pt: supprot --output
in dp train
#755
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
on: | |
# manually trigger | |
workflow_dispatch: | |
pull_request: | |
types: | |
- "labeled" | |
# to let the PR pass the test | |
- "opened" | |
- "reopened" | |
- "synchronize" | |
merge_group: | |
concurrency: | |
group: ${{ github.workflow }}-${{ github.ref || github.run_id }} | |
cancel-in-progress: true | |
name: Test CUDA | |
jobs: | |
test_cuda: | |
name: Test Python and C++ on CUDA | |
runs-on: nvidia | |
# https://github.com/deepmodeling/deepmd-kit/pull/2884#issuecomment-1744216845 | |
container: | |
image: nvidia/cuda:12.3.1-devel-ubuntu22.04 | |
options: --gpus all | |
if: github.repository_owner == 'deepmodeling' && (github.event_name == 'pull_request' && github.event.label && github.event.label.name == 'Test CUDA' || github.event_name == 'workflow_dispatch' || github.event_name == 'merge_group') | |
steps: | |
- name: Make sudo and git work | |
run: apt-get update && apt-get install -y sudo git | |
- uses: actions/checkout@v4 | |
- uses: actions/setup-python@v5 | |
with: | |
python-version: '3.11' | |
# cache: 'pip' | |
- name: Setup MPI | |
uses: mpi4py/setup-mpi@v1 | |
with: | |
mpi: mpich | |
- uses: lukka/get-cmake@latest | |
with: | |
useLocalCache: true | |
useCloudCache: false | |
- name: Install wget and unzip | |
run: apt-get update && apt-get install -y wget unzip | |
- run: | | |
wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/cuda-keyring_1.0-1_all.deb \ | |
&& sudo dpkg -i cuda-keyring_1.0-1_all.deb \ | |
&& sudo apt-get update \ | |
&& sudo apt-get -y install cuda-12-3 libcudnn8=8.9.5.*-1+cuda12.3 | |
if: false # skip as we use nvidia image | |
- run: python -m pip install -U "pip>=21.3.1,!=23.0.0" | |
- run: python -m pip install "tensorflow>=2.15.0rc0" "torch>=2.2.0" | |
- run: python -m pip install -v -e .[gpu,test,lmp,cu12,torch] "ase @ https://gitlab.com/ase/ase/-/archive/8c5aa5fd6448c5cfb517a014dccf2b214a9dfa8f/ase-8c5aa5fd6448c5cfb517a014dccf2b214a9dfa8f.tar.gz" | |
env: | |
DP_VARIANT: cuda | |
NUM_WORKERS: 0 | |
DP_ENABLE_NATIVE_OPTIMIZATION: 1 | |
- run: dp --version | |
- run: python -m pytest source/tests --durations=0 | |
- name: Download libtorch | |
run: | | |
wget https://download.pytorch.org/libtorch/cu121/libtorch-cxx11-abi-shared-with-deps-2.2.1%2Bcu121.zip -O libtorch.zip | |
unzip libtorch.zip | |
- run: | | |
export CMAKE_PREFIX_PATH=$GITHUB_WORKSPACE/libtorch | |
source/install/test_cc_local.sh | |
env: | |
OMP_NUM_THREADS: 1 | |
TF_INTRA_OP_PARALLELISM_THREADS: 1 | |
TF_INTER_OP_PARALLELISM_THREADS: 1 | |
LMP_CXX11_ABI_0: 1 | |
CMAKE_GENERATOR: Ninja | |
DP_VARIANT: cuda | |
DP_USE_MPICH2: 1 | |
- run: | | |
export LD_LIBRARY_PATH=$GITHUB_WORKSPACE/dp_test/lib:$GITHUB_WORKSPACE/libtorch/lib:$CUDA_PATH/lib64:$LD_LIBRARY_PATH | |
export PATH=$GITHUB_WORKSPACE/dp_test/bin:$PATH | |
python -m pytest source/lmp/tests | |
python -m pytest source/ipi/tests | |
env: | |
OMP_NUM_THREADS: 1 | |
TF_INTRA_OP_PARALLELISM_THREADS: 1 | |
TF_INTER_OP_PARALLELISM_THREADS: 1 | |
LAMMPS_PLUGIN_PATH: ${{ github.workspace }}/dp_test/lib/deepmd_lmp | |
pass: | |
name: Pass testing on CUDA | |
needs: [test_cuda] | |
runs-on: ubuntu-latest | |
if: always() | |
steps: | |
- name: Decide whether the needed jobs succeeded or failed | |
uses: re-actors/alls-green@release/v1 | |
with: | |
jobs: ${{ toJSON(needs) }} | |
allowed-skips: test_cuda |