Files
sglang/test/srt/test_mla.py
Lianmin Zheng 4af3f889fc Simplify flashinfer indices update for prefill (#2074)
Co-authored-by: kavioyu <kavioyu@tencent.com>
Co-authored-by: kavioyu <kavioyu@gmail.com>
2024-11-18 00:02:36 -08:00

57 lines
1.4 KiB
Python

import unittest
from types import SimpleNamespace
from sglang.srt.utils import kill_child_process
from sglang.test.run_eval import run_eval
from sglang.test.test_utils import (
DEFAULT_MLA_MODEL_NAME_FOR_TEST,
DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
DEFAULT_URL_FOR_TEST,
popen_launch_server,
)
class TestMLA(unittest.TestCase):
@classmethod
def setUpClass(cls):
cls.model = DEFAULT_MLA_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,
other_args=["--tp", "2", "--trust-remote-code"],
)
@classmethod
def tearDownClass(cls):
kill_child_process(cls.process.pid, include_self=True)
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)
self.assertGreater(metrics["score"], 0.5)
def test_mgsm_en(self):
args = SimpleNamespace(
base_url=self.base_url,
model=self.model,
eval_name="mgsm_en",
num_examples=None,
num_threads=1024,
)
metrics = run_eval(args)
self.assertGreater(metrics["score"], 0.8)
if __name__ == "__main__":
unittest.main()