Merge branch 'dev' into makefile-fix

Signed-off-by: Shmuel Kallner <kallner@il.ibm.com>

Author: shmuelk

.tekton/README.md

@@ -2,7 +2,7 @@
 
 <!-- NOTE TO CONTRIBUTORS: every repo in the hc4ai organization is intended to have the same contents in this file. The origin is the copy in https://github.ibm.com/mspreitz/hc4ai-hello-neural/blob/dev/.tekton/README.md; submit PRs against that one -->
 
-This pipeline is designed to support safe, efficient, and traceable development and deployment workflows using [OpenShift Pipelines-as-Code](https://pipelinesascode.com/), [Tekton](https://tekton.dev/), [buildah](https://buildah.io/), GitHub, and Quay.io.
+This pipeline is designed to support safe, efficient, and traceable development and deployment workflows using [OpenShift Pipelines-as-Code](https://pipelinesascode.com/), [Tekton](https://tekton.dev/), [buildah](https://buildah.io/), GitHub, and ghcr.io.
 
 This pipeline is used for CI/CD of the `dev` and `main` branches. This pipeline runs from source through container image build to deployment and testing in the hc4ai cluster.
 
@@ -20,9 +20,9 @@ Each repo includes a `.version.json` file at its root. This file controls:
 ```json
 {
   "dev-version": "0.0.5",
-  "dev-registry": "quay.io/llm-d/<your project name>-dev",
+  "dev-registry": "ghcr.io/llm-d/<your project name>-dev",
   "prod-version": "0.0.4",
-  "prod-registry": "quay.io/llm-d/<your project name>"
+  "prod-registry": "ghcr.io/llm-d/<your project name>"
 }
 ```
 
@@ -43,8 +43,8 @@ The pipeline reads this file to:
 
 This pipeline maintains two container repositories for this GitHub repository, as follows.
 
-- `quay.io/llm-d/<repoName>-dev`. Hold builds from the `dev` branch as described below.
-- `quay.io/llm-d/<repoName>`. Holds promotions to prod, as described below.
+- `ghcr.io/llm-d/<repoName>-dev`. Hold builds from the `dev` branch as described below.
+- `ghcr.io/llm-d/<repoName>`. Holds promotions to prod, as described below.
 
 ---
 

.tekton/buildah-build.yaml

@@ -41,17 +41,17 @@ spec:
         cp /workspace/registry/.dockerconfigjson /root/.docker/config.json
 
         echo "🔐 Extracting credentials..."
-        USERNAME=$(jq -r '.auths["quay.io"].username' /root/.docker/config.json)
-        PASSWORD=$(jq -r '.auths["quay.io"].password' /root/.docker/config.json)
+        USERNAME=$(jq -r '.auths["ghcr.io"].username' /root/.docker/config.json)
+        PASSWORD=$(jq -r '.auths["ghcr.io"].password' /root/.docker/config.json)
 
         if [ "$USERNAME" = "null" ] || [ "$PASSWORD" = "null" ]; then
           echo "❌ Error: Missing registry credentials"
           exit 1
         fi
 
         echo "🔓 Logging in to registry with Buildah..."
-        buildah logout quay.io || true
-        buildah login --username "$USERNAME" --password "$PASSWORD" quay.io
+        buildah logout ghcr.io || true
+        buildah login --username "$USERNAME" --password "$PASSWORD" ghcr.io
 
         export DOCKER_CONFIG=/root/.docker
         export BUILDER=buildah

.tekton/pipelinerun.yaml

@@ -1,7 +1,7 @@
 apiVersion: tekton.dev/v1
 kind: PipelineRun
 metadata:
-  name: vllm-sim
+  name: llm-d-inference-sim
   annotations:
     pipelinesascode.tekton.dev/on-event: "[pull_request, push]"
     pipelinesascode.tekton.dev/on-target-branch: "[main, dev]"
@@ -632,7 +632,10 @@ spec:
         secretName: "{{ git_auth_secret }}"
     - name: git-auth  
       secret:
-        secretName: "git-auth-secret-neuralmagic"
+        secretName: "git-auth-secret-llm-d"
+    # - name: registry-secret
+    #   secret:
+    #     secretName: quay-secret-llm-d
     - name: registry-secret
       secret:
-        secretName: quay-secret-llm-d
+        secretName: ghcr-secret-llm-d

.tekton/vuln-scan-trivy.yaml

@@ -10,7 +10,7 @@ spec:
   params:
     - name: IMAGE_URL
       type: string
-      description: Full image URL (e.g., quay.io/org/image:tag)
+      description: Full image URL (e.g., ghcr.io/org/image:tag)
     - name: SEVERITY
       type: string
       default: "CRITICAL,HIGH,MEDIUM"

.version.json

@@ -1,6 +1,6 @@
 {
-  "dev-version": "0.0.5",
-  "dev-registry": "quay.io/llm-d/vllm-sim-dev",
-  "prod-version": "0.0.4",
-  "prod-registry": "quay.io/llm-d/vllm-sim"
+  "dev-version": "0.0.6",
+  "dev-registry": "ghcr.io/llm-d/llm-d-inference-sim-dev",
+  "prod-version": "0.0.5",
+  "prod-registry": "ghcr.io/llm-d/llm-d-inference-sim"
 }

Dockerfile

@@ -12,23 +12,23 @@ COPY go.sum go.sum
 RUN go mod download
 
 # Copy the go source
-COPY cmd/vllm-sim/main.go cmd/cmd.go
+COPY cmd/llm-d-inference-sim/main.go cmd/cmd.go
 COPY . .
 
 # Build
 # the GOARCH has not a default value to allow the binary be built according to the host where the command
 # was called. For example, if we call make image-build in a local env which has the Apple Silicon M1 SO
 # the docker BUILDPLATFORM arg will be linux/arm64 when for Apple x86 it will be linux/amd64. Therefore,
 # by leaving it empty we can ensure that the container and binary shipped on it will have the same platform.
-RUN CGO_ENABLED=0 GOOS=${TARGETOS:-linux} GOARCH=${TARGETARCH} go build -a -o bin/vllm-sim cmd/cmd.go
+RUN CGO_ENABLED=0 GOOS=${TARGETOS:-linux} GOARCH=${TARGETARCH} go build -a -o bin/llm-d-inference-sim cmd/cmd.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
 WORKDIR /
-COPY --from=builder /workspace/bin/vllm-sim /app/vllm-sim
+COPY --from=builder /workspace/bin/llm-d-inference-sim /app/llm-d-inference-sim
 USER 65532:65532
 
-ENTRYPOINT ["/app/vllm-sim"]
+ENTRYPOINT ["/app/llm-d-inference-sim"]
 
 

Makefile

@@ -1,4 +1,4 @@
-# Copyright 2025 The vLLM-Sim Authors.
+# Copyright 2025 The llm-d-inference-sim Authors.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -12,33 +12,34 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-# Makefile for the vllm-sim project
+# Makefile for the llm-d-inference-sim project
+
 CONTAINER_RUNTIME ?= docker
 
-PACKAGE_VLLM_SIM = github.com/neuralmagic/vllm-sim/cmd/vllm-sim
-VLLM_SIM_NAME = vllm-sim/vllm-sim
+PACKAGE_VLLM_SIM = github.com/llm-d/llm-d-inference-sim/cmd/llm-d-inference-sim
+VLLM_SIM_NAME = llm-d-inference-sim/llm-d-inference-sim
 VLLM_SIM_TAG ?= 0.0.2
 
-.PHONY: build-vllm-sim
-build-vllm-sim:
+.PHONY: build-llm-d-inference-sim
+build-llm-d-inference-sim:
 	go build -o bin/ ${PACKAGE_VLLM_SIM}
 
-.PHONY: build-vllm-sim-linux
-build-vllm-sim-linux:
+.PHONY: build-llm-d-inference-sim-linux
+build-llm-d-inference-sim-linux:
 	CGO_ENABLED=0 GOOS=linux GOARCH=amd64 go build -o bin/linux/ ${PACKAGE_VLLM_SIM}
 
-.PHONY: build-vllm-sim-image
-build-vllm-sim-image: build-vllm-sim-linux
-	$(CONTAINER_RUNTIME) build --file build/vllm-sim.Dockerfile --tag ${VLLM_SIM_NAME}:${VLLM_SIM_TAG} ./bin/linux
+.PHONY: build-llm-d-inference-sim-image
+build-llm-d-inference-sim-image: build-llm-d-inference-sim-linux
+	$(CONTAINER_RUNTIME) build --file build/llm-d-inference-sim.Dockerfile --tag ${VLLM_SIM_NAME}:${VLLM_SIM_TAG} ./bin/linux
 
 
 SHELL := /usr/bin/env bash
 
 # Defaults
-PROJECT_NAME ?= vllm-sim
+PROJECT_NAME ?= llm-d-inference-sim
 DEV_VERSION ?= 0.0.1
 PROD_VERSION ?= 0.0.0
-IMAGE_TAG_BASE ?= quay.io/llm-d/$(PROJECT_NAME)
+IMAGE_TAG_BASE ?= ghcr.io/llm-d/$(PROJECT_NAME)
 IMG = $(IMAGE_TAG_BASE):$(DEV_VERSION)
 NAMESPACE ?= hc4ai-operator
 
@@ -264,7 +265,7 @@ load-version-json: check-jq
 	  export DEV_VERSION; \
 	  export PROD_VERSION; \
 	fi && \
-	CURRENT_DEFAULT="quay.io/llm-d/$(PROJECT_NAME)"; \
+	CURRENT_DEFAULT="ghcr.io/llm-d/$(PROJECT_NAME)"; \
 	if [ "$(IMAGE_TAG_BASE)" = "$$CURRENT_DEFAULT" ]; then \
 	  IMAGE_TAG_BASE=$$(jq -r '."dev-registry"' .version.json); \
 	  echo "✔ Loaded IMAGE_TAG_BASE from .version.json: $$IMAGE_TAG_BASE"; \

README.md

@@ -89,13 +89,13 @@ For more details see the <a href="https://docs.vllm.ai/en/stable/getting_started
 ### Building
 To build a Docker image of the vLLM Simulator, run:
 ```bash
-make build-vllm-sim-image
+make build-llm-d-inference-sim-image
 ```
 
 ### Running
 To run the vLLM Simulator image under Docker, run:
 ```bash
-docker run --rm --publish 8000:8000 ai-aware-router/vllm-sim:0.0.1 /ai-aware-router/vllm-sim  --port 8000 --model "Qwen/Qwen2.5-1.5B-Instruct" --lora "tweet-summary-0,tweet-summary-1"
+docker run --rm --publish 8000:8000 ai-aware-router/llm-d-inference-sim:0.0.1 /ai-aware-router/llm-d-inference-sim  --port 8000 --model "Qwen/Qwen2.5-1.5B-Instruct" --lora "tweet-summary-0,tweet-summary-1"
 ```
 **Note:** The above command exposes the simulator on port 8000, and serves the Qwen/Qwen2.5-1.5B-Instruct model.
 
@@ -104,13 +104,13 @@ docker run --rm --publish 8000:8000 ai-aware-router/vllm-sim:0.0.1 /ai-aware-rou
 ### Building
 To build the vLLM simulator, run:
 ```bash
-make build-vllm-sim
+make build-llm-d-inference-sim
 ```
 
 ### Running
 To run the router in a standalone test environment, run:
 ```bash
-./bin/vllm-sim --model my_model --port 8000
+./bin/llm-d-inference-sim --model my_model --port 8000
 ```
 
 

build/vllm-sim.Dockerfile

@@ -1,4 +1,4 @@
-# Copyright 2025 The vLLM-Sim Authors.
+# Copyright 2025 The llm-d-inference-sim Authors.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -14,8 +14,8 @@
 
 FROM alpine:3.21
 
-ADD --chmod=777 ./vllm-sim /vllm-sim/
+ADD --chmod=777 ./llm-d-inference-sim /llm-d-inference-sim/
 
-WORKDIR /vllm-sim/
+WORKDIR /llm-d-inference-sim/
 
-ENTRYPOINT ["/vllm-sim/vllm-sim"]
+ENTRYPOINT ["/llm-d-inference-sim/llm-d-inference-sim"]

cmd/vllm-sim/main.go renamed to cmd/llm-d-inference-sim/main.go

@@ -1,5 +1,5 @@
 /*
-Copyright 2025 The vLLM-Sim Authors.
+Copyright 2025 The llm-d-inference-sim Authors.
 
 Licensed under the Apache License, Version 2.0 (the "License");
 you may not use this file except in compliance with the License.
@@ -23,8 +23,8 @@ import (
 
 	"k8s.io/klog/v2"
 
-	"github.com/neuralmagic/vllm-sim/cmd/signals"
-	vllmsim "github.com/neuralmagic/vllm-sim/pkg/vllm-sim"
+	"github.com/llm-d/llm-d-inference-sim/cmd/signals"
+	vllmsim "github.com/llm-d/llm-d-inference-sim/pkg/llm-d-inference-sim"
 )
 
 func main() {