Created
December 8, 2025 21:29
-
-
Save sozercan/42f427f5f9d216ed6a01c953532c8fb7 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| apiVersion: ray.io/v1 | |
| kind: RayService | |
| metadata: | |
| name: qwen | |
| spec: | |
| serveConfigV2: | | |
| applications: | |
| - name: llm_app | |
| import_path: ray.serve.llm:build_openai_app | |
| route_prefix: "/" | |
| # Runtime env for the Serve app | |
| runtime_env: | |
| env_vars: | |
| VLLM_USE_V1: "1" | |
| # Args passed to build_openai_app | |
| args: | |
| llm_configs: | |
| - model_loading_config: | |
| model_id: "qwen" | |
| model_source: "Qwen/Qwen3-0.6B" | |
| accelerator_type: "A100" | |
| deployment_config: | |
| autoscaling_config: | |
| min_replicas: 1 | |
| max_replicas: 2 | |
| engine_kwargs: | |
| # 0.6B is tiny; single GPU is enough | |
| tensor_parallel_size: 1 | |
| pipeline_parallel_size: 1 | |
| gpu_memory_utilization: 0.9 | |
| dtype: "auto" | |
| max_num_seqs: 40 | |
| max_model_len: 16384 | |
| enable_chunked_prefill: true | |
| enable_prefix_caching: true | |
| rayClusterConfig: | |
| headGroupSpec: | |
| rayStartParams: | |
| num-gpus: "0" | |
| template: | |
| spec: | |
| containers: | |
| - name: ray-head | |
| image: rayproject/ray-llm:2.52.0-py311-cu128 | |
| resources: | |
| limits: | |
| cpu: "4" | |
| memory: "32Gi" | |
| requests: | |
| cpu: "4" | |
| memory: "32Gi" | |
| ports: | |
| - containerPort: 6379 | |
| name: gcs-server | |
| - containerPort: 8265 | |
| name: dashboard | |
| - containerPort: 10001 | |
| name: client | |
| - containerPort: 8000 | |
| name: serve | |
| workerGroupSpecs: | |
| - groupName: gpu-group | |
| replicas: 2 | |
| minReplicas: 2 | |
| maxReplicas: 2 | |
| rayStartParams: {} | |
| template: | |
| spec: | |
| containers: | |
| - name: ray-worker | |
| image: rayproject/ray-llm:2.52.0-py311-cu128 | |
| resources: | |
| # Adjust these to match your node flavor | |
| limits: | |
| cpu: "8" | |
| memory: "64Gi" | |
| nvidia.com/gpu: "1" | |
| requests: | |
| cpu: "8" | |
| memory: "64Gi" | |
| nvidia.com/gpu: "1" | |
| tolerations: | |
| - key: "nvidia.com/gpu" | |
| operator: "Exists" | |
| effect: "NoSchedule" |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment