Add llama.cpp backend #369

	name: CLI CUDA Pytorch Single-GPU Tests

	on:
	workflow_dispatch:
	push:
	branches:
	- main
	paths:
	- .github/workflows/test_cli_cuda_pytorch_single_gpu.yaml
	- "optimum_benchmark/**"
	- "docker/**"
	- "tests/**"
	- "setup.py"
	pull_request:
	branches:
	- main
	paths:
	- .github/workflows/test_cli_cuda_pytorch_single_gpu.yaml
	- "optimum_benchmark/**"
	- "docker/**"
	- "tests/**"
	- "setup.py"

	concurrency:
	cancel-in-progress: true
	group: ${{ github.workflow }}-${{ github.event.pull_request.number \|\| github.ref }}

	env:
	IMAGE: ghcr.io/huggingface/optimum-benchmark:latest-cuda

	jobs:
	run_cli_cuda_pytorch_single_gpu_tests:
	runs-on: [single-gpu, nvidia-gpu, a10, ci]

	steps:
	- name: Checkout
	uses: actions/checkout@v3

	- name: Run tests
	uses: addnab/docker-run-action@v3
	with:
	image: ${{ env.IMAGE }}
	options: \|
	--rm
	--gpus all
	--shm-size 64G
	--env MKL_THREADING_LAYER=GNU
	--volume ${{ github.workspace }}:/workspace
	--workdir /workspace
	run: \|
	pip install -e .[testing,diffusers,timm,peft,bitsandbytes,autoawq,auto-gptq]
	pytest -x -s -k "cli and cuda and pytorch and not (dp or ddp or device_map or deepspeed) and not (awq)"

Provide feedback