nv-torch19-v100 #1844

	name: nv-torch19-v100

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

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

	jobs:
	unit-tests:
	runs-on: [self-hosted, nvidia, cu111, v100]

	steps:
	- uses: actions/checkout@v3

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

	- name: Install pytorch
	run: \|
	pip install -U --cache-dir $TORCH_CACHE torch==1.9.0+cu111 torchvision==0.10.0+cu111 -f https://download.pytorch.org/whl/torch_stable.html
	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] --no-build-isolation
	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/ --torch_ver="1.9" --cuda_ver="11"
	pytest $PYTEST_OPTS --forked -m 'sequential' unit/ --torch_ver="1.9" --cuda_ver="11"

Provide feedback