Skip to content

4 GPU Integration Test #3106

4 GPU Integration Test

4 GPU Integration Test #3106

name: 4 GPU Integration Test
on:
push:
branches: [ main ]
pull_request:
schedule:
# Runs hourly
- cron: '0 * * * *'
concurrency:
group: unit-test${{ github.workflow }}-${{ github.ref == 'refs/heads/main' && github.run_number || github.ref }}
cancel-in-progress: true
defaults:
run:
shell: bash -l -eo pipefail {0}
jobs:
build-test:
uses: pytorch/test-infra/.github/workflows/linux_job.yml@main
with:
runner: linux.g5.12xlarge.nvidia.gpu
gpu-arch-type: cuda
gpu-arch-version: "12.1"
# This image is faster to clone than the default, but it lacks CC needed by triton
# (1m25s vs 2m37s).
docker-image: torchtitan-ubuntu-20.04-clang12
repository: pytorch/torchtitan
upload-artifact: outputs
script: |
set -eux
# The generic Linux job chooses to use base env, not the one setup by the image
CONDA_ENV=$(conda env list --json | jq -r ".envs | .[-1]")
conda activate "${CONDA_ENV}"
pip config --user set global.progress_bar off
python -m pip install --force-reinstall --pre torch --index-url https://download.pytorch.org/whl/nightly/cu121
USE_CPP=0 python -m pip install git+https://github.com/pytorch/ao.git
mkdir artifacts-to-be-uploaded
python ./test_runner.py artifacts-to-be-uploaded --ngpu 4