Refactor prefill and inference benchmark #98

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

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

	- name: Pull image
	run: docker pull huggingface/optimum-nvidia:latest

	- name: Run tests
	uses: addnab/docker-run-action@v3
	with:
	image: huggingface/optimum-nvidia:latest
	options: \|
	--rm
	--gpus all
	--shm-size 64G
	--env MKL_THREADING_LAYER=GNU
	--volume ${{ github.workspace }}:/workspace
	--workdir /workspace
	run: \|
	pip install -e .[testing]
	pytest -x -s -k "cli and cuda and tensorrt_llm"

Provide feedback