| 1 | # SPDX-License-Identifier: Apache-2.0 |
| 2 | # SPDX-FileCopyrightText: Copyright contributors to the vLLM project |
| 3 | |
| 4 | from tempfile import TemporaryDirectory |
| 5 | |
| 6 | import httpx |
| 7 | import pytest |
| 8 | |
| 9 | from tests.utils import RemoteOpenAIServer |
| 10 | from vllm import envs |
| 11 | from vllm.version import __version__ as VLLM_VERSION |
| 12 | |
| 13 | MODEL_NAME = "Qwen/Qwen3-0.6B" |
| 14 | |
| 15 | |
| 16 | @pytest.fixture(scope="module") |
| 17 | def server(): |
| 18 | with TemporaryDirectory() as tmpdir: |
| 19 | args = [ |
| 20 | # use half precision for speed and memory savings in CI environment |
| 21 | "--dtype", |
| 22 | "bfloat16", |
| 23 | "--max-model-len", |
| 24 | "8192", |
| 25 | "--enforce-eager", |
| 26 | "--max-num-seqs", |
| 27 | "128", |
| 28 | "--uds", |
| 29 | f"{tmpdir}/vllm.sock", |
| 30 | ] |
| 31 | |
| 32 | with RemoteOpenAIServer(MODEL_NAME, args) as remote_server: |
| 33 | yield remote_server |
| 34 | |
| 35 | |
| 36 | @pytest.mark.asyncio |
| 37 | async def test_show_version(server: RemoteOpenAIServer): |
| 38 | transport = httpx.HTTPTransport(uds=server.uds) |
| 39 | client = httpx.Client(transport=transport) |
| 40 | response = client.get(server.url_for("version")) |
| 41 | response.raise_for_status() |
| 42 | |
| 43 | payload = response.json() |
| 44 | assert payload["version"] == VLLM_VERSION |
| 45 | if envs.VLLM_USE_RUST_FRONTEND: |
| 46 | assert payload["rust_frontend_version"] == VLLM_VERSION |