Refactor test configs and CI #25

	name: CLI CUDA TensorRT-LLM Tests

	on:
	workflow_dispatch:
	push:
	branches: [main]
	pull_request:
	types: [opened, reopened, synchronize]

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

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

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

	- name: Run tests
	run: docker run
	--rm
	--gpus all
	--shm-size 64G
	--env USE_CUDA="1"
	--env PROCESS_SPECIFIC_VRAM="0"
	--volume $(pwd):/workspace/optimum-benchmark
	--workdir /workspace/optimum-benchmark
	--entrypoint /bin/bash
	huggingface/optimum-nvidia:latest
	-c "pip install -e .[testing] && pip uninstall -y nvidia-ml-py &&
	pytest -s -v -k 'cli and tensorrt_llm' -x"

Provide feedback