wehub-resource-sync
116 lines
3.7 KiB
YAML
116 lines
3.7 KiB
YAML
################################################################################
|
|
# DeepSpeed CI - AWS L40S GPU Tests (HuggingFace Accelerate Integration)
|
|
#
|
|
# Runs the same tests as modal-accelerate.yml but on AWS self-hosted runners.
|
|
# Tests DeepSpeed integration with HuggingFace Accelerate library.
|
|
# Uses 4x NVIDIA L40S GPUs on g6e.12xlarge instances.
|
|
################################################################################
|
|
|
|
name: aws-accelerate
|
|
|
|
on:
|
|
workflow_dispatch:
|
|
|
|
push:
|
|
branches:
|
|
- master
|
|
|
|
pull_request:
|
|
branches:
|
|
- master
|
|
|
|
concurrency:
|
|
group: ${{ github.workflow }}-${{ github.ref }}
|
|
cancel-in-progress: true
|
|
|
|
jobs:
|
|
check-paths:
|
|
name: aws-accelerate / check paths
|
|
runs-on: ubuntu-latest
|
|
outputs:
|
|
should_run: ${{ steps.filter.outputs.run_tests }}
|
|
steps:
|
|
- uses: actions/checkout@v4
|
|
- uses: dorny/paths-filter@v3
|
|
id: filter
|
|
with:
|
|
filters: |
|
|
run_tests:
|
|
- '**'
|
|
- '!docs/**'
|
|
- '!blogs/**'
|
|
- '!deepspeed/inference/v2/**'
|
|
- '!tests/unit/inference/v2/**'
|
|
|
|
accelerate-tests:
|
|
name: aws-accelerate / accelerate integration tests
|
|
needs: check-paths
|
|
if: needs.check-paths.outputs.should_run == 'true'
|
|
runs-on: [self-hosted, gpu-ci, gpu-l40s, l40s-1gpu, aws]
|
|
timeout-minutes: 60
|
|
|
|
container:
|
|
image: nvidia/cuda:12.6.3-devel-ubuntu22.04
|
|
options: --gpus all --shm-size "32G"
|
|
|
|
env:
|
|
TORCH_VER: "2.7"
|
|
CUDA_VER: "12.6"
|
|
|
|
steps:
|
|
- name: Install system dependencies
|
|
run: |
|
|
apt-get update && apt-get install -y git git-lfs libaio-dev python3 python3-pip
|
|
git lfs install
|
|
ln -sf /usr/bin/python3 /usr/bin/python
|
|
|
|
- name: Checkout repository
|
|
uses: actions/checkout@v4
|
|
with:
|
|
lfs: true
|
|
|
|
- name: Install PyTorch
|
|
run: |
|
|
pip install torch==2.7.1 torchvision==0.22.1 torchaudio==2.7.1 --index-url https://download.pytorch.org/whl/cu126
|
|
|
|
- name: Install Python dependencies
|
|
run: |
|
|
pip install --upgrade pip
|
|
pip install -r requirements/requirements.txt
|
|
pip install -r requirements/requirements-dev.txt
|
|
pip install datasets
|
|
|
|
- name: Check environment
|
|
run: |
|
|
echo "=== GPU Information ==="
|
|
nvidia-smi
|
|
echo ""
|
|
echo "=== CUDA Version ==="
|
|
nvcc --version
|
|
echo ""
|
|
echo "=== Python/PyTorch Info ==="
|
|
python --version
|
|
python -c "import torch; print(f'PyTorch: {torch.__version__}')"
|
|
python -c "import torch; print(f'CUDA available: {torch.cuda.is_available()}')"
|
|
python -c "import torch; print(f'CUDA devices: {torch.cuda.device_count()}')"
|
|
python -c "import torch; print(f'BF16 support: {torch.cuda.is_bf16_supported()}')"
|
|
|
|
- name: Install DeepSpeed
|
|
run: |
|
|
# Initialize CUDA before install so setup.py can detect NCCL version
|
|
python -c "import torch; torch.cuda.init(); print(f'NCCL version: {torch.cuda.nccl.version()}')"
|
|
# Use --no-build-isolation so setup.py can access pre-installed PyTorch
|
|
pip install --no-build-isolation .
|
|
ds_report
|
|
# Debug: Check captured torch_info values
|
|
python -c "from deepspeed.git_version_info import torch_info; print(f'torch_info: {torch_info}')"
|
|
|
|
- name: Clone and install Accelerate
|
|
run: |
|
|
git clone https://github.com/huggingface/accelerate
|
|
pip install "./accelerate[testing]"
|
|
|
|
- name: Run Accelerate DeepSpeed tests
|
|
run: |
|
|
pytest --verbose ./accelerate/tests/deepspeed
|