model-runner/.github/workflows/release.yml at a469544e7603a7d7c1093e3f27b368b12a38accc · docker/model-runner · 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
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
name: Release model-runner images for CE
run-name: Release model-runner images for CE, version ${{ inputs.releaseTag }}

on:
  workflow_dispatch:
    inputs:
      pushLatest:
        description: 'Tag images produced by this job as latest'
        required: false
        type: boolean
        default: false
      releaseTag:
        description: 'Release tag'
        required: false
        type: string
        default: "test"
      llamaServerVersion:
        description: 'llama-server version'
        required: false
        type: string
        default: "latest"
      vllmVersion:
        description: 'vLLM version'
        required: false
        type: string
        default: "0.11.0"

jobs:
  test:
    runs-on: ubuntu-latest
    steps:
      - name: Checkout code
        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955

      - name: Set up Go
        uses: actions/setup-go@d35c59abb061a4a6fb18e82ac0862c26744d6ab5
        with:
          go-version: 1.24.2
          cache: true

      - name: Run tests
        run: go test ./...

  build:
    needs: test
    runs-on: ubuntu-latest
    steps:
      - name: Checkout repo
        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955

      - name: Format tags
        id: tags
        shell: bash
        run: |
          echo "cpu<<EOF" >> "$GITHUB_OUTPUT"
          echo "docker/model-runner:${{ inputs.releaseTag }}" >> "$GITHUB_OUTPUT"
          if [ "${{ inputs.pushLatest }}" == "true" ]; then
            echo "docker/model-runner:latest" >> "$GITHUB_OUTPUT"
          fi
          echo 'EOF' >> "$GITHUB_OUTPUT"
          echo "cuda<<EOF" >> "$GITHUB_OUTPUT"
          echo "docker/model-runner:${{ inputs.releaseTag }}-cuda" >> "$GITHUB_OUTPUT"
          if [ "${{ inputs.pushLatest }}" == "true" ]; then
            echo "docker/model-runner:latest-cuda" >> "$GITHUB_OUTPUT"
          fi
          echo 'EOF' >> "$GITHUB_OUTPUT"
          echo "vllm-cuda<<EOF" >> "$GITHUB_OUTPUT"
          echo "docker/model-runner:${{ inputs.releaseTag }}-vllm-cuda" >> "$GITHUB_OUTPUT"
          if [ "${{ inputs.pushLatest }}" == "true" ]; then
            echo "docker/model-runner:latest-vllm-cuda" >> "$GITHUB_OUTPUT"
          fi
          echo 'EOF' >> "$GITHUB_OUTPUT"
          echo "rocm<<EOF" >> "$GITHUB_OUTPUT"
          echo "docker/model-runner:${{ inputs.releaseTag }}-rocm" >> "$GITHUB_OUTPUT"
          if [ "${{ inputs.pushLatest }}" == "true" ]; then
            echo "docker/model-runner:latest-rocm" >> "$GITHUB_OUTPUT"
          fi
          echo 'EOF' >> "$GITHUB_OUTPUT"

      - name: Log in to DockerHub
        uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef
        with:
          username: "docker"
          password: ${{ secrets.ORG_ACCESS_TOKEN }}

      - name: Set up Buildx
        uses: docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435
        with:
          version: "lab:latest"
          driver: cloud
          endpoint: "docker/make-product-smarter"
          install: true

      - name: Build CPU image
        uses: docker/build-push-action@ca052bb54ab0790a636c9b5f226502c73d547a25
        with:
          file: Dockerfile
          target: final-llamacpp
          platforms: linux/amd64, linux/arm64
          build-args: |
            "LLAMA_SERVER_VERSION=${{ inputs.llamaServerVersion }}"
          push: true
          sbom: true
          provenance: mode=max
          tags: ${{ steps.tags.outputs.cpu }}

      - name: Build CUDA image
        uses: docker/build-push-action@ca052bb54ab0790a636c9b5f226502c73d547a25
        with:
          file: Dockerfile
          target: final-llamacpp
          platforms: linux/amd64, linux/arm64
          build-args: |
            "LLAMA_SERVER_VERSION=${{ inputs.llamaServerVersion }}"
            "LLAMA_SERVER_VARIANT=cuda"
            "BASE_IMAGE=nvidia/cuda:12.9.0-runtime-ubuntu24.04"
          push: true
          sbom: true
          provenance: mode=max
          tags: ${{ steps.tags.outputs.cuda }}

      - name: Build vLLM CUDA image
        uses: docker/build-push-action@ca052bb54ab0790a636c9b5f226502c73d547a25
        with:
          file: Dockerfile
          target: final-vllm
          platforms: linux/amd64
          build-args: |
            "LLAMA_SERVER_VERSION=${{ inputs.llamaServerVersion }}"
            "LLAMA_SERVER_VARIANT=cuda"
            "BASE_IMAGE=nvidia/cuda:12.9.0-runtime-ubuntu24.04"
            "VLLM_VERSION=${{ inputs.vllmVersion }}"
          push: true
          sbom: true
          provenance: mode=max

      - name: Build ROCm image
        uses: docker/build-push-action@ca052bb54ab0790a636c9b5f226502c73d547a25
        with:
          file: Dockerfile
          target: final-llamacpp
          platforms: linux/amd64
          build-args: |
            "LLAMA_SERVER_VERSION=${{ inputs.llamaServerVersion }}"
            "LLAMA_SERVER_VARIANT=rocm"
            "BASE_IMAGE=rocm/ubuntu:22.04"
          push: true
          sbom: true
          provenance: mode=max
          tags: ${{ steps.tags.outputs.rocm }}