[Test] Start Llama tests on GPU #898

	name: Unit tests

	on:
	push:
	branches: [main]
	pull_request:
	branches: [main]
	workflow_dispatch:

	jobs:
	unit-tests:

	strategy:
	matrix:
	os: [ubuntu-latest, windows-latest, macos-latest]
	python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
	model: ["gpt2cpu", "phi2cpu", "hfllama7b"]

	runs-on: ${{ matrix.os }}
	steps:
	- uses: actions/checkout@v3
	- name: Set up Python ${{ matrix.python-version }}
	uses: actions/setup-python@v4
	with:
	python-version: ${{ matrix.python-version }}
	- name: Install dependencies
	shell: bash
	run: \|
	python -m pip install --upgrade pip
	pip install pytest
	pip install -e .[test]
	if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
	- name: Install model-specific dependencies
	run: \|
	pip install llama-cpp-python
	- name: Run tests (except server)
	run: \|
	pytest --cov=guidance --cov-report=xml --cov-report=term-missing --selected_model ${{ matrix.model }} -m "not server" ./tests/
	- name: Upload coverage reports to Codecov
	uses: codecov/codecov-action@v3
	with:
	token: ${{ secrets.CODECOV_TOKEN }}

Provide feedback