sglang_v0.5.2/sglang/test/srt/test_cpp_radix_cache.py

48 lines
1.2 KiB
Python

import os
import unittest
from types import SimpleNamespace
from sglang.srt.utils import kill_process_tree
from sglang.test.run_eval import run_eval
from sglang.test.test_utils import (
DEFAULT_MODEL_NAME_FOR_TEST,
DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
DEFAULT_URL_FOR_TEST,
CustomTestCase,
popen_launch_server,
)
class TestCppRadixCache(CustomTestCase):
@classmethod
def setUpClass(cls):
os.environ["SGLANG_EXPERIMENTAL_CPP_RADIX_TREE"] = "1"
cls.model = DEFAULT_MODEL_NAME_FOR_TEST
cls.base_url = DEFAULT_URL_FOR_TEST
cls.process = popen_launch_server(
cls.model,
cls.base_url,
timeout=DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
)
@classmethod
def tearDownClass(cls):
kill_process_tree(cls.process.pid)
def test_mmlu(self):
args = SimpleNamespace(
base_url=self.base_url,
model=self.model,
eval_name="mmlu",
num_examples=64,
num_threads=32,
)
metrics = run_eval(args)
print(metrics)
self.assertGreaterEqual(metrics["score"], 0.65)
if __name__ == "__main__":
unittest.main()