A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 14, 23:45 UTC
[CI/Build] Fix plugin tests (#21758)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Cyrus Leung committed
Jul 28, 2025 at 23:08 UTC
04fe61aa3d4133aaf5e76c9fc9450a06eb9fddc5
1 file changed
+1
-4
tests/models/test_oot_registration.py
+1
-4
@@ -15,13 +15,10 @@ def test_plugin(
15
monkeypatch: pytest.MonkeyPatch,
16
dummy_opt_path: str,
17
):
18
- # V1 shuts down rather than raising an error here.
18
with monkeypatch.context() as m:
20
- m.setenv("VLLM_USE_V1", "0")
19
m.setenv("VLLM_PLUGINS", "")
20
23
- match = "Cannot find model module"
24
- with pytest.raises(ValueError, match=match):
21
+ with pytest.raises(ValueError, match="are not supported for now"):
22
LLM(model=dummy_opt_path, load_format="dummy")
23
24