# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0

apiVersion: resource.k8s.io/v1
kind: ResourceClaimTemplate
metadata:
  name: gpu-template
spec:
  spec:
    devices:
      requests:
        - name: gpu
          exactly:
            deviceClassName: gpu.intel.com
            count: 1
---
apiVersion: nvidia.com/v1alpha1
kind: DynamoGraphDeployment
metadata:
  name: vllm-agg-xpu-dra
spec:
  services:
    Frontend:
      envFromSecret: hf-token-secret
      componentType: frontend
      replicas: 1
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
    VllmDecodeWorker:
      envFromSecret: hf-token-secret
      componentType: worker
      replicas: 1
      resources:
        requests:
          custom:
            # Increase this value for larger models
            ephemeral-storage: "2Gi"
      extraPodSpec:
        resourceClaims:
          - name: gpu
            resourceClaimTemplateName: gpu-template
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
          resources:
            claims:
              - name: gpu
          env:
            - name: VLLM_TARGET_DEVICE
              value: xpu
          workingDir: /workspace/examples/backends/vllm
          command:
            - python3
            - -m
            - dynamo.vllm
          args:
            - --model
            - Qwen/Qwen3-0.6B
            - --block-size
            - "64"