Skip to content

GitLab

Switch branch/tag
Find file Normal viewHistoryPermalink
disagg.yaml 4.44 KB
Newer Older
Tanmay Verma's avatar
feat: Add trtllm deploy examples for k8s (#2133)  
Tanmay Verma committed
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
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150 
# SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0

apiVersion: nvidia.com/v1alpha1
kind: DynamoGraphDeployment
metadata:
  name: trtllm-disagg
spec:
  services:
    Frontend:
      dynamoNamespace: trtllm-disagg
      componentType: main
      livenessProbe:
        exec:
          command:
            - /bin/sh
            - -c
            - 'curl -s http://localhost:8000/health | jq -e ".status == \"healthy\""'
        periodSeconds: 5
        timeoutSeconds: 3
        failureThreshold: 3
      readinessProbe:
        exec:
          command:
            - /bin/sh
            - -c
            - 'curl -s http://localhost:8000/health | jq -e ".status == \"healthy\""'
        initialDelaySeconds: 60
        periodSeconds: 60
        timeoutSeconds: 3
        failureThreshold: 10
      replicas: 1
      resources:
        requests:
          cpu: "5"
          memory: "10Gi"
        limits:
          cpu: "5"
          memory: "10Gi"
      extraPodSpec:
        mainContainer:
          image: nvcr.io/nvidian/nim-llm-dev/trtllm-runtime:dep-233.17
          workingDir: /workspace/components/backends/trtllm
          command:
            - /bin/sh
            - -c
          args:
            - "python3 -m dynamo.frontend --http-port 8000"
    TRTLLMPrefillWorker:
      dynamoNamespace: trtllm-disagg
      envFromSecret: hf-token-secret
      componentType: worker
      replicas: 1
      livenessProbe:
        httpGet:
          path: /live
          port: 9090
        periodSeconds: 5
        timeoutSeconds: 3
        failureThreshold: 3
      readinessProbe:
        httpGet:
          path: /health
          port: 9090
        periodSeconds: 10
        timeoutSeconds: 3
        failureThreshold: 60
      resources:
        requests:
          cpu: "10"
          memory: "20Gi"
          gpu: "1"
        limits:
          cpu: "10"
          memory: "20Gi"
          gpu: "1"
      extraPodSpec:
        mainContainer:
          startupProbe:
            httpGet:
              path: /health
              port: 9090
            periodSeconds: 10
            timeoutSeconds: 3
            failureThreshold: 60
          image: nvcr.io/nvidian/nim-llm-dev/trtllm-runtime:dep-233.17
          workingDir: /workspace/components/backends/trtllm
          command:
            - /bin/sh
            - -c
          args:
            - "python3 -m dynamo.trtllm --model-path deepseek-ai/DeepSeek-R1-Distill-Llama-8B --served-model-name deepseek-ai/DeepSeek-R1-Distill-Llama-8B --extra-engine-args engine_configs/prefill.yaml --disaggregation-mode prefill --disaggregation-strategy decode_first  2>&1 | tee /tmp/trtllm.log"
      envs:
        - name: DYN_SYSTEM_ENABLED
          value: "true"
        - name: DYN_SYSTEM_USE_ENDPOINT_HEALTH_STATUS
          value: "[\"generate\"]"
        - name: DYN_SYSTEM_PORT
          value: "9090"
    TRTLLMDecodeWorker:
      dynamoNamespace: trtllm-disagg
      envFromSecret: hf-token-secret
      componentType: worker
      replicas: 1
      livenessProbe:
        httpGet:
          path: /live
          port: 9090
        periodSeconds: 5
        timeoutSeconds: 3
        failureThreshold: 3
      readinessProbe:
        httpGet:
          path: /health
          port: 9090
        periodSeconds: 10
        timeoutSeconds: 3
        failureThreshold: 60
      resources:
        requests:
          cpu: "10"
          memory: "20Gi"
          gpu: "1"
        limits:
          cpu: "10"
          memory: "20Gi"
          gpu: "1"
      extraPodSpec:
        mainContainer:
          startupProbe:
            httpGet:
              path: /health
              port: 9090
            periodSeconds: 10
            timeoutSeconds: 3
            failureThreshold: 60
          image: nvcr.io/nvidian/nim-llm-dev/trtllm-runtime:dep-233.17
          workingDir: /workspace/components/backends/trtllm
          command:
            - /bin/sh
            - -c
          args:
            - "python3 -m dynamo.trtllm --model-path deepseek-ai/DeepSeek-R1-Distill-Llama-8B --served-model-name deepseek-ai/DeepSeek-R1-Distill-Llama-8B --extra-engine-args engine_configs/decode.yaml --disaggregation-mode decode --disaggregation-strategy decode_first 2>&1 | tee /tmp/trtllm.log"
      envs:
        - name: DYN_SYSTEM_ENABLED
          value: "true"
        - name: DYN_SYSTEM_USE_ENDPOINT_HEALTH_STATUS
          value: "[\"generate\"]"
        - name: DYN_SYSTEM_PORT
          value: "9090"