biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Convert formatting to use ruff instead of yapf + isort (#26247)

Browse Source 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2025-10-05 15:06:22 +01:00
committed by GitHub
parent 17edd8a807
commit d6953beb91
1508 changed files with 115244 additions and 94146 deletions
Download Patch File Download Diff File Expand all files Collapse all files

58
tests/entrypoints/openai/test_basic.py
View File

@@ -16,9 +16,9 @@ from ...utils import RemoteOpenAIServer
MODEL_NAME = "HuggingFaceH4/zephyr-7b-beta"
@pytest.fixture(scope='module')
@pytest.fixture(scope="module")
def server_args(request: pytest.FixtureRequest) -> list[str]:
""" Provide extra arguments to the server via indirect parametrization
"""Provide extra arguments to the server via indirect parametrization
Usage:
@@ -80,8 +80,10 @@ async def client(server):
"server_args",
[
pytest.param([], id="default-frontend-multiprocessing"),
pytest.param(["--disable-frontend-multiprocessing"],
id="disable-frontend-multiprocessing")
pytest.param(
["--disable-frontend-multiprocessing"],
id="disable-frontend-multiprocessing",
),
],
indirect=True,
)
@@ -97,8 +99,10 @@ async def test_show_version(server: RemoteOpenAIServer):
"server_args",
[
pytest.param([], id="default-frontend-multiprocessing"),
pytest.param(["--disable-frontend-multiprocessing"],
id="disable-frontend-multiprocessing")
pytest.param(
["--disable-frontend-multiprocessing"],
id="disable-frontend-multiprocessing",
),
],
indirect=True,
)
@@ -112,11 +116,13 @@ async def test_check_health(server: RemoteOpenAIServer):
@pytest.mark.parametrize(
"server_args",
[
pytest.param(["--max-model-len", "10100"],
id="default-frontend-multiprocessing"),
pytest.param(
["--max-model-len", "10100"], id="default-frontend-multiprocessing"
),
pytest.param(
["--disable-frontend-multiprocessing", "--max-model-len", "10100"],
id="disable-frontend-multiprocessing")
id="disable-frontend-multiprocessing",
),
],
indirect=True,
)
@@ -131,14 +137,16 @@ async def test_request_cancellation(server: RemoteOpenAIServer):
# Request about 2 million tokens
for _ in range(200):
task = asyncio.create_task(
client.chat.completions.create(messages=chat_input,
model=MODEL_NAME,
max_tokens=10000,
extra_body={"min_tokens": 10000}))
client.chat.completions.create(
messages=chat_input,
model=MODEL_NAME,
max_tokens=10000,
extra_body={"min_tokens": 10000},
)
)
tasks.append(task)
done, pending = await asyncio.wait(tasks,
return_when=asyncio.ALL_COMPLETED)
done, pending = await asyncio.wait(tasks, return_when=asyncio.ALL_COMPLETED)
# Make sure all requests were sent to the server and timed out
# (We don't want to hide other errors like 400s that would invalidate this
@@ -151,16 +159,15 @@ async def test_request_cancellation(server: RemoteOpenAIServer):
# If the server had not cancelled all the other requests, then it would not
# be able to respond to this one within the timeout
client = server.get_async_client(timeout=5)
response = await client.chat.completions.create(messages=chat_input,
model=MODEL_NAME,
max_tokens=10)
response = await client.chat.completions.create(
messages=chat_input, model=MODEL_NAME, max_tokens=10
)
assert len(response.choices) == 1
@pytest.mark.asyncio
async def test_request_wrong_content_type(server: RemoteOpenAIServer):
chat_input = [{"role": "user", "content": "Write a long story"}]
client = server.get_async_client()
@@ -169,17 +176,13 @@ async def test_request_wrong_content_type(server: RemoteOpenAIServer):
messages=chat_input,
model=MODEL_NAME,
max_tokens=10000,
extra_headers={
"Content-Type": "application/x-www-form-urlencoded"
})
extra_headers={"Content-Type": "application/x-www-form-urlencoded"},
)
@pytest.mark.parametrize(
"server_args",
[
pytest.param(["--enable-server-load-tracking"],
id="enable-server-load-tracking")
],
[pytest.param(["--enable-server-load-tracking"], id="enable-server-load-tracking")],
indirect=True,
)
@pytest.mark.asyncio
@@ -202,7 +205,8 @@ async def test_server_load(server: RemoteOpenAIServer):
# Start the completion request in a background thread.
completion_future = asyncio.create_task(
asyncio.to_thread(make_long_completion_request))
asyncio.to_thread(make_long_completion_request)
)
# Give a short delay to ensure the request has started.
await asyncio.sleep(0.1)