[feat: Benchmarking Workflow] add stuff for a benchmarking workflow #42

	name: Benchmarking tests

	on:
	pull_request:
	branches:
	- main
	push:
	branches:
	- ci-*

	env:
	DIFFUSERS_IS_CI: yes
	HF_HOME: /mnt/cache
	OMP_NUM_THREADS: 8
	MKL_NUM_THREADS: 8

	jobs:
	torch_pipelines_cuda_benchmark_tests:
	name: Torch Core Pipelines CUDA Benchmarking Tests
	strategy:
	fail-fast: false
	max-parallel: 1
	runs-on: docker-gpu
	container:
	image: diffusers/diffusers-pytorch-cuda
	options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --gpus 0
	steps:
	- name: Checkout diffusers
	uses: actions/checkout@v3
	with:
	fetch-depth: 2
	- name: NVIDIA-SMI
	run: \|
	nvidia-smi
	- name: Install dependencies
	run: \|
	apt-get update && apt-get install libsndfile1-dev libgl1 -y
	python -m pip install -e .[quality,test]
	python -m pip install git+https://github.com/huggingface/accelerate.git
	python -m pip install pandas
	- name: Environment
	run: \|
	python utils/print_env.py
	- name: Stable Diffusion Benchmarking Tests
	env:
	HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
	BASE_PATH: benchmark_outputs
	run: \|
	cd benchmarks && mkdir ${BASE_PATH} && \
	python benchmark_sd.py && python benchmark_sd.py --run_compile && \
	python benchmark_sd_img.py && python benchmark_sd_img.py --run_compile && \
	python benchmark_sd_inpainting.py && python benchmark_sd_inpainting.py --run_compile && \
	python push_results.py

	- name: Test suite reports artifacts
	if: ${{ always() }}
	uses: actions/upload-artifact@v2
	with:
	name: benchmark_test_reports
	path: benchmarks/benchmark_outputs

Provide feedback