ac2387279e
Co-authored-by: SangBin Cho <rkooo567@gmail.com> Co-authored-by: dhou-xai <dhou@x.ai> Co-authored-by: Hanming Lu <hanming_lu@berkeley.edu>
28 lines
767 B
Python
28 lines
767 B
Python
import unittest
|
|
|
|
from sglang.test.test_utils import (
|
|
DEFAULT_SMALL_MODEL_NAME_FOR_TEST,
|
|
DEFAULT_URL_FOR_TEST,
|
|
popen_launch_server,
|
|
)
|
|
|
|
|
|
class TestHealthCheck(unittest.TestCase):
|
|
def test_health_check(self):
|
|
"""Test that metrics endpoint returns data when enabled"""
|
|
with self.assertRaises(TimeoutError):
|
|
popen_launch_server(
|
|
DEFAULT_SMALL_MODEL_NAME_FOR_TEST,
|
|
DEFAULT_URL_FOR_TEST,
|
|
timeout=60,
|
|
other_args=[
|
|
"--disable-cuda-graph",
|
|
"--json-model-override-args",
|
|
'{"architectures": ["LlamaForCausalLMForHealthTest"]}',
|
|
],
|
|
)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|