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

# Disaggregated vLLM deployment with OpenTelemetry tracing enabled.
# Base deployment: disagg.yaml
# See docs/observability/tracing.md for setup instructions.

apiVersion: nvidia.com/v1alpha1
kind: DynamoGraphDeployment
metadata:
  name: vllm-disagg-tracing
spec:
  envs:
    - name: DYN_LOGGING_JSONL
      value: "true"
    - name: OTEL_EXPORT_ENABLED
      value: "true"
    - name: OTEL_EXPORTER_OTLP_TRACES_ENDPOINT
      value: "http://tempo.observability.svc.cluster.local:4317"
  services:
    Frontend:
      componentType: frontend
      replicas: 1
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
          env:
            - name: OTEL_SERVICE_NAME
              value: "dynamo-frontend"
    VllmDecodeWorker:
      envFromSecret: hf-token-secret
      componentType: worker
      subComponentType: decode
      replicas: 1
      resources:
        limits:
          gpu: "1"
        requests:
          custom:
            # Increase this value for larger models
            ephemeral-storage: "2Gi"
      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
            - --disaggregation-mode
            - decode
          env:
            - name: OTEL_SERVICE_NAME
              value: "dynamo-worker-decode"
    VllmPrefillWorker:
      envFromSecret: hf-token-secret
      componentType: worker
      subComponentType: prefill
      replicas: 1
      resources:
        limits:
          gpu: "1"
        requests:
          custom:
            # Increase this value for larger models
            ephemeral-storage: "2Gi"
      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
            - --disaggregation-mode
            - prefill
            - --kv-transfer-config
            - '{"kv_connector":"NixlConnector","kv_role":"kv_both"}'
          env:
            - name: OTEL_SERVICE_NAME
              value: "dynamo-worker-prefill"