deploy.yaml

# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
apiVersion: nvidia.com/v1alpha1
kind: DynamoGraphDeployment
metadata:
  name: llama3-70b-agg
spec:
  backendFramework: vllm
  pvcs:
    - name: model-cache
      create: false
  services:
    Frontend:
      componentType: frontend
      volumeMounts:
        - name: model-cache
          mountPoint: /opt/models
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.0.0
          workingDir: /workspace/examples/backends/vllm
      envs:
        - name: HF_HOME
          value: /opt/models
      replicas: 1
    VllmPrefillWorker:
      componentType: worker
      envFromSecret: hf-token-secret
      volumeMounts:
        - name: model-cache
          mountPoint: /opt/models
      sharedMemory:
        size: 20Gi
      extraPodSpec:
        mainContainer:
          env:
            - name: SERVED_MODEL_NAME
              value: "RedHatAI/Llama-3.3-70B-Instruct-FP8-dynamic"
            - name: MODEL_PATH
              value: "RedHatAI/Llama-3.3-70B-Instruct-FP8-dynamic"
            - name: HF_HOME
              value: /opt/models
          args:
          - "python3 -m dynamo.vllm --model $MODEL_PATH --served-model-name $SERVED_MODEL_NAME --tensor-parallel-size 4 --data-parallel-size 1 --gpu-memory-utilization 0.90 --no-enable-prefix-caching --block-size 128"
          command:
          - /bin/sh
          - -c
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.0.0
          workingDir: /workspace/examples/backends/vllm
      replicas: 1
      resources:
        limits:
          gpu: "4"
        requests:
          gpu: "4"