nv-torch-nightly-v100 #137

	name: nv-torch-nightly-v100

	on:
	workflow_dispatch:
	schedule:
	- cron: "0 0 * * *"

	concurrency:
	group: ${{ github.workflow }}-${{ github.ref }}
	cancel-in-progress: true

	permissions:
	contents: read
	issues: write

	jobs:
	unit-tests:
	runs-on: [self-hosted, nvidia, cu117, v100]

	steps:
	- uses: actions/checkout@v4

	- id: setup-venv
	uses: ./.github/workflows/setup-venv

	- name: Install pytorch
	run: \|
	pip install --pre torch torchvision --index-url https://download.pytorch.org/whl/nightly/cu118
	python -c "import torch; print('torch:', torch.__version__, torch)"
	python -c "import torch; print('CUDA available:', torch.cuda.is_available())"

	- name: Install transformers
	run: \|
	git clone https://github.com/huggingface/transformers
	cd transformers
	# if needed switch to the last known good SHA until transformers@master is fixed
	# git checkout 1cc453d33
	git rev-parse --short HEAD
	pip install .

	- name: Install deepspeed
	run: \|
	pip install .[dev,1bit,autotuning]
	ds_report

	- name: Python environment
	run: \|
	pip list

	- name: Unit tests
	run: \|
	unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
	cd tests
	pytest $PYTEST_OPTS --forked -n 4 unit/
	pytest $PYTEST_OPTS --forked -m 'sequential' unit/

	- name: Open GitHub issue if nightly CI fails
	if: ${{ failure() && (github.event_name == 'schedule') }}
	uses: JasonEtco/create-an-issue@v2
	env:
	GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
	with:
	filename: .github/ISSUE_TEMPLATE/ci_failure_report.md
	update_existing: true

Provide feedback