Add support for Replicate op in distributed training #26
This file contains hidden or 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: deploy | |
| on: [push, pull_request, workflow_dispatch] | |
| jobs: | |
| deploy: | |
| name: Test Deployment (GCC ${{ matrix.gcc }}) | |
| runs-on: ubuntu-latest | |
| container: nvidia/cuda:12.9.1-cudnn-devel-ubuntu24.04 | |
| steps: | |
| - name: Checkout Git Repository | |
| uses: actions/checkout@v3 | |
| - name: Install Depedencies | |
| run: | | |
| apt-get update -qq | |
| apt-get install -y build-essential cmake curl gcc-${{ matrix.gcc }} g++-${{ matrix.gcc }} git libibverbs-dev libmpich-dev mpich python3 python3-venv zlib1g-dev | |
| - name: Run Deploy Script | |
| run: ./deploy/sapling.sh | |
| env: | |
| CC: gcc-${{ matrix.gcc }} | |
| CXX: g++-${{ matrix.gcc }} | |
| strategy: | |
| matrix: | |
| gcc: [10, 11] |