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 4, 03:45 UTC
[Bugfix] Fix XPU/ROCm compatibility in spawn_new_process_for_each_test (#41895)
Signed-off-by: dqzhengAP <dqzheng1996@gmail.com>
David Zheng committed
May 7, 2026 at 21:47 UTC
1acd67a795ebccdf9b9db7697ae9082058301657
1 file changed
+2
-2
tests/v1/logits_processors/test_custom_online.py
+2
-2
@@ -10,7 +10,7 @@ import openai
10
import pytest
11
import pytest_asyncio
12
13
-from tests.utils import RemoteOpenAIServerCustom, create_new_process_for_each_test
13
+from tests.utils import RemoteOpenAIServerCustom
14
from tests.v1.logits_processors.utils import (
15
DUMMY_LOGITPROC_ARG,
16
DUMMY_LOGITPROC_FQCN,
@@ -119,7 +119,7 @@ api_keyword_args = {
119
}
120
121
122
-@create_new_process_for_each_test()
122
+@pytest.mark.asyncio
123
@pytest.mark.parametrize(
124
"model_name",
125
[MODEL_NAME],