Upamanyu098's picture
End of training
ef4d689 verified
raw
history blame
1.24 kB
name: SSH into runners
on:
workflow_dispatch:
inputs:
runner_type:
description: 'Type of runner to test (a10 or t4)'
required: true
docker_image:
description: 'Name of the Docker image'
required: true
env:
IS_GITHUB_CI: "1"
HF_HUB_READ_TOKEN: ${{ secrets.HF_HUB_READ_TOKEN }}
HF_HOME: /mnt/cache
DIFFUSERS_IS_CI: yes
OMP_NUM_THREADS: 8
MKL_NUM_THREADS: 8
RUN_SLOW: yes
jobs:
ssh_runner:
name: "SSH"
runs-on: [single-gpu, nvidia-gpu, "${{ github.event.inputs.runner_type }}", ci]
container:
image: ${{ github.event.inputs.docker_image }}
options: --gpus all --privileged --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/
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@v1
with:
authkey: ${{ secrets.TAILSCALE_SSH_AUTHKEY }}
slackChannel: ${{ secrets.SLACK_CIFEEDBACK_CHANNEL }}
slackToken: ${{ secrets.SLACK_CIFEEDBACK_BOT_TOKEN }}
waitForSSH: true