inference_cache_stable_diffusion.yml

name: Optimum neuron SD inference cache builder

on:
  workflow_dispatch:
  schedule:
    # Schedule the workflow to run every Saturday at midnight UTC
    - cron: '0 0 * * 6'

concurrency:
  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}

jobs:
  cache:
    name: Create optimum-neuron inference cache
    runs-on:
      group: aws-inf2-8xlarge
    env:
      AWS_REGION: us-east-1
    strategy:
      fail-fast: false
      matrix:
        config: [stable-diffusion]
    steps:
      - name: Install Neuron runtime
        run: |
          . /etc/os-release
          sudo tee /etc/apt/sources.list.d/neuron.list > /dev/null <<EOF
          deb https://apt.repos.neuron.amazonaws.com ${VERSION_CODENAME} main
          EOF
          wget -qO - https://apt.repos.neuron.amazonaws.com/GPG-PUB-KEY-AMAZON-AWS-NEURON.PUB | sudo apt-key add -
          sudo apt-get update -y
          sudo apt-get install aws-neuronx-tools=2.19.0.0 aws-neuronx-runtime-lib=2.22.19.0-5856c0b42 aws-neuronx-collectives=2.22.33.0-d2128d1aa  -y
          export PATH=/opt/aws/neuron/bin:$PATH
      - name: Checkout
        uses: actions/checkout@v4
      - name: Install python and create venv
        run: |
          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 config set global.extra-index-url https://pip.repos.neuron.amazonaws.com
      - name: Install optimum neuron
        run: |
          source aws_neuron_venv_pytorch/bin/activate
          python -m pip install .[neuronx,diffusers]
      - name: Create cache for ${{matrix.config}} models
        run: |
          source aws_neuron_venv_pytorch/bin/activate
          config_prefix_url=https://huggingface.co/aws-neuron/optimum-neuron-cache/raw/main/inference-cache-config
          HF_TOKEN=${{secrets.HF_TOKEN_OPTIMUM_NEURON_CACHE}} \
            python tools/auto_fill_inference_cache.py --config_file ${config_prefix_url}/${{matrix.config}}.json