Added test llama-2-7b with GPTQ quant. scheme #150

	name: CLI TensorRT OnnxRuntime 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:
	build_image_and_run_cli_tensorrt_onnxruntime_tests:
	runs-on: [single-gpu, nvidia-gpu, a10, ci]

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

	- name: Build image
	run: docker build
	--file docker/tensorrt.dockerfile
	--build-arg USER_ID=$(id -u)
	--build-arg GROUP_ID=$(id -g)
	--tag opt-bench-tensorrt:latest
	.

	- name: Run tests
	run: docker run
	--rm
	--gpus all
	--pid host
	--shm-size 64G
	--env USE_CUDA="1"
	--env PROCESS_SPECIFIC_VRAM="0"
	--volume $(pwd):/workspace/optimum-benchmark
	--workdir /workspace/optimum-benchmark
	--entrypoint /bin/bash
	opt-bench-tensorrt:latest
	-c "pip install -e .[testing,onnxruntime-gpu,diffusers,timm] && pytest -k 'cli and tensorrt and onnxruntime' -x"

Provide feedback