From b1c5817a896ff59604f5ab2b3334df8c5c71ff5b Mon Sep 17 00:00:00 2001 From: Dhruv Nair Date: Mon, 29 Apr 2024 13:44:39 +0530 Subject: [PATCH] Add debugging workflow (#7778) add debug workflow Co-authored-by: Sayak Paul --- .github/workflows/ssh-runner.yml | 55 ++++++++++++++++++++++++++++++++ 1 file changed, 55 insertions(+) create mode 100644 .github/workflows/ssh-runner.yml diff --git a/.github/workflows/ssh-runner.yml b/.github/workflows/ssh-runner.yml new file mode 100644 index 0000000000..befebfbc9b --- /dev/null +++ b/.github/workflows/ssh-runner.yml @@ -0,0 +1,55 @@ +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: Update clone + working-directory: /diffusers + run: | + git fetch && git checkout ${{ github.sha }} + - name: Cleanup + working-directory: /diffusers + run: | + rm -rf tests/__pycache__ + rm -rf tests/models/__pycache__ + rm -rf reports + - name: Show installed libraries and their versions + working-directory: /diffusers + run: pip freeze + + - 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