| 1 | # KubeRay |
| 2 | |
| 3 | [KubeRay](https://github.com/ray-project/kuberay) provides a Kubernetes-native way to run vLLM workloads on Ray clusters. |
| 4 | A Ray cluster can be declared in YAML, and the operator then handles pod scheduling, networking configuration, restarts, and blue-green deployments — all while preserving the familiar Kubernetes experience. |
| 5 | |
| 6 | ## Why KubeRay instead of manual scripts? |
| 7 | |
| 8 | | Feature | Manual scripts | KubeRay | |
| 9 | | ------- | --------------------------------------------------------- | ------- | |
| 10 | | Cluster bootstrap | Manually SSH into every node and run a script | One command to create or update the whole cluster: `kubectl apply -f cluster.yaml` | |
| 11 | | Autoscaling | Manual | Automatically patches CRDs for adjusting cluster size | |
| 12 | | Upgrades | Tear down & re-create manually | Blue/green deployment updates supported | |
| 13 | | Declarative config | Bash flags & environment variables | Git-ops-friendly YAML CRDs (RayCluster/RayService) | |
| 14 | |
| 15 | Using KubeRay reduces the operational burden and simplifies integration of Ray + vLLM with existing Kubernetes workflows (CI/CD, secrets, storage classes, etc.). |
| 16 | |
| 17 | ## Learn more |
| 18 | |
| 19 | * ["Serve a Large Language Model using Ray Serve LLM on Kubernetes"](https://docs.ray.io/en/master/cluster/kubernetes/examples/rayserve-llm-example.html) - An end-to-end example of how to serve a model using vLLM, KubeRay, and Ray Serve. |
| 20 | * [KubeRay documentation](https://docs.ray.io/en/latest/cluster/kubernetes/index.html) |