.md

@@ -20,9 +20,9 @@ callback mechanism the EPP relies on to make routing decisions to model serving
 workloads currently.
 
 [Kubernetes]:https://kubernetes.io
-[Architecture Documentation]:/docs/architecture.md
+[Architecture Documentation]:docs/architecture.md
 [Gateway API Inference Extension (GIE)]:https://github.com/kubernetes-sigs/gateway-api-inference-extension
-[P/D Disaggregation]:/docs/dp.md
+[P/D Disaggregation]:docs/dp.md
 [Gateway API]:https://github.com/kubernetes-sigs/gateway-api
 [Envoy]:https://github.com/envoyproxy/envoy
 [ext-proc]:https://www.envoyproxy.io/docs/envoy/latest/configuration/http/http_filters/ext_proc_filter
@@ -33,7 +33,7 @@ Contributions are welcome!
 
 For large changes please [create an issue] first describing the change so the
 maintainers can do an assessment, and work on the details with you. See
-[DEVELOPMENT.md](/DEVELOPMENT.md) for details on how to work with the codebase.
+[DEVELOPMENT.md](DEVELOPMENT.md) for details on how to work with the codebase.
 
 Note that in general features should go to the upstream [Gateway API Inference
 Extension (GIE)] project _first_ if applicable. The GIE is a major dependency of

scripts/kind-dev-env.sh

@@ -26,13 +26,13 @@ SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 : "${VLLM_SIMULATOR_IMAGE:=llm-d-inference-sim}"
 
 # Set a default VLLM_SIMULATOR_TAG if not provided
-export VLLM_SIMULATOR_TAG="${VLLM_SIMULATOR_TAG:-0.0.6}"
+export VLLM_SIMULATOR_TAG="${VLLM_SIMULATOR_TAG:-v0.1.0}"
 
 # Set a default EPP_IMAGE if not provided
 : "${EPP_IMAGE:=llm-d-inference-scheduler}"
 
 # Set a default EPP_TAG if not provided
-export EPP_TAG="${EPP_TAG:-0.0.4}"
+export EPP_TAG="${EPP_TAG:-dev}"
 
 # Set the default routing side car image tag
 export ROUTING_SIDECAR_TAG="${ROUTING_SIDECAR_TAG:-0.0.6}"