agg_failover.yaml

# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# Active-passive GPU failover example.
#
# The operator clones the worker's main container into two engine containers
# (engine-0 active, engine-1 standby) sharing GPUs via DRA and the GMS sidecar.
# When the active engine fails, the standby acquires the flock and takes over.
#
# Requires:
#   - gpuMemoryService.enabled: true (GMS sidecar + DRA)
#   - nvidia.com/dynamo-kube-discovery-mode: container (per-container K8s discovery)
#   - Kubernetes 1.32+ with DRA enabled and the NVIDIA GPU DRA driver installed

apiVersion: nvidia.com/v1alpha1
kind: DynamoGraphDeployment
metadata:
  name: vllm-agg-failover
  annotations:
    nvidia.com/dynamo-kube-discovery-mode: container
spec:
  services:
    Frontend:
      envFromSecret: hf-token-secret
      componentType: frontend
      replicas: 1
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
    VllmWorker:
      envFromSecret: hf-token-secret
      componentType: worker
      replicas: 1
      resources:
        limits:
          gpu: "2"
        requests:
          custom:
            ephemeral-storage: "2Gi"
      gpuMemoryService:
        enabled: true
      failover:
        enabled: true
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
          workingDir: /workspace/examples/backends/vllm
          command:
            - python3
            - -m
            - dynamo.vllm
          args:
            - --model
            - Qwen/Qwen3-0.6B
            - --tensor-parallel-size
            - "2"
            - --load-format
            - gms