squash commits

Signed-off-by: Varun Gupta <[email protected]>

.github/workflows/docker-push-images.yml

@@ -21,12 +21,12 @@ jobs:
         with:
           username: ${{ secrets.DOCKER_HUB_USERNAME }}
           password: ${{ secrets.DOCKER_HUB_ACCESS_TOKEN }}
-      - name: Login to the Container registry
-        uses: docker/login-action@65b78e6e13532edd9afa3aa52ac7964289d1a9c1
-        with:
-          registry: ghcr.io
-          username: ${{ github.actor }}
-          password: ${{ secrets.GITHUB_TOKEN }}
+#      - name: Login to the Container registry
+#        uses: docker/login-action@65b78e6e13532edd9afa3aa52ac7964289d1a9c1
+#        with:
+#          registry: ghcr.io
+#          username: ${{ github.actor }}
+#          password: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Build Container Images
         run: |
@@ -36,10 +36,11 @@ jobs:
         run: |
           make docker-push-all
 
-      - name: Build Container Images with Github Container Registry prefix
-        run: |
-          GIT_COMMIT_HASH=${{ github.sha }} AIBRIX_CONTAINER_REGISTRY_NAMESPACE=ghcr.io/aibrix make docker-build-all
-
-      - name: Push Container Images to Github Container Registry
-        run: |
-          GIT_COMMIT_HASH=${{ github.sha }} AIBRIX_CONTAINER_REGISTRY_NAMESPACE=ghcr.io/aibrix make docker-push-all
+# TODO: Disable GHCR at this moment after org transfer, let's enable it later.
+#      - name: Build Container Images with Github Container Registry prefix
+#        run: |
+#          GIT_COMMIT_HASH=${{ github.sha }} AIBRIX_CONTAINER_REGISTRY_NAMESPACE=ghcr.io/aibrix make docker-build-all
+#
+#      - name: Push Container Images to Github Container Registry
+#        run: |
+#          GIT_COMMIT_HASH=${{ github.sha }} AIBRIX_CONTAINER_REGISTRY_NAMESPACE=ghcr.io/aibrix make docker-push-all

.github/workflows/installation-tests.yml

@@ -99,7 +99,7 @@ jobs:
       - name: Set up testing environment
         run: |
           # Set up the cluster with kind or other Kubernetes environment needed
-          kind create cluster --name installation-test --config=./hack/kind_config.yaml
+          kind create cluster --name installation-test --config=./hack/ci/kind-config.yaml
           kubectl cluster-info --context kind-installation-test
 
       - name: Load image into Kind

.github/workflows/release-build.yaml

@@ -30,12 +30,12 @@ jobs:
           password: ${{ secrets.DOCKER_HUB_ACCESS_TOKEN }}
 
       # Log in to Github Registry
-      - name: Login to the Container registry
-        uses: docker/login-action@65b78e6e13532edd9afa3aa52ac7964289d1a9c1
-        with:
-          registry: ghcr.io
-          username: ${{ github.actor }}
-          password: ${{ secrets.GITHUB_TOKEN }}
+#      - name: Login to the Container registry
+#        uses: docker/login-action@65b78e6e13532edd9afa3aa52ac7964289d1a9c1
+#        with:
+#          registry: ghcr.io
+#          username: ${{ github.actor }}
+#          password: ${{ secrets.GITHUB_TOKEN }}
 
       # Build container images with docker registry namespace
       - name: Build Container Images
@@ -48,14 +48,14 @@ jobs:
           IS_MAIN_BRANCH=false GIT_COMMIT_HASH=${{ github.ref_name }} make docker-push-all
 
       # Build container images with Github registry namespace
-      - name: Build Container Images with Github Container Registry prefix
-        run: |
-          IS_MAIN_BRANCH=false GIT_COMMIT_HASH=${{ github.ref_name }} AIBRIX_CONTAINER_REGISTRY_NAMESPACE=ghcr.io/aibrix make docker-build-all
+#      - name: Build Container Images with Github Container Registry prefix
+#        run: |
+#          IS_MAIN_BRANCH=false GIT_COMMIT_HASH=${{ github.ref_name }} AIBRIX_CONTAINER_REGISTRY_NAMESPACE=ghcr.io/aibrix make docker-build-all
 
       # Push container image to Github container registry
-      - name: Push Container Images to Github Container Registry
-        run: |
-          IS_MAIN_BRANCH=false GIT_COMMIT_HASH=${{ github.ref_name }} AIBRIX_CONTAINER_REGISTRY_NAMESPACE=ghcr.io/aibrix make docker-push-all
+#      - name: Push Container Images to Github Container Registry
+#        run: |
+#          IS_MAIN_BRANCH=false GIT_COMMIT_HASH=${{ github.ref_name }} AIBRIX_CONTAINER_REGISTRY_NAMESPACE=ghcr.io/aibrix make docker-push-all
 
   python-wheel-release:
     runs-on: ubuntu-latest

CONTRIBUTING.md

@@ -12,25 +12,25 @@ please see the [Development Guide](development/README.md) in the `docs/developme
 
 ### 1. Understanding the Repository Structure
 
-You can refer to the [Design Doc](https://github.com/aibrix/aibrix/tree/main/docs/tutorial) to quickly understand the layout of the AIBrix directory structure.
+You can refer to the [Design Doc](https://github.com/vllm-project/aibrix/tree/main/docs/tutorial) to quickly understand the layout of the AIBrix directory structure.
 
 ### 2. Picking an Issue
 
-Start by picking an [issue](https://github.com/aibrix/aibrix/issues) tagged with "good first issue" to get familiar with the project. Claim the issue by commenting to avoid duplicate efforts.
+Start by picking an [issue](https://github.com/vllm-project/aibrix/issues) tagged with "good first issue" to get familiar with the project. Claim the issue by commenting to avoid duplicate efforts.
 
 ### 3. Submitting Codes
 
 - **Creating Branches**: Use the following naming convention: `/<YOUR_NAME>/[feat|patch|bug_fix] description`
 - **Making Commits**: Write detailed commit messages that explain your changes.
 - **Pull Requests**:
-  - Create a pull request on [PR Page](https://github.com/aibrix/aibrix/pulls) against the master branch.
+  - Create a pull request on [PR Page](https://github.com/vllm-project/aibrix/pulls) against the master branch.
   - Use the provided PR template to describe your changes.
 - **Code Review Process**: Your PR will be reviewed by related contributors. Address feedback to improve and finalize your contribution.
 
 ## Advanced Contributions
 
 - **Feature Proposals and Bug Reporting**: Report bugs or propose new features by creating an issue on our GitHub page. Provide as much detail as possible to facilitate discussions.
-- **Contributing to Documentation**: Help improve our documentation by proposing changes to issue list. Our documentation is at [AIBrix Doc](https://github.com/aibrix/aibrix/tree/main/docs/tutorial)
+- **Contributing to Documentation**: Help improve our documentation by proposing changes to issue list. Our documentation is at [AIBrix Doc](https://github.com/vllm-project/aibrix/tree/main/docs/tutorial)
 - **Organizing Community Events**: If you are interested in organizing meetups or webinars, contact our community manager (TODO: contact information).
 
 ## Community and Communication

Makefile

@@ -59,7 +59,8 @@ manifests: controller-gen ## Generate WebhookConfiguration, ClusterRole and Cust
 .PHONY: generate
 generate: controller-gen ## Generate code containing DeepCopy, DeepCopyInto, and DeepCopyObject method implementations.
 	$(CONTROLLER_GEN) object:headerFile="hack/boilerplate.go.txt" paths="./..."
-
+	./hack/update-codegen.sh go $(PROJECT_DIR)/bin
+
 .PHONY: update-codegen
 update-codegen:
 	sh ./hack/update-codegen.sh
@@ -137,7 +138,7 @@ define push_image
 endef
 
 .PHONY: docker-build-all
-docker-build-all: 
+docker-build-all:
 	make -j $(nproc) docker-build-controller-manager docker-build-gateway-plugins docker-build-runtime docker-build-metadata-service ## Build all docker images
 
 .PHONY: docker-build-controller-manager
@@ -157,7 +158,7 @@ docker-build-metadata-service: ## Build docker image with the metadata-service.
 	$(call build_and_tag,metadata-service,Dockerfile.metadata)
 
 .PHONY: docker-push-all
-docker-push-all: 
+docker-push-all:
 	make -j $(nproc) docker-push-controller-manager docker-push-gateway-plugins docker-push-runtime docker-push-metadata-service ## Push all docker images
 
 .PHONY: docker-push-controller-manager
@@ -212,9 +213,9 @@ endif
 .PHONY: install
 install: manifests kustomize ## Install CRDs into the K8s cluster specified in ~/.kube/config.
 	$(KUSTOMIZE) build config/crd | $(KUBECTL) apply -f -
-    ## helm creates objects without aibrix prefix, hence deploying gateway components outside of kustomization	
+    ## helm creates objects without aibrix prefix, hence deploying gateway components outside of kustomization
 	$(KUBECTL) create -k config/dependency
-	
+
 .PHONY: uninstall
 uninstall: manifests kustomize ## Uninstall CRDs from the K8s cluster specified in ~/.kube/config. Call with ignore-not-found=true to ignore resource not found errors during deletion.
 	$(KUBECTL) delete --ignore-not-found=$(ignore-not-found) -k config/dependency
@@ -231,9 +232,9 @@ undeploy: kustomize ## Undeploy controller from the K8s cluster specified in ~/.
 .PHONY: install-vke
 install-vke: manifests kustomize ## Install CRDs into the K8s cluster specified in ~/.kube/config.
 	$(KUSTOMIZE) build config/crd | $(KUBECTL) apply -f -
-    ## helm creates objects without aibrix prefix, hence deploying gateway components outside of kustomization	
+    ## helm creates objects without aibrix prefix, hence deploying gateway components outside of kustomization
 	$(KUBECTL) create -k config/overlays/vke/dependency
-	
+
 .PHONY: uninstall-vke
 uninstall-vke: manifests kustomize ## Uninstall CRDs from the K8s cluster specified in ~/.kube/config. Call with ignore-not-found=true to ignore resource not found errors during deletion.
 	$(KUBECTL) delete --ignore-not-found=$(ignore-not-found) -k config/overlays/vke/dependency

PROJECT

@@ -7,7 +7,7 @@ layout:
 - go.kubebuilder.io/v4
 multigroup: true
 projectName: aibrix
-repo: github.com/aibrix/aibrix
+repo: github.com/vllm-project/aibrix
 resources:
 - api:
     crdVersion: v1
@@ -16,7 +16,7 @@ resources:
   domain: aibrix.ai
   group: autoscaling
   kind: PodAutoscaler
-  path: github.com/aibrix/aibrix/api/autoscaling/v1alpha1
+  path: github.com/vllm-project/aibrix/api/autoscaling/v1alpha1
   version: v1alpha1
 - api:
     crdVersion: v1
@@ -25,7 +25,7 @@ resources:
   domain: aibrix.ai
   group: model
   kind: ModelAdapter
-  path: github.com/aibrix/aibrix/api/model/v1alpha1
+  path: github.com/vllm-project/aibrix/api/model/v1alpha1
   version: v1alpha1
 - api:
     crdVersion: v1
@@ -34,7 +34,7 @@ resources:
   domain: aibrix.ai
   group: orchestration
   kind: RayClusterReplicaSet
-  path: github.com/aibrix/aibrix/api/orchestration/v1alpha1
+  path: github.com/vllm-project/aibrix/api/orchestration/v1alpha1
   version: v1alpha1
 - api:
     crdVersion: v1
@@ -43,7 +43,7 @@ resources:
   domain: aibrix.ai
   group: orchestration
   kind: RayClusterFleet
-  path: github.com/aibrix/aibrix/api/orchestration/v1alpha1
+  path: github.com/vllm-project/aibrix/api/orchestration/v1alpha1
   version: v1alpha1
 - api:
     crdVersion: v1
@@ -52,6 +52,6 @@ resources:
   domain: aibrix.ai
   group: orchestration
   kind: KVCache
-  path: github.com/aibrix/aibrix/api/orchestration/v1alpha1
+  path: github.com/vllm-project/aibrix/api/orchestration/v1alpha1
   version: v1alpha1
 version: "3"

README.md

@@ -11,8 +11,13 @@ The initial release includes the following key features:
 - **Distributed Inference**: Scalable architecture to handle large workloads across multiple nodes.
 - **LLM App-Tailored Autoscaler**: Dynamically scale inference resources based on real-time demand.
 - **Unified AI Runtime**: A versatile sidecar enabling metric standardization, model downloading, and management.
+- **Distributed KV Cache**: Enables high-capacity, cross-engine KV reuse.
+- **Cost-efficient Heterogeneous Serving**: Enables mixed GPU inference to reduce costs with SLO guarantees.
 - **GPU Hardware Failure Detection (TBD)**: Proactive detection of GPU hardware issues.
-- **Benchmark Tool (TBD)**: A tool for measuring inference performance and resource efficiency.
+
+## Architecture
+
+![aibrix-architecture-v1](docs/source/assets/images/aibrix-architecture-v1.jpeg)
 
 
 ## Quick Start
@@ -21,7 +26,7 @@ To get started with AIBrix, clone this repository and follow the setup instructi
 
 ```shell
 # Local Testing
-git clone https://github.com/aibrix/aibrix.git
+git clone https://github.com/vllm-project/aibrix.git
 cd aibrix
 
 # Install nightly aibrix dependencies
@@ -34,26 +39,28 @@ kubectl create -k config/default
 Install stable distribution
 ```shell
 # Install component dependencies
-kubectl create -k "github.com/aibrix/aibrix/config/dependency?ref=v0.2.0-rc.2"
+kubectl create -k "github.com/vllm-project/aibrix/config/dependency?ref=v0.2.0"
 
 # Install aibrix components
-kubectl create -k "github.com/aibrix/aibrix/config/overlays/release?ref=v0.2.0-rc.2"
+kubectl create -k "github.com/vllm-project/aibrix/config/overlays/release?ref=v0.2.0"
 ```
 
 ## Documentation
 
-For detailed documentation on installation, configuration, and usage, please visit our [documentation page](https://github.com/aibrix/aibrix).
+For detailed documentation on installation, configuration, and usage, please visit our [documentation page](https://aibrix.readthedocs.io/latest/).
 
 ## Contributing
 
-We welcome contributions from the community! Check out our [contributing guidelines](https://github.com/aibrix/aibrix/CONTRIBUTING.md) to see how you can make a difference.
+We welcome contributions from the community! Check out our [contributing guidelines](https://github.com/vllm-project/aibrix/CONTRIBUTING.md) to see how you can make a difference.
+
+Slack Channel: https://vllm-dev.slack.com/archives/C07QP347J4D
 
 ## License
 
-AIBrix is licensed under the [APACHE License](https://github.com/aibrix/aibrix/LICENSE.md).
+AIBrix is licensed under the [APACHE License](https://github.com/vllm-project/aibrix/LICENSE.md).
 
 ## Support
 
-If you have any questions or encounter any issues, please submit an issue on our [GitHub issues page](https://github.com/aibrix/aibrix/issues).
+If you have any questions or encounter any issues, please submit an issue on our [GitHub issues page](https://github.com/vllm-project/aibrix/issues).
 
 Thank you for choosing AIBrix for your GenAI infrastructure needs!

api/autoscaling/v1alpha1/podautoscaler_types.go

@@ -23,7 +23,6 @@ import (
 	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
 )
 
-// EDIT THIS FILE!  THIS IS SCAFFOLDING FOR YOU TO OWN!
 // NOTE: json tags are required.  Any new fields you add must have json tags for the fields to be serialized.
 // INSERT ADDITIONAL SPEC FIELDS - desired state of cluster
 // Important: Run "make" to regenerate code after modifying this file
@@ -57,16 +56,19 @@ type PodAutoscalerSpec struct {
 	//PodSelector *metav1.LabelSelector `json:"podSelector,omitempty"`
 
 	// MinReplicas is the minimum number of replicas to which the target can be scaled down.
+	// +optional
 	MinReplicas *int32 `json:"minReplicas,omitempty"`
 
 	// MaxReplicas is the maximum number of replicas to which the target can be scaled up.
 	// It cannot be less than minReplicas
 	MaxReplicas int32 `json:"maxReplicas"`
 
 	// MetricsSources defines a list of sources from which metrics are collected to make scaling decisions.
+	// +kubebuilder:validation:MinItems=1
 	MetricsSources []MetricSource `json:"metricsSources,omitempty"`
 
 	// ScalingStrategy defines the strategy to use for scaling.
+	// +kubebuilder:validation:Enum={HPA,KPA,APA}
 	ScalingStrategy ScalingStrategyType `json:"scalingStrategy"`
 }
 
@@ -103,8 +105,10 @@ const (
 // MetricSource defines an endpoint and path from which metrics are collected.
 type MetricSource struct {
 	// access an endpoint or scan a list of k8s pod
+	// +kubebuilder:validation:Enum={pod,domain}
 	MetricSourceType MetricSourceType `json:"metricSourceType"`
 	// http or https
+	// +kubebuilder:validation:Enum={http,https}
 	ProtocolType ProtocolType `json:"protocolType"`
 	// e.g. service1.example.com. meaningless for MetricSourceType.POD
 	Endpoint string `json:"endpoint,omitempty"`

api/model/v1alpha1/modeladapter_types.go

@@ -21,15 +21,14 @@ import (
 	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
 )
 
-// EDIT THIS FILE!  THIS IS SCAFFOLDING FOR YOU TO OWN!
 // NOTE: json tags are required.  Any new fields you add must have json tags for the fields to be serialized.
 
 // ModelAdapterSpec defines the desired state of ModelAdapter
 type ModelAdapterSpec struct {
 
 	// BaseModel is the identifier for the base model to which the ModelAdapter will be attached.
 	// +optional
-	BaseModel string `json:"baseModel,omitempty"`
+	BaseModel *string `json:"baseModel,omitempty"`
 
 	// PodSelector is a label query over pods that should match the ModelAdapter configuration.
 	// +kubebuilder:validation:Required

api/orchestration/v1alpha1/kvcache_types.go

@@ -35,7 +35,7 @@ type ServiceConfig struct {
 
 	// NodePort specifies the port on each node on which this service is exposed when using NodePort type.
 	// +kubebuilder:validation:Optional
-	NodePort int32 `json:"nodePort,omitempty"`
+	NodePort *int32 `json:"nodePort,omitempty"`
 }
 
 // MetadataConfig holds the configuration about the kv cache metadata service
@@ -95,7 +95,7 @@ type CacheSpec struct {
 
 	// the memory resources of kvcache container
 	// +kubebuilder:validation:Optional
-	// +kubebuilder:default:="2"
+	// +kubebuilder:default:="2Gi"
 	Memory string `json:"memory,omitempty"`
 
 	// the cpu resources of kvcache container

api/orchestration/v1alpha1/rayclusterfleet_types.go

@@ -22,13 +22,13 @@ import (
 	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
 )
 
-// EDIT THIS FILE!  THIS IS SCAFFOLDING FOR YOU TO OWN!
 // NOTE: json tags are required.  Any new fields you add must have json tags for the fields to be serialized.
 
 // RayClusterFleetSpec defines the desired state of RayClusterFleet
 type RayClusterFleetSpec struct {
 	// Number of desired pods. This is a pointer to distinguish between explicit
 	// zero and not specified. Defaults to 1.
+	// +kubebuilder:default=1
 	// +optional
 	Replicas *int32 `json:"replicas,omitempty" protobuf:"varint,1,opt,name=replicas"`
 
@@ -55,6 +55,7 @@ type RayClusterFleetSpec struct {
 	// The number of old ReplicaSets to retain to allow rollback.
 	// This is a pointer to distinguish between explicit zero and not specified.
 	// Defaults to 10.
+	// +kubebuilder:default=10
 	// +optional
 	RevisionHistoryLimit *int32 `json:"revisionHistoryLimit,omitempty" protobuf:"varint,6,opt,name=revisionHistoryLimit"`
 
@@ -67,6 +68,8 @@ type RayClusterFleetSpec struct {
 	// process failed deployments and a condition with a ProgressDeadlineExceeded
 	// reason will be surfaced in the deployment status. Note that progress will
 	// not be estimated during the time a deployment is paused. Defaults to 600s.
+	// +kubebuilder:default=600
+	// +optional
 	ProgressDeadlineSeconds *int32 `json:"progressDeadlineSeconds,omitempty" protobuf:"varint,9,opt,name=progressDeadlineSeconds"`
 }