nv-h100 #139

	name: nv-h100

	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, h100]
	container:
	image: nvcr.io/nvidia/pytorch:23.03-py3
	ports:
	- 80
	options: --gpus all --shm-size "8G"

	steps:
	- uses: actions/checkout@v4

	- name: Check container state
	run: \|
	nvidia-smi
	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
	git rev-parse --short HEAD
	python -m pip install .

	- name: Install deepspeed
	run: \|
	python -m pip install docutils==0.18.1 jinja2==3.0 urllib3==1.26.11 ninja
	python -m pip install .[dev,1bit,autotuning]
	ds_report

	- name: Python environment
	run: \|
	python -m pip list

	- name: Unit tests
	run: \|
	unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
	cd tests
	python -m pytest $PYTEST_OPTS -n 4 unit/ --torch_ver="2.0" --cuda_ver="12"
	python -m pytest $PYTEST_OPTS -m 'sequential' unit/ --torch_ver="2.0" --cuda_ver="12"

	- 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