mirror of
https://github.com/vllm-project/vllm.git
synced 2026-08-18 19:50:17 +00:00
c89d692cb5
Signed-off-by: Bugen Zhao <[email protected]> Co-authored-by: Nick Hill <[email protected]> Co-authored-by: Andreas Karatzas <[email protected]>
48 lines
1.3 KiB
Python
48 lines
1.3 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
|
|
from tempfile import TemporaryDirectory
|
|
|
|
import httpx
|
|
import pytest
|
|
|
|
from vllm import envs
|
|
from vllm.version import __version__ as VLLM_VERSION
|
|
|
|
from ...utils import RemoteOpenAIServer
|
|
|
|
MODEL_NAME = "Qwen/Qwen3-0.6B"
|
|
|
|
|
|
@pytest.fixture(scope="module")
|
|
def server():
|
|
with TemporaryDirectory() as tmpdir:
|
|
args = [
|
|
# use half precision for speed and memory savings in CI environment
|
|
"--dtype",
|
|
"bfloat16",
|
|
"--max-model-len",
|
|
"8192",
|
|
"--enforce-eager",
|
|
"--max-num-seqs",
|
|
"128",
|
|
"--uds",
|
|
f"{tmpdir}/vllm.sock",
|
|
]
|
|
|
|
with RemoteOpenAIServer(MODEL_NAME, args) as remote_server:
|
|
yield remote_server
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_show_version(server: RemoteOpenAIServer):
|
|
transport = httpx.HTTPTransport(uds=server.uds)
|
|
client = httpx.Client(transport=transport)
|
|
response = client.get(server.url_for("version"))
|
|
response.raise_for_status()
|
|
|
|
payload = response.json()
|
|
assert payload["version"] == VLLM_VERSION
|
|
if envs.VLLM_USE_RUST_FRONTEND:
|
|
assert payload["rust_frontend_version"] == VLLM_VERSION
|