Skip to content
Back to pull request #230

New improved modelling for LLM Deepspeed. #177

Sign in to view logs

New improved modelling for LLM Deepspeed.

New improved modelling for LLM Deepspeed. #177

Workflow file for this run

.github/workflows/ci.yml at ecc384a
name: Build and Test
on:
pull_request:
branches: [main, dev]
push:
jobs:
build-and-test:
strategy:
fail-fast: false
matrix:
os: [ubuntu-22.04]
gcc: [10]
python: ["3.9", "3.10", "3.11"]
venv: ["via-setup", "via-reqs"]
name: ${{ matrix.os }}-${{ matrix.gcc }}-${{ matrix.python }}-${{ matrix.venv }}
runs-on: ${{ matrix.os }}
env:
CC: gcc-${{ matrix.gcc }}
CXX: g++-${{ matrix.gcc }}
DFTRACER_BUILD_TYPE: "Debug"
DFTRACER_ENABLE: 1
DFTRACER_LOG_LEVEL: "INFO"
DLIO_EXEC: ${{ matrix.venv == 'via-setup' && 'dlio_benchmark' || 'python dlio_benchmark/main.py' }}
GOTCHA_DEBUG: 1
OMPI_ALLOW_RUN_AS_ROOT: 1
OMPI_ALLOW_RUN_AS_ROOT_CONFIRM: 1
PYTHON_VER: ${{ matrix.python }}
RDMAV_FORK_SAFE: "1"
VENV_PATH: "/home/runner/work/.venv/${{ matrix.venv }}"
steps:
- name: Clear disc
run: |
sudo rm -rf /usr/share/dotnet
sudo rm -rf /opt/ghc
sudo rm -rf "/usr/local/share/boost"
sudo rm -rf "$AGENT_TOOLSDIRECTORY"
- name: Push checkout
if: github.event_name == 'push'
uses: actions/checkout@v3
- name: PR checkout
if: github.event_name == 'pull_request'
uses: actions/checkout@v3
with:
ref: ${{ github.event.pull_request.head.sha }}
- name: Set up Python ${{ matrix.python }}
uses: actions/setup-python@v3
with:
python-version: ${{ matrix.python }}
- name: Add current directory to PYTHONPATH
if: matrix.venv == 'via-reqs'
run: echo "PYTHONPATH=$(pwd):$PYTHONPATH" >> $GITHUB_ENV
- name: Cache install modules
id: cache-modules
uses: actions/cache@v3
with:
path: ${{ env.VENV_PATH }}
key: ${{ matrix.venv }}-gcc${{ matrix.gcc }}-python${{ matrix.python }}-${{ hashFiles('requirements.txt', 'setup.py') }}
- name: Install system dependencies
run: |
sudo apt update
sudo apt-get install -y $CC $CXX libc6 git
sudo apt-get install -y openmpi-bin openmpi-common libopenmpi-dev python3-dev
- name: Install DLIO via setup.py
if: matrix.venv == 'via-setup' && steps.cache-modules.outputs.cache-hit != 'true'
run: |
echo "venv: ${VENV_PATH} - gcc: $CC"
python -m venv ${VENV_PATH}
source ${VENV_PATH}/bin/activate
pip install --upgrade pip
pip install .[test]
- name: Install DLIO via requirements.txt
if: matrix.venv == 'via-reqs' && steps.cache-modules.outputs.cache-hit != 'true'
run: |
echo "venv: ${VENV_PATH} - gcc: $CC"
python -m venv ${VENV_PATH}
source ${VENV_PATH}/bin/activate
pip install --upgrade pip
pip install -r requirements.txt
- name: test_checkpoint_epoch
run: |
source ${VENV_PATH}/bin/activate
mpirun -np 2 pytest -k test_checkpoint_epoch[tensorflow-1024-optimizers0-2-layer_params0-all_ranks] -v
mpirun -np 2 pytest -k test_checkpoint_epoch[pytorch-1024-optimizers1-2-layer_params1-all_ranks] -v
mpirun -np 2 pytest -k test_checkpoint_epoch[tensorflow-1024-optimizers2-2-layer_params2-rank_zero] -v
mpirun -np 2 pytest -k test_checkpoint_epoch[pytorch-1024-optimizers3-2-layer_params3-rank_zero] -v
mpirun -np 2 pytest -k test_checkpoint_epoch[tensorflow-1024-optimizers4-1-layer_params4-all_ranks] -v
mpirun -np 2 pytest -k test_checkpoint_epoch[pytorch-1024-optimizers5-1-layer_params5-all_ranks] -v
rm -rf data
- name: test_checkpoint_step
run: |
source ${VENV_PATH}/bin/activate
mpirun -np 2 pytest -k test_checkpoint_step -v
- name: test_gen_data
run: |
source ${VENV_PATH}/bin/activate
mpirun -np 2 pytest -k test_gen_data[png-tensorflow] -v
mpirun -np 2 pytest -k test_gen_data[npz-tensorflow] -v
mpirun -np 2 pytest -k test_gen_data[jpeg-tensorflow] -v
mpirun -np 2 pytest -k test_gen_data[tfrecord-tensorflow] -v
mpirun -np 2 pytest -k test_gen_data[hdf5-tensorflow] -v
mpirun -np 2 pytest -k test_gen_data[indexed_binary-tensorflow] -v
mpirun -np 2 pytest -k test_gen_data[mmap_indexed_binary-tensorflow] -v
rm -rf data
- name: test_custom_storage_root_gen_data
run: |
source ${VENV_PATH}/bin/activate
mpirun -np 2 pytest -k test_storage_root_gen_data[png-tensorflow] -v
mpirun -np 2 pytest -k test_storage_root_gen_data[npz-tensorflow] -v
mpirun -np 2 pytest -k test_storage_root_gen_data[jpeg-tensorflow] -v
mpirun -np 2 pytest -k test_storage_root_gen_data[tfrecord-tensorflow] -v
mpirun -np 2 pytest -k test_storage_root_gen_data[hdf5-tensorflow] -v
mpirun -np 2 pytest -k test_storage_root_gen_data[indexed_binary-tensorflow] -v
mpirun -np 2 pytest -k test_storage_root_gen_data[mmap_indexed_binary-tensorflow] -v
rm -rf data
- name: test_train
run: |
source ${VENV_PATH}/bin/activate
mpirun -np 2 pytest -k test_train[png-tensorflow-tensorflow-True] -v
mpirun -np 2 pytest -k test_train[npz-tensorflow-tensorflow-True] -v
mpirun -np 2 pytest -k test_train[jpeg-tensorflow-tensorflow-True] -v
mpirun -np 2 pytest -k test_train[tfrecord-tensorflow-tensorflow-True] -v
mpirun -np 2 pytest -k test_train[hdf5-tensorflow-tensorflow-True] -v
mpirun -np 2 pytest -k test_train[csv-tensorflow-tensorflow-True] -v
mpirun -np 2 pytest -k test_train[png-pytorch-pytorch-True] -v
mpirun -np 2 pytest -k test_train[npz-pytorch-pytorch-True] -v
mpirun -np 2 pytest -k test_train[jpeg-pytorch-pytorch-True] -v
mpirun -np 2 pytest -k test_train[hdf5-pytorch-pytorch-True] -v
mpirun -np 2 pytest -k test_train[csv-pytorch-pytorch-True] -v
mpirun -np 2 pytest -k test_train[png-tensorflow-dali-True] -v
mpirun -np 2 pytest -k test_train[npz-tensorflow-dali-True] -v
mpirun -np 2 pytest -k test_train[jpeg-tensorflow-dali-True] -v
mpirun -np 2 pytest -k test_train[hdf5-tensorflow-dali-True] -v
mpirun -np 2 pytest -k test_train[csv-tensorflow-dali-True] -v
mpirun -np 2 pytest -k test_train[png-pytorch-dali-True] -v
mpirun -np 2 pytest -k test_train[npz-pytorch-dali-True] -v
mpirun -np 2 pytest -k test_train[jpeg-pytorch-dali-True] -v
mpirun -np 2 pytest -k test_train[hdf5-pytorch-dali-True] -v
mpirun -np 2 pytest -k test_train[csv-pytorch-dali-True] -v
mpirun -np 2 pytest -k test_train[indexed_binary-tensorflow-tensorflow-True] -v
mpirun -np 2 pytest -k test_train[indexed_binary-pytorch-pytorch-True] -v
mpirun -np 2 pytest -k test_train[indexed_binary-tensorflow-dali-True] -v
mpirun -np 2 pytest -k test_train[indexed_binary-pytorch-dali-True] -v
mpirun -np 2 pytest -k test_train[mmap_indexed_binary-tensorflow-tensorflow-True] -v
mpirun -np 2 pytest -k test_train[mmap_indexed_binary-pytorch-pytorch-True] -v
mpirun -np 2 pytest -k test_train[mmap_indexed_binary-tensorflow-dali-True] -v
mpirun -np 2 pytest -k test_train[mmap_indexed_binary-pytorch-dali-True] -v
mpirun -np 2 pytest -k test_train[png-tensorflow-tensorflow-False] -v
mpirun -np 2 pytest -k test_train[npz-tensorflow-tensorflow-False] -v
mpirun -np 2 pytest -k test_train[jpeg-tensorflow-tensorflow-False] -v
mpirun -np 2 pytest -k test_train[tfrecord-tensorflow-tensorflow-False] -v
mpirun -np 2 pytest -k test_train[hdf5-tensorflow-tensorflow-False] -v
mpirun -np 2 pytest -k test_train[csv-tensorflow-tensorflow-False] -v
mpirun -np 2 pytest -k test_train[png-pytorch-pytorch-False] -v
mpirun -np 2 pytest -k test_train[npz-pytorch-pytorch-False] -v
mpirun -np 2 pytest -k test_train[jpeg-pytorch-pytorch-False] -v
mpirun -np 2 pytest -k test_train[hdf5-pytorch-pytorch-False] -v
mpirun -np 2 pytest -k test_train[csv-pytorch-pytorch-False] -v
mpirun -np 2 pytest -k test_train[png-tensorflow-dali-False] -v
mpirun -np 2 pytest -k test_train[npz-tensorflow-dali-False] -v
mpirun -np 2 pytest -k test_train[jpeg-tensorflow-dali-False] -v
mpirun -np 2 pytest -k test_train[hdf5-tensorflow-dali-False] -v
mpirun -np 2 pytest -k test_train[csv-tensorflow-dali-False] -v
mpirun -np 2 pytest -k test_train[png-pytorch-dali-False] -v
mpirun -np 2 pytest -k test_train[npz-pytorch-dali-False] -v
mpirun -np 2 pytest -k test_train[jpeg-pytorch-dali-False] -v
mpirun -np 2 pytest -k test_train[hdf5-pytorch-dali-False] -v
mpirun -np 2 pytest -k test_train[csv-pytorch-dali-False] -v
mpirun -np 2 pytest -k test_train[indexed_binary-tensorflow-tensorflow-False] -v
mpirun -np 2 pytest -k test_train[indexed_binary-pytorch-pytorch-False] -v
mpirun -np 2 pytest -k test_train[indexed_binary-tensorflow-dali-False] -v
mpirun -np 2 pytest -k test_train[indexed_binary-pytorch-dali-False] -v
mpirun -np 2 pytest -k test_train[mmap_indexed_binary-tensorflow-tensorflow-False] -v
mpirun -np 2 pytest -k test_train[mmap_indexed_binary-pytorch-pytorch-False] -v
mpirun -np 2 pytest -k test_train[mmap_indexed_binary-tensorflow-dali-False] -v
mpirun -np 2 pytest -k test_train[mmap_indexed_binary-pytorch-dali-False] -v
rm -rf data
- name: test_custom_storage_root_train
run: |
source ${VENV_PATH}/bin/activate
mpirun -np 2 pytest -k test_custom_storage_root_train[png-tensorflow] -v
mpirun -np 2 pytest -k test_custom_storage_root_train[npz-tensorflow] -v
mpirun -np 2 pytest -k test_custom_storage_root_train[jpeg-tensorflow] -v
mpirun -np 2 pytest -k test_custom_storage_root_train[tfrecord-tensorflow] -v
mpirun -np 2 pytest -k test_custom_storage_root_train[hdf5-tensorflow] -v
mpirun -np 2 pytest -k test_custom_storage_root_train[csv-tensorflow] -v
mpirun -np 2 pytest -k test_custom_storage_root_train[png-pytorch] -v
mpirun -np 2 pytest -k test_custom_storage_root_train[npz-pytorch] -v
mpirun -np 2 pytest -k test_custom_storage_root_train[jpeg-pytorch] -v
mpirun -np 2 pytest -k test_custom_storage_root_train[hdf5-pytorch] -v
mpirun -np 2 pytest -k test_custom_storage_root_train[csv-pytorch] -v
mpirun -np 2 pytest -k test_custom_storage_root_train[indexed_binary-tensorflow] -v
mpirun -np 2 pytest -k test_custom_storage_root_train[indexed_binary-pytorch] -v
mpirun -np 2 pytest -k test_custom_storage_root_train[mmap_indexed_binary-tensorflow] -v
mpirun -np 2 pytest -k test_custom_storage_root_train[mmap_indexed_binary-pytorch] -v
rm -rf data
- name: test_eval
run: |
source ${VENV_PATH}/bin/activate
mpirun -np 2 pytest -k test_eval -v
- name: test_multi_threads
run: |
source ${VENV_PATH}/bin/activate
mpirun -np 2 pytest -k test_multi_threads[tensorflow-0] -v
mpirun -np 2 pytest -k test_multi_threads[tensorflow-1] -v
mpirun -np 2 pytest -k test_multi_threads[tensorflow-2] -v
mpirun -np 2 pytest -k test_multi_threads[pytorch-0] -v
mpirun -np 2 pytest -k test_multi_threads[pytorch-1] -v
mpirun -np 2 pytest -k test_multi_threads[pytorch-2] -v
rm -rf data
- name: test-pytorch-multiprocessing-context
run: |
source ${VENV_PATH}/bin/activate
mpirun -np 2 pytest -k test_pytorch_multiprocessing_context[0-None] -v
mpirun -np 2 pytest -k test_pytorch_multiprocessing_context[1-fork] -v
mpirun -np 2 pytest -k test_pytorch_multiprocessing_context[2-forkserver] -v
mpirun -np 2 pytest -k test_pytorch_multiprocessing_context[2-spawn] -v
rm -rf data
- name: test_subset
run: |
source ${VENV_PATH}/bin/activate
rm -rf output data checkpoints
mpirun -np 2 pytest -k test_subset -v
rm -rf data
- name: test-tf-loader-tfrecord
run: |
source ${VENV_PATH}/bin/activate
rm -rf output data checkpoints
mpirun -np 2 ${DLIO_EXEC} workload=resnet50_tf ++workload.dataset.num_files_train=64 ++workload.workflow.train=False ++workload.workflow.generate_data=True ++workload.dataset.num_files_train=4 ++workload.dataset.num_samples_per_file=16
mpirun -np 2 ${DLIO_EXEC} workload=resnet50_tf ++workload.dataset.num_files_train=64 ++workload.workflow.train=True ++workload.workflow.generate_data=False ++workload.dataset.num_files_train=4 ++workload.dataset.num_samples_per_file=16 ++workload.train.computation_time=0.01 ++workload.train.epochs=1
rm -rf data
- name: test-torch-loader-npz
run: |
source ${VENV_PATH}/bin/activate
rm -rf output data checkpoints
mpirun -np 2 ${DLIO_EXEC} workload=unet3d_a100 ++workload.train.computation_time=0.05 ++workload.evaluation.eval_time=0.01 ++workload.workflow.train=False ++workload.workflow.generate_data=True ++workload.dataset.num_files_train=8 ++workload.dataset.num_files_eval=8 ++workload.reader.read_threads=2 ++workload.dataset.record_length=4096 ++workload.dataset.record_length_stdev=0
mpirun -np 2 ${DLIO_EXEC} workload=unet3d_a100 ++workload.train.computation_time=0.05 ++workload.evaluation.eval_time=0.01 ++workload.train.epochs=1 ++workload.workflow.train=True ++workload.workflow.generate_data=False ++workload.dataset.num_files_train=8 ++workload.dataset.num_files_eval=8 ++workload.reader.read_threads=0 ++workload.dataset.record_length=4096 ++workload.dataset.record_length_stdev=0
rm -rf data
- name: test-tf-loader-npz
run: |
source ${VENV_PATH}/bin/activate
rm -rf output data checkpoints
mpirun -np 2 ${DLIO_EXEC} workload=unet3d_a100 ++workload.framework=tensorflow ++workload.data_reader.data_loader=tensorflow ++workload.train.computation_time=0.05 ++workload.evaluation.eval_time=0.01 ++workload.train.epochs=2 ++workload.workflow.train=False ++workload.workflow.generate_data=True ++workload.dataset.num_files_train=16 ++workload.dataset.num_files_eval=16 ++workload.reader.read_threads=2 ++workload.dataset.record_length=4096 ++workload.dataset.record_length_stdev=0
mpirun -np 2 ${DLIO_EXEC} workload=unet3d_a100 ++workload.framework=tensorflow ++workload.data_reader.data_loader=tensorflow ++workload.train.computation_time=0.05 ++workload.evaluation.eval_time=0.01 ++workload.train.epochs=2 ++workload.workflow.train=True ++workload.workflow.generate_data=False ++workload.dataset.num_files_train=16 ++workload.dataset.num_files_eval=16 ++workload.reader.read_threads=2 ++workload.dataset.record_length=4096 ++workload.dataset.record_length_stdev=0
rm -rf data
- name: test_unet3d
run: |
source ${VENV_PATH}/bin/activate
rm -rf output data checkpoints
mpirun -np 2 ${DLIO_EXEC} workload=unet3d_a100 ++workload.workflow.generate_data=True ++workload.dataset.num_files_train=42
mpirun -np 2 ${DLIO_EXEC} workload=unet3d_h100 ++workload.workflow.generate_data=True ++workload.dataset.num_files_train=42
mpirun -np 2 ${DLIO_EXEC} workload=unet3d_h100 ++workload.workflow.generate_data=True ++workload.dataset.num_files_train=42 ++workload.dataset.format=synthetic
rm -rf data
- name: test_resnet50
run: |
source ${VENV_PATH}/bin/activate
rm -rf output data checkpoints
mpirun -np 2 ${DLIO_EXEC} workload=resnet50_a100 ++workload.workflow.generate_data=True ++workload.dataset.num_files_train=8 ++workload.reader.read_threads=1
mpirun -np 2 ${DLIO_EXEC} workload=resnet50_h100 ++workload.workflow.generate_data=True ++workload.dataset.num_files_train=8 ++workload.reader.read_threads=1
mpirun -np 2 ${DLIO_EXEC} workload=resnet50_h100 ++workload.workflow.generate_data=True ++workload.dataset.num_files_train=8 ++workload.reader.read_threads=1 ++workload.dataset.format=synthetic
rm -rf data
- name: test_cosmoflow
run: |
source ${VENV_PATH}/bin/activate
rm -rf output data checkpoints
mpirun -np 2 ${DLIO_EXEC} workload=cosmoflow_a100 ++workload.workflow.generate_data=True ++workload.dataset.num_files_train=16
mpirun -np 2 ${DLIO_EXEC} workload=cosmoflow_h100 ++workload.workflow.generate_data=True ++workload.dataset.num_files_train=16
mpirun -np 2 ${DLIO_EXEC} workload=cosmoflow_h100 ++workload.workflow.generate_data=True ++workload.dataset.num_files_train=16 ++workload.dataset.format=synthetic
rm -rf data