E2E (NVIDIA A10G x4) #110
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # SPDX-License-Identifier: Apache-2.0 | |
| name: E2E (NVIDIA A10G x4) | |
| on: | |
| schedule: | |
| - cron: '0 8,20 * * *' # Runs at 8 AM and 8 PM UTC every day | |
| workflow_dispatch: | |
| inputs: | |
| pr_or_branch: | |
| description: 'pull request number or branch name' | |
| required: true | |
| default: 'main' | |
| jobs: | |
| start-runner: | |
| name: Start external EC2 runner | |
| runs-on: ubuntu-latest | |
| outputs: | |
| label: ${{ steps.start-ec2-runner.outputs.label }} | |
| ec2-instance-id: ${{ steps.start-ec2-runner.outputs.ec2-instance-id }} | |
| steps: | |
| - name: Configure AWS credentials | |
| uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2 | |
| with: | |
| aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }} | |
| aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }} | |
| aws-region: ${{ secrets.AWS_REGION }} | |
| - name: Start EC2 runner | |
| id: start-ec2-runner | |
| uses: machulav/ec2-github-runner@fcfb31a5760dad1314a64a0e172b78ec6fc8a17e # v2.3.6 | |
| with: | |
| mode: start | |
| github-token: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }} | |
| ec2-image-id: ami-03f6686697972e40a | |
| ec2-instance-type: g5.12xlarge | |
| subnet-id: subnet-02d230cffd9385bd4 | |
| security-group-id: sg-06300447c4a5fbef3 | |
| iam-role-name: instructlab-ci-runner | |
| aws-resource-tags: > | |
| [ | |
| {"Key": "Name", "Value": "instructlab-ci-github-runner"}, | |
| {"Key": "GitHubRepository", "Value": "${{ github.repository }}"} | |
| ] | |
| e2e: | |
| name: E2E Test | |
| needs: start-runner | |
| runs-on: ${{ needs.start-runner.outputs.label }} | |
| permissions: | |
| pull-requests: write | |
| steps: | |
| - name: Checkout | |
| uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 # v4.1.7 | |
| with: | |
| fetch-depth: 0 | |
| - name: Determine if pr_or_branch is a PR number | |
| id: check_pr | |
| run: | | |
| PR_OR_BRANCH=${{ github.event.inputs.pr_or_branch || 'main' }} # Default to 'main' if not set | |
| if [[ "$PR_OR_BRANCH" =~ ^[0-9]+$ ]]; then | |
| echo "is_pr=true" >> "$GITHUB_OUTPUT" | |
| else | |
| echo "is_pr=false" >> "$GITHUB_OUTPUT" | |
| fi | |
| echo "pr_or_branch=$PR_OR_BRANCH" >> "$GITHUB_OUTPUT" | |
| - name: Check if gh cli is installed | |
| id: gh_cli | |
| run: | | |
| if command -v gh &> /dev/null ; then | |
| echo "gh_cli_installed=true" >> "$GITHUB_OUTPUT" | |
| else | |
| echo "gh_cli_installed=false" >> "$GITHUB_OUTPUT" | |
| fi | |
| - name: Install gh CLI | |
| if: steps.gh_cli.outputs.gh_cli_installed == 'false' | |
| run: | | |
| sudo dnf install 'dnf-command(config-manager)' -y | |
| sudo dnf config-manager --add-repo https://cli.github.com/packages/rpm/gh-cli.repo | |
| sudo dnf install gh --repo gh-cli -y | |
| - name: test gh CLI | |
| run: | | |
| gh --version | |
| - name: set default repo | |
| run: | | |
| gh repo set-default ${{ github.server_url }}/${{ github.repository }} | |
| env: | |
| GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} | |
| - name: Add comment to PR | |
| if: steps.check_pr.outputs.is_pr == 'true' | |
| run: | | |
| gh pr comment "${{ steps.check_pr.outputs.pr_or_branch }}" -b "${{ github.workflow }} workflow launched on this PR: [View run](${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }})" | |
| env: | |
| GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} | |
| - name: Fetch and checkout PR | |
| if: steps.check_pr.outputs.is_pr == 'true' | |
| run: | | |
| gh pr checkout ${{ steps.check_pr.outputs.pr_or_branch }} | |
| env: | |
| GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} | |
| - name: Checkout branch | |
| if: steps.check_pr.outputs.is_pr == 'false' | |
| run: | | |
| git checkout ${{ steps.check_pr.outputs.pr_or_branch }} | |
| - name: Install Packages | |
| run: | | |
| cat /etc/os-release | |
| sudo dnf install -y gcc gcc-c++ make git python3.11 python3.11-devel | |
| - name: Install ilab | |
| run: | | |
| export CUDA_HOME="/usr/local/cuda" | |
| export LD_LIBRARY_PATH="$LD_LIBRARY_PATH:/usr/local/cuda/lib64:/usr/local/cuda/extras/CUPTI/lib64" | |
| export PATH="$PATH:$CUDA_HOME/bin" | |
| python3.11 -m venv --upgrade-deps venv | |
| . venv/bin/activate | |
| nvidia-smi | |
| python3.11 -m pip cache remove llama_cpp_python | |
| CMAKE_ARGS="-DLLAMA_CUDA=on" python3.11 -m pip install . | |
| # issue 1821: workaround for flash-attn and vllm | |
| # install with Torch and build dependencies installed | |
| python3.11 -m pip install packaging wheel setuptools-scm | |
| python3.11 -m pip install .[cuda] -r requirements-vllm-cuda.txt | |
| - name: ilab system info | |
| run: | | |
| . venv/bin/activate | |
| ilab system info | |
| - name: Run e2e test | |
| env: | |
| HF_TOKEN: ${{ secrets.HF_TOKEN }} | |
| run: | | |
| . venv/bin/activate | |
| ./scripts/basic-workflow-tests.sh -mevFMT | |
| - name: Add comment to PR if the workflow failed | |
| if: failure() && steps.check_pr.outputs.is_pr == 'true' | |
| run: | | |
| gh pr comment "${{ steps.check_pr.outputs.pr_or_branch }}" -b "e2e workflow failed on this PR: [View run](${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}), please investigate." | |
| env: | |
| GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} | |
| - name: Add comment to PR if the workflow succeeded | |
| if: success() && steps.check_pr.outputs.is_pr == 'true' | |
| run: | | |
| gh pr comment "${{ steps.check_pr.outputs.pr_or_branch }}" -b "e2e workflow succeeded on this PR: [View run](${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}), congrats!" | |
| env: | |
| GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} | |
| stop-runner: | |
| name: Stop external EC2 runner | |
| needs: | |
| - start-runner | |
| - e2e | |
| runs-on: ubuntu-latest | |
| if: ${{ always() }} | |
| steps: | |
| - name: Configure AWS credentials | |
| uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2 | |
| with: | |
| aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }} | |
| aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }} | |
| aws-region: ${{ secrets.AWS_REGION }} | |
| - name: Stop EC2 runner | |
| uses: machulav/ec2-github-runner@fcfb31a5760dad1314a64a0e172b78ec6fc8a17e # v2.3.6 | |
| with: | |
| mode: stop | |
| github-token: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }} | |
| label: ${{ needs.start-runner.outputs.label }} | |
| ec2-instance-id: ${{ needs.start-runner.outputs.ec2-instance-id }} |