Skip to content
.github/workflows/ci-cd.yml

Rename ci-cd to ci-cd.yml #28

Sign in to view logs

Rename ci-cd to ci-cd.yml

Rename ci-cd to ci-cd.yml #28

Workflow file for this run

.github/workflows/ci-cd.yml at 213bb22
# name: CI/CD Pipeline
# on:
# push:
# branches: [ main, develop ]
# pull_request:
# branches: [ main, develop ]
# release:
# types: [ created ]
# env:
# PYTHON_VERSION: '3.10'
# PYTORCH_VERSION: '2.0.0'
# jobs:
# code-quality:
# name: Code Quality Checks
# runs-on: ubuntu-latest
# steps:
# - uses: actions/checkout@v3
# - name: Set up Python
# uses: actions/setup-python@v4
# with:
# python-version: ${{ env.PYTHON_VERSION }}
# - name: Install dependencies
# run: |
# pip install black isort flake8 mypy pylint bandit
# - name: Black formatting check
# run: black --check .
# - name: isort import sorting check
# run: isort --check-only .
# - name: Flake8 linting
# run: flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
# - name: Security check with bandit
# run: bandit -r . -f json -o bandit-report.json
# - name: Type checking with mypy
# run: mypy . --ignore-missing-imports || true
# unit-tests:
# name: Unit Tests
# runs-on: ubuntu-latest
# strategy:
# matrix:
# python-version: ['3.8', '3.9', '3.10']
# steps:
# - uses: actions/checkout@v3
# - name: Set up Python ${{ matrix.python-version }}
# uses: actions/setup-python@v4
# with:
# python-version: ${{ matrix.python-version }}
# - name: Install dependencies
# run: |
# pip install torch torchvision --index-url https://download.pytorch.org/whl/cpu
# pip install -r requirements.txt
# pip install pytest pytest-cov pytest-xdist
# pip install -e .
# - name: Run unit tests
# run: |
# pytest test_distributed.py -v --cov=. --cov-report=xml --cov-report=html
# - name: Upload coverage to Codecov
# uses: codecov/codecov-action@v3
# with:
# file: ./coverage.xml
# integration-tests:
# name: Integration Tests (GPU)
# runs-on: [self-hosted, gpu]
# if: github.event_name == 'push'
# steps:
# - uses: actions/checkout@v3
# - name: Set up Python
# uses: actions/setup-python@v4
# with:
# python-version: ${{ env.PYTHON_VERSION }}
# - name: Install dependencies
# run: |
# pip install torch torchvision --index-url https://download.pytorch.org/whl/cu118
# pip install -r requirements.txt
# pip install -e .
# - name: Run single GPU tests
# run: |
# python production_train.py --batch-size 16 --epochs 1
# - name: Run multi-GPU tests
# run: |
# torchrun --nproc_per_node=2 production_train.py --batch-size 16 --epochs 1 --strategy ddp
# - name: Run benchmarks
# run: |
# python run_benchmark.py --gpus 1 2 --strategies ddp --batch-sizes 32
# docker-build:
# name: Build Docker Image
# runs-on: ubuntu-latest
# needs: [code-quality, unit-tests]
# steps:
# - uses: actions/checkout@v3
# - name: Set up Docker Buildx
# uses: docker/setup-buildx-action@v2
# - name: Login to DockerHub
# uses: docker/login-action@v2
# with:
# username: ${{ secrets.DOCKERHUB_USERNAME }}
# password: ${{ secrets.DOCKERHUB_TOKEN }}
# - name: Build and push
# uses: docker/build-push-action@v4
# with:
# context: .
# push: ${{ github.event_name == 'push' && github.ref == 'refs/heads/main' }}
# tags: |
# ${{ secrets.DOCKERHUB_USERNAME }}/distributed-training:latest
# ${{ secrets.DOCKERHUB_USERNAME }}/distributed-training:${{ github.sha }}
# cache-from: type=registry,ref=${{ secrets.DOCKERHUB_USERNAME }}/distributed-training:buildcache
# cache-to: type=registry,ref=${{ secrets.DOCKERHUB_USERNAME }}/distributed-training:buildcache,mode=max
# performance-benchmarks:
# name: Performance Benchmarks
# runs-on: [self-hosted, gpu]
# if: github.event_name == 'pull_request'
# steps:
# - uses: actions/checkout@v3
# - name: Install dependencies
# run: |
# pip install torch torchvision
# pip install -r requirements.txt
# pip install -e .
# - name: Run performance benchmarks
# run: |
# python run_benchmark.py --gpus 1 2 4 --strategies ddp fsdp --output-dir benchmark-results
# - name: Upload benchmark results
# uses: actions/upload-artifact@v3
# with:
# name: benchmark-results
# path: benchmark-results/
# security-scan:
# name: Security Scanning
# runs-on: ubuntu-latest
# steps:
# - uses: actions/checkout@v3
# - name: Run Trivy vulnerability scanner
# uses: aquasecurity/trivy-action@master
# with:
# scan-type: 'fs'
# scan-ref: '.'
# format: 'sarif'
# output: 'trivy-results.sarif'
# - name: Upload Trivy results to GitHub Security tab
# uses: github/codeql-action/upload-sarif@v2
# with:
# sarif_file: 'trivy-results.sarif'
# deploy-staging:
# name: Deploy to Staging
# runs-on: ubuntu-latest
# needs: [docker-build, integration-tests]
# if: github.ref == 'refs/heads/develop'
# steps:
# - uses: actions/checkout@v3
# - name: Configure kubectl
# uses: azure/setup-kubectl@v3
# - name: Deploy to staging
# run: |
# kubectl apply -f k8s-deployment.yaml --namespace=staging
# kubectl rollout status statefulset/distributed-training --namespace=staging
# deploy-production:
# name: Deploy to Production
# runs-on: ubuntu-latest
# needs: [docker-build, integration-tests, performance-benchmarks]
# if: github.event_name == 'release'
# steps:
# - uses: actions/checkout@v3
# - name: Configure kubectl
# uses: azure/setup-kubectl@v3
# - name: Deploy to production
# run: |
# kubectl apply -f k8s-deployment.yaml --namespace=production
# kubectl rollout status statefulset/distributed-training --namespace=production
# - name: Run smoke tests
# run: |
# kubectl exec -n production distributed-training-0 -- python -c "import torch; print(f'PyTorch {torch.__version__}')"
# notification:
# name: Send Notifications
# runs-on: ubuntu-latest
# needs: [code-quality, unit-tests, integration-tests]
# if: always()
# steps:
# - name: Send Slack notification
# uses: 8398a7/action-slack@v3
# with:
# status: ${{ job.status }}
# text: 'CI/CD Pipeline Status: ${{ job.status }}'
# webhook_url: ${{ secrets.SLACK_WEBHOOK }}