dynamo/recipes/deepseek-v4/deepseek-v4-flash/vllm/agg_b200/deploy.yaml at main · nvyutwu/dynamo · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# DynamoGraphDeployment for deepseek-ai/DeepSeek-V4-Flash on vLLM,
# aggregated serving (no prefill/decode disaggregation).
#
# Upstream vLLM recipe:
#   https://github.com/vllm-project/recipes/blob/main/models/deepseek-ai/DeepSeek-V4-Flash.yaml
#
# Shape: 1 replica x 4 B200 GPUs, DP=4 + Expert Parallel, TP=1.
#        Tested on 4 of 8 GPUs per B200 node.
#
# Weights: served from the `model-cache` PVC populated by
#          `../../model-cache/model-download.yaml`.
apiVersion: nvidia.com/v1alpha1
kind: DynamoGraphDeployment
metadata:
  name: dsv4-flash-agg
spec:
  backendFramework: vllm
  pvcs:
    - name: model-cache
      create: false
  services:
    Frontend:
      componentType: frontend
      replicas: 1
      volumeMounts:
        - name: model-cache
          mountPoint: /opt/models
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.2.0-deepseek-v4-cuda13-dev.3
          workingDir: /workspace/examples/backends/vllm
          env:
            - name: HF_HOME
              value: /opt/models
            - name: HF_HUB_OFFLINE
              value: "1"
    VllmDecodeWorker:
      componentType: worker
      subComponentType: decode
      envFromSecret: hf-token-secret
      volumeMounts:
        - name: model-cache
          mountPoint: /opt/models
      sharedMemory:
        size: 200Gi
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:1.2.0-deepseek-v4-cuda13-dev.3
          workingDir: /workspace/examples/backends/vllm
          # Up to ~60 min for first launch: weight load + FlashInfer autotune +
          # cudagraph warmup. periodSeconds * failureThreshold = 10 * 360 = 3600s.
          startupProbe:
            httpGet:
              path: /health
              port: 9090
            periodSeconds: 10
            timeoutSeconds: 10
            failureThreshold: 360
          env:
            - name: SERVED_MODEL_NAME
              value: deepseek-ai/DeepSeek-V4-Flash
            - name: MODEL_PATH
              value: deepseek-ai/DeepSeek-V4-Flash
            - name: HF_HOME
              value: /opt/models
            # Read weights from the PVC only; do not hit the HF Hub at startup.
            - name: HF_HUB_OFFLINE
              value: "1"
            # Give the engine room to finish first-launch init.
            - name: VLLM_ENGINE_READY_TIMEOUT_S
              value: "3600"
            # Stabilize DP dummy inputs (matches the DeepSeek-R1 vLLM recipe).
            - name: VLLM_RANDOMIZE_DP_DUMMY_INPUTS
              value: "1"
            - name: VLLM_SKIP_P2P_CHECK
              value: "1"
            - name: NCCL_CUMEM_ENABLE
              value: "1"
          command:
            - /bin/sh
            - -c
          args:
            - |
              python3 -m dynamo.vllm \
                --model "${MODEL_PATH}" \
                --served-model-name "${SERVED_MODEL_NAME}" \
                --trust-remote-code \
                --kv-cache-dtype fp8 \
                --block-size 256 \
                --tensor-parallel-size 1 \
                --data-parallel-size 4 \
                --enable-expert-parallel \
                --tokenizer-mode deepseek_v4 \
                --dyn-reasoning-parser deepseek_v4 \
                --dyn-tool-call-parser deepseek_v4 \
                --attention-config '{"use_fp4_indexer_cache":true}' \
                --compilation-config '{"cudagraph_mode":"FULL_AND_PIECEWISE","custom_ops":["all"]}' \
                --no-enable-flashinfer-autotune \
                --max-num-seqs 256
      replicas: 1
      resources:
        limits:
          gpu: "4"
        requests:
          gpu: "4"