# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
apiVersion: v1
kind: ConfigMap
metadata:
  name: llm-config
data:
  config.yaml: |
    backend: pytorch
    tensor_parallel_size: 2
    pipeline_parallel_size: 1
    enable_attention_dp: false
    enable_chunked_prefill: false
    max_batch_size: 96
    max_num_tokens: 7964
    max_seq_len: 7964
    kv_cache_config:
      enable_block_reuse: false
      free_gpu_memory_fraction: 0.7
      dtype: fp8
    cuda_graph_config:
      enable_padding: true
      batch_sizes:
        - 1
        - 2
        - 4
        - 8
        - 16
        - 32
        - 64
        - 96
    disable_overlap_scheduler: false
    print_iter_log: false
---
apiVersion: nvidia.com/v1alpha1
kind: DynamoGraphDeployment
metadata:
  name: qwen3-32b-fp8-agg
spec:
  backendFramework: trtllm
  pvcs:
    - name: model-cache
      create: false
  services:
    Frontend:
      componentType: frontend
      extraPodSpec:
        affinity:
          podAntiAffinity:
            requiredDuringSchedulingIgnoredDuringExecution:
            - labelSelector:
                matchExpressions:
                - key: nvidia.com/dynamo-graph-deployment-name
                  operator: In
                  values:
                  - qwen3-32b-fp8-agg-frontend
              topologyKey: kubernetes.io/hostname
        mainContainer:
          args:
          - python3 -m dynamo.frontend --router-mode round-robin --http-port 8000
          command:
          - /bin/sh
          - -c
          image: nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:1.0.0
      replicas: 1
    TrtllmWorker:
      componentType: worker
      envFromSecret: hf-token-secret
      volumeMounts:
        - name: model-cache
          mountPoint: /opt/models
      sharedMemory:
        size: 80Gi
      extraPodSpec:
        affinity:
          nodeAffinity:
            requiredDuringSchedulingIgnoredDuringExecution:
              nodeSelectorTerms:
              - matchExpressions:
                - key: nvidia.com/gpu.present
                  operator: In
                  values:
                  - "true"
        mainContainer:
          args:
          - |
            python3 -m dynamo.trtllm \
              --model-path "${MODEL_PATH}" \
              --served-model-name "${MODEL_PATH}" \
              --extra-engine-args "${ENGINE_ARGS}" \
              --tensor-parallel-size 2 \
              --max-batch-size 96 \
              --free-gpu-memory-fraction 0.9
          command:
          - /bin/sh
          - -c
          image: nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:1.0.0
          env:
          - name: TRTLLM_ENABLE_PDL
            value: "1"
          - name: TRT_LLM_DISABLE_LOAD_WEIGHTS_IN_PARALLEL
            value: "True"
          - name: ENGINE_ARGS
            value: "/opt/dynamo/configs/config.yaml"
          - name: MODEL_PATH
            value: "Qwen/Qwen3-32B-FP8"
          - name: HF_HOME
            value: "/opt/models"
          volumeMounts:
          - mountPath: /opt/dynamo/configs
            name: llm-config
            readOnly: true
          workingDir: /workspace/examples/backends/trtllm
        volumes:
        - configMap:
            name: llm-config
          name: llm-config
      replicas: 1
      resources:
        limits:
          gpu: "2"
        requests:
          gpu: "2"