GPU CI #2

	name: GPU tests

	on:
	schedule:
	# Runs at midnight every day
	- cron: '0 0 * * *'
	push:
	branches: [ main ]
	pull_request:
	workflow_dispatch:

	concurrency:
	group: gpu-test-${{ github.workflow }}-${{ github.ref == 'refs/heads/main' && github.run_number \|\| github.ref }}
	cancel-in-progress: true

	permissions:
	id-token: write
	contents: read

	defaults:
	run:
	shell: bash -l -eo pipefail {0}

	jobs:
	gpu_test:
	if: github.repository_owner == 'meta-pytorch'
	runs-on: linux.g5.12xlarge.nvidia.gpu
	strategy:
	matrix:
	python-version: ['3.10']
	steps:
	- name: Check out repo
	uses: actions/checkout@v4
	- name: Setup conda env
	uses: conda-incubator/setup-miniconda@v2
	with:
	auto-update-conda: true
	miniconda-version: "latest"
	activate-environment: test
	python-version: ${{ matrix.python-version }}
	- name: Update pip
	run: python -m pip install --upgrade pip
	- name: Install torch nightly
	run: python -m pip install torch --extra-index-url https://download.pytorch.org/cu128
	- name: Install torchtitan and torchstore
	run: python -m pip install torchtitan torchstore
	- name: Download and install monarch
	run: pip install monarch --index-url https://download.pytorch.org/whl/preview/forge
	- name: Download and install vLLM
	run: pip install vllm --index-url https://download.pytorch.org/whl/preview/forge
	- name: Run unit tests with coverage
	# TODO add all tests
	run: pytest tests/unit_tests --cov=. --cov-report=xml --durations=20 -vv
	- name: Upload Coverage to Codecov
	uses: codecov/codecov-action@v3

Provide feedback