agg.yaml

# SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
apiVersion: nvidia.com/v1alpha1
kind: DynamoGraphDeployment
metadata:
  name: vllm-v1-agg
spec:
  services:
    Frontend:
      livenessProbe:
        httpGet:
          path: /health
          port: 8000
        initialDelaySeconds: 60
        periodSeconds: 60
        timeoutSeconds: 30
        failureThreshold: 10
      readinessProbe:
        exec:
          command:
            - /bin/sh
            - -c
            - 'curl -s http://localhost:8000/health | jq -e ".status == \"healthy\""'
        initialDelaySeconds: 60
        periodSeconds: 60
        timeoutSeconds: 30
        failureThreshold: 10
      dynamoNamespace: vllm-v1-agg
      componentType: main
      replicas: 1
      resources:
        requests:
          cpu: "1"
          memory: "2Gi"
        limits:
          cpu: "1"
          memory: "2Gi"
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidian/nim-llm-dev/vllm_v1-runtime:dep-216.4
          workingDir: /workspace/examples/vllm
          args:
            - dynamo
            - run
            - in=http
            - out=dyn
            - --http-port
            - "8000"
    VllmDecodeWorker:
      envFromSecret: hf-token-secret
      livenessProbe:
        exec:
          command:
            - /bin/sh
            - -c
            - "exit 0"
        periodSeconds: 60
        timeoutSeconds: 30
        failureThreshold: 10
      readinessProbe:
        exec:
          command:
            - /bin/sh
            - -c
            - 'grep "VllmWorker.*has been initialized" /tmp/vllm.log'
        initialDelaySeconds: 60
        periodSeconds: 60
        timeoutSeconds: 30
        failureThreshold: 10
      dynamoNamespace: vllm-v1-agg
      componentType: worker
      replicas: 1
      resources:
        requests:
          cpu: "10"
          memory: "20Gi"
          gpu: "1"
        limits:
          cpu: "10"
          memory: "20Gi"
          gpu: "1"
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidian/nim-llm-dev/vllm_v1-runtime:dep-216.4
          workingDir: /workspace/examples/vllm
          args:
            - "python3 components/main.py --model Qwen/Qwen3-0.6B --enforce-eager 2>&1 | tee /tmp/vllm.log"