Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
80 changes: 80 additions & 0 deletions .github/workflows/ci.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,80 @@
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"

jobs:
build:
runs-on: ubuntu-latest
steps:
- name: Checkout repo
uses: actions/checkout@v4

- 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"

- name: Log in to DockerHub
uses: docker/login-action@v3
with:
username: "docker"
password: ${{ secrets.ORG_ACCESS_TOKEN }}

- name: Set up Buildx
uses: docker/setup-buildx-action@v3
with:
version: "lab:latest"
driver: cloud
endpoint: "docker/make-product-smarter"
install: true

- name: Build CPU image
uses: docker/build-push-action@v5
with:
file: Dockerfile
platforms: linux/amd64, linux/arm64
build-args: |
"LLAMA_SERVER_VERSION=v0.0.5-rc2"
push: true
sbom: true
provenance: mode=max
tags: ${{ steps.tags.outputs.cpu }}

- name: Build CUDA image
uses: docker/build-push-action@v5
with:
file: Dockerfile
platforms: linux/amd64, linux/arm64
build-args: |
"LLAMA_SERVER_VERSION=v0.0.5-rc2"
"LLAMA_SERVER_VARIANT=cuda"
"BASE_IMAGE=nvidia/cuda:12.9.0-cudnn-runtime-ubuntu24.04"
push: true
sbom: true
provenance: mode=max
tags: ${{ steps.tags.outputs.cuda }}