diffusers/.github/workflows/ssh-runner.yml

name: SSH into GPU runners

on:
  workflow_dispatch:
    inputs:
      runner_type:
        description: 'Type of runner to test (aws-g6-4xlarge-plus: a10 or aws-g4dn-2xlarge: t4)'
        type: choice
        required: true
        options:
          - aws-g6-4xlarge-plus
          - aws-g4dn-2xlarge
      docker_image:
        description: 'Name of the Docker image'
        required: true

env:
  IS_GITHUB_CI: "1"
  HF_HUB_READ_TOKEN: ${{ secrets.HF_HUB_READ_TOKEN }}
  HF_HOME: /mnt/cache
  DIFFUSERS_IS_CI: yes
  OMP_NUM_THREADS: 8
  MKL_NUM_THREADS: 8
  RUN_SLOW: yes

jobs:
  ssh_runner:
    name: "SSH"
    runs-on:
      group: "${{ github.event.inputs.runner_type }}"
    container:
      image: ${{ github.event.inputs.docker_image }}
      options: --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface/diffusers:/mnt/cache/ --gpus 0 --privileged

    steps:
      - name: Checkout diffusers
        uses: actions/checkout@v3
        with:
          fetch-depth: 2

      - name: NVIDIA-SMI
        run: |
          nvidia-smi

      - name: Tailscale # In order to be able to SSH when a test fails
        uses: huggingface/tailscale-action@main
        with:
          authkey: ${{ secrets.TAILSCALE_SSH_AUTHKEY }}
          slackChannel: ${{ secrets.SLACK_CIFEEDBACK_CHANNEL }}
          slackToken: ${{ secrets.SLACK_CIFEEDBACK_BOT_TOKEN }}
          waitForSSH: true