build-neuronx-tgi.yml

name: Build and push NeuronX docker image to ghcr.io

on:
  workflow_dispatch:
  push:
    tags:
      - '*'

jobs:
  docker:
    runs-on:
      group: aws-general-8-plus
    permissions:
      contents: write
      packages: write
    steps:
      -
        name: Checkout sources
        uses: actions/checkout@v4
      -
        name: Install python and create venv
        run: |
          sudo apt update
          sudo apt install python3-venv python3-dev -y
          python3 -m venv aws_neuron_venv_pytorch
          source aws_neuron_venv_pytorch/bin/activate
          python -m pip install -U pip
          python -m pip install build
          python -m pip config set global.extra-index-url https://pip.repos.neuron.amazonaws.com
          python -m build .
      -
        name: Extract version
        run: |
          pkg=$(ls dist/optimum_neuron*.tar.gz); tmp=${pkg#*-}; echo "ON_VERSION=${tmp%.tar.gz*}">> $GITHUB_ENV
      -
        name: Set up Docker Buildx
        uses: docker/setup-buildx-action@v3
      -
        name: Login to ghcr.io
        uses: docker/login-action@v3
        with:
          registry: ghcr.io
          username: ${{ github.actor }}
          password: ${{ secrets.GITHUB_TOKEN }}
      -
        name: Build and push
        uses: docker/build-push-action@v6
        with:
          context: .
          file: text-generation-inference/Dockerfile
          push: true
          build-args: VERSION=${{ env.ON_VERSION }}
          tags: ghcr.io/huggingface/neuronx-tgi:${{ env.ON_VERSION }}, ghcr.io/huggingface/neuronx-tgi:latest