feat(backend): add vllm support #513

	name: CI

	on:
	pull_request:
	branches: [ main ]

	jobs:
	test:
	runs-on: macos-15
	strategy:
	matrix:
	python-version: ['3.11']

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

	- name: Set up Python ${{ matrix.python-version }}
	uses: actions/setup-python@v4
	with:
	python-version: ${{ matrix.python-version }}

	- name: Cache pip dependencies
	uses: actions/cache@v3
	with:
	path: ~/.cache/pip
	key: ${{ runner.os }}-pip-${{ matrix.python-version }}-${{ hashFiles('pyproject.toml') }}
	restore-keys: \|
	${{ runner.os }}-pip-${{ matrix.python-version }}-
	${{ runner.os }}-pip-

	- name: Install dependencies
	run: \|
	python -m pip install --upgrade pip
	pip install -e '.[mac, dev]'

	- name: Run tests
	run: pytest tests/ -v --cov=src/parallax --cov-report=xml

	- name: Upload coverage to Codecov
	uses: codecov/codecov-action@v3
	with:
	file: ./coverage.xml
	fail_ci_if_error: false

	- name: Run E2E tests
	run: \|
	python src/parallax/launch.py \
	--model-path Qwen/Qwen3-0.6B-MLX-bf16 \
	--max-num-tokens-per-batch 16384 \
	--kv-block-size 1024 \
	--max-batch-size 128 \
	--start-layer 0 \
	--end-layer 28 &
	PID=$!
	sleep 60
	curl --location 'http://localhost:3000/v1/chat/completions' --header 'Content-Type: application/json' --data '{
	"messages": [
	{
	"role": "user",
	"content": "What is the capital of France"
	}
	],
	"stream": false,
	"max_tokens": 1024,
	"chat_template_kwargs": {"enable_thinking": false},
	"sampling_params": {
	"top_k": 3
	}
	}'
	kill $PID 2>/dev/null \|\| true
	wait $PID 2>/dev/null \|\| echo -e "\nE2E test completed after 60 seconds"

Provide feedback