Skip to content

GitLab

"vllm/vscode:/vscode.git/clone" did not exist on "a1f53addb132f75704710184f4c1cc4780343329"
Switch branch/tag
Find file Normal viewHistoryPermalink
agg_router.yaml 2.91 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 
# 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-agg-router
spec:
  services:
    Frontend:
      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: 5
      dynamoNamespace: trtllm-agg-router
      componentType: main
      replicas: 1
      resources:
        requests:
          cpu: "1"
          memory: "2Gi"
        limits:
          cpu: "1"
          memory: "2Gi"
      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 --router-mode kv"
    TRTLLMWorker:
      envFromSecret: hf-token-secret
      livenessProbe:
        httpGet:
          path: /live
          port: 9090
        periodSeconds: 5
        timeoutSeconds: 3
        failureThreshold: 3
      readinessProbe:
        httpGet:
          path: /health
          port: 9090
        periodSeconds: 10
        timeoutSeconds: 3
        failureThreshold: 60
      dynamoNamespace: trtllm-agg-router
      componentType: worker
      replicas: 2
      resources:
        requests:
          cpu: "10"
          memory: "20Gi"
          gpu: "1"
        limits:
          cpu: "10"
          memory: "20Gi"
          gpu: "1"
      envs:
        - name: DYN_SYSTEM_ENABLED
          value: "true"
        - name: DYN_SYSTEM_USE_ENDPOINT_HEALTH_STATUS
          value: "[\"generate\"]"
        - name: DYN_SYSTEM_PORT
          value: "9090"
      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
          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/agg.yaml"
            - "--publish-events-and-metrics"