Add t4 for llm perf leaderboard #340

	name: CLI CUDA Py-TXI Tests

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

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

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

	steps:
	- name: Checkout
	uses: actions/checkout@v4

	- name: Set up Python 3.10
	uses: actions/setup-python@v5
	with:
	python-version: "3.10"

	- name: Install requirements
	run: \|
	pip install --upgrade pip
	pip install -e .[testing,py-txi]

	- name: Run tests
	run: pytest -s -k "cli and cuda and py_txi"

Provide feedback