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

[V0 Deprecation] Deprecate --disable-frontend-multiprocessing (#37612)

Browse Source 
Signed-off-by: sfeng33 <4florafeng@gmail.com>
This commit is contained in:
Flora Feng
2026-03-19 23:31:43 -04:00
committed by GitHub
parent 8fbe3f303f
commit 9040151fe1
10 changed files with 8 additions and 73 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
tests/entrypoints/instrumentator/test_basic.py
View File

@@ -28,7 +28,7 @@ def server_args(request: pytest.FixtureRequest) -> list[str]:
>>> @pytest.mark.parametrize(
>>> "server_args",
>>> [
>>> ["--disable-frontend-multiprocessing"],
>>> ["--max-model-len", "10100"],
>>> [
>>> "--model=NousResearch/Hermes-3-Llama-3.1-70B",
>>> "--enable-auto-tool-choice",
@@ -40,7 +40,7 @@ def server_args(request: pytest.FixtureRequest) -> list[str]:
>>> ...
This will run `test_foo` twice with servers with:
- `--disable-frontend-multiprocessing`
- `--max-model-len 10100`
- `--model=NousResearch/Hermes-3-Llama-3.1-70B --enable-auto-tool-choice`.
"""
@@ -79,17 +79,6 @@ async def client(server):
yield async_client
@pytest.mark.parametrize(
"server_args",
[
pytest.param([], id="default-frontend-multiprocessing"),
pytest.param(
["--disable-frontend-multiprocessing"],
id="disable-frontend-multiprocessing",
),
],
indirect=True,
)
@pytest.mark.asyncio
async def test_show_version(server: RemoteOpenAIServer):
response = requests.get(server.url_for("version"))
@@ -98,17 +87,6 @@ async def test_show_version(server: RemoteOpenAIServer):
assert response.json() == {"version": VLLM_VERSION}
@pytest.mark.parametrize(
"server_args",
[
pytest.param([], id="default-frontend-multiprocessing"),
pytest.param(
["--disable-frontend-multiprocessing"],
id="disable-frontend-multiprocessing",
),
],
indirect=True,
)
@pytest.mark.asyncio
async def test_check_health(server: RemoteOpenAIServer):
response = requests.get(server.url_for("health"))
@@ -119,13 +97,7 @@ async def test_check_health(server: RemoteOpenAIServer):
@pytest.mark.parametrize(
"server_args",
[
pytest.param(
["--max-model-len", "10100"], id="default-frontend-multiprocessing"
),
pytest.param(
["--disable-frontend-multiprocessing", "--max-model-len", "10100"],
id="disable-frontend-multiprocessing",
),
pytest.param(["--max-model-len", "10100"]),
],
indirect=True,
)