agg_gms.yaml

# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# GPU Memory Service (GMS) sidecar example.
#
# The operator injects a GMS sidecar init container that provides shared GPU
# memory access via DRA (Dynamic Resource Allocation). The sidecar runs two GMS
# processes per GPU (weights + kv_cache) and communicates with the main container
# over UDS sockets on a shared emptyDir volume.
#
# Requires Kubernetes 1.32+ with DRA enabled and the NVIDIA GPU DRA driver installed.

apiVersion: nvidia.com/v1alpha1
kind: DynamoGraphDeployment
metadata:
  name: vllm-agg-gms
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: "1"
        requests:
          custom:
            ephemeral-storage: "2Gi"
      gpuMemoryService:
        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
            - --load-format
            - gms