# SPDX-License-Identifier: Apache-2.0 # SPDX-FileCopyrightText: Copyright contributors to the vLLM project import openai # use the official client for correctness check import pytest import pytest_asyncio from tests.utils import RemoteOpenAIServer # any model with a chat template should work here MODEL_NAME = "Qwen/Qwen3-0.6B" @pytest.fixture(scope="module") def server(): args = [ # use half precision for speed and memory savings in CI environment "--dtype", "bfloat16", "--max-model-len", "8192", "--enforce-eager", "--max-num-seqs", "128", ] with RemoteOpenAIServer(MODEL_NAME, args) as remote_server: yield remote_server @pytest_asyncio.fixture async def client(server): async with server.get_async_client() as async_client: yield async_client @pytest.mark.asyncio async def test_check_models(client: openai.AsyncOpenAI): models = await client.models.list() models = models.data served_model = models[0] assert served_model.id == MODEL_NAME assert served_model.root == MODEL_NAME