Parallel cross entropy #51
Workflow file for this run
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
| name: Optimum Neuron - Common tests on Trainium | |
| on: | |
| push: | |
| branches: [ main ] | |
| paths: | |
| - "optimum/**.py" | |
| pull_request: | |
| branches: [ main ] | |
| paths: | |
| - "optimum/**.py" | |
| concurrency: | |
| group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }} | |
| cancel-in-progress: true | |
| jobs: | |
| start-runner: | |
| name: Start self-hosted EC2 runner | |
| runs-on: ubuntu-latest | |
| env: | |
| AWS_REGION: us-east-1 | |
| EC2_AMI_ID: ${{ vars.TRAINIUM_AMI_ID }} | |
| EC2_INSTANCE_TYPE: trn1.2xlarge | |
| EC2_SUBNET_ID: subnet-859322b4,subnet-b7533b96,subnet-47cfad21,subnet-a396b2ad,subnet-06576a4b,subnet-df0f6180 | |
| EC2_SECURITY_GROUP: sg-0bb210cd3ec725a13 | |
| EC2_IAM_ROLE: optimum-ec2-github-actions-role | |
| 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@v1 | |
| with: | |
| aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }} | |
| aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }} | |
| aws-region: ${{ env.AWS_REGION }} | |
| - name: Start EC2 runner | |
| id: start-ec2-runner | |
| uses: philschmid/philschmid-ec2-github-runner@main | |
| with: | |
| mode: start | |
| github-token: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }} | |
| ec2-image-id: ${{ env.EC2_AMI_ID }} | |
| ec2-instance-type: ${{ env.EC2_INSTANCE_TYPE }} | |
| subnet-id: ${{ env.EC2_SUBNET_ID }} | |
| security-group-id: ${{ env.EC2_SECURITY_GROUP }} | |
| iam-role-name: ${{ env.EC2_IAM_ROLE }} | |
| aws-resource-tags: > # optional, requires additional permissions | |
| [ | |
| {"Key": "Name", "Value": "ec2-optimum-github-runner"}, | |
| {"Key": "GitHubRepository", "Value": "${{ github.repository }}"} | |
| ] | |
| optimum-neuron-tests: | |
| needs: start-runner # required to start the main job when the runner is ready | |
| runs-on: ${{ needs.start-runner.outputs.label }} # run the job on the newly created runner | |
| env: | |
| AWS_REGION: us-east-1 | |
| TESTS_TO_IGNORE_FLAGS: --ignore tests/distributed/ --ignore tests/test_examples.py | |
| steps: | |
| - name: Checkout | |
| uses: actions/checkout@v2 | |
| # - name: Install python3.8-venv | |
| # run: sudo apt update; sudo apt install -y python3.8-venv | |
| - name: Set pip repository pointing to the Neuron repository | |
| run: pip config set global.extra-index-url https://pip.repos.neuron.amazonaws.com | |
| - name: Install Python dependencies | |
| run: pip install .[tests,neuronx] | |
| - name: Run tests on Neuron cores | |
| run: | | |
| HF_TOKEN_OPTIMUM_NEURON_CI=${{ secrets.HF_TOKEN_OPTIMUM_NEURON_CI }} USE_VENV="false" pytest -m "is_trainium_test" $TESTS_TO_IGNORE_FLAGS tests | |
| - name: Run staging tests on Neuron cores | |
| run: HUGGINGFACE_CO_STAGING=1 pytest -m "is_trainium_test and is_staging_test" $TESTS_TO_IGNORE_FLAGS tests | |
| stop-runner: | |
| name: Stop self-hosted EC2 runner | |
| needs: | |
| - start-runner | |
| - optimum-neuron-tests | |
| runs-on: ubuntu-latest | |
| env: | |
| AWS_REGION: us-east-1 | |
| if: ${{ always() }} # required to stop the runner even if the error happened in the previous jobs | |
| steps: | |
| - name: Configure AWS credentials | |
| uses: aws-actions/configure-aws-credentials@v1 | |
| with: | |
| aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }} | |
| aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }} | |
| aws-region: ${{ env.AWS_REGION }} | |
| - name: Stop EC2 runner | |
| uses: philschmid/philschmid-ec2-github-runner@main | |
| 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 }} |