minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[Test] Consolidate eval accuracy test mixins into eval_accuracy_kit (#21047)

Browse Source
This commit is contained in:
Liangsheng Yin
2026-03-26 14:26:46 -07:00
committed by GitHub
parent e5dd411f64
commit fb90c9d298
25 changed files with 276 additions and 377 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/registered/core/test_cpp_radix_cache.py
+6 -16
View File
@@ -1,10 +1,9 @@
import unittest
from types import SimpleNamespace
from sglang.srt.environ import envs
from sglang.srt.utils import kill_process_tree
from sglang.test.ci.ci_register import register_cuda_ci
from sglang.test.run_eval import run_eval
from sglang.test.kits.eval_accuracy_kit import MMLUMixin
from sglang.test.test_utils import (
DEFAULT_MODEL_NAME_FOR_TEST,
DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
@@ -17,7 +16,11 @@ from sglang.test.test_utils import (
register_cuda_ci(est_time=60, suite="nightly-1-gpu", nightly=True)
class TestCppRadixCache(CustomTestCase):
class TestCppRadixCache(CustomTestCase, MMLUMixin):
mmlu_score_threshold = 0.65
mmlu_num_examples = 64
mmlu_num_threads = 32
@classmethod
def setUpClass(cls):
envs.SGLANG_EXPERIMENTAL_CPP_RADIX_TREE.set(True)
@@ -33,19 +36,6 @@ class TestCppRadixCache(CustomTestCase):
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()
test/registered/core/test_page_size.py
+6 -15
View File
@@ -1,10 +1,9 @@
import os
import unittest
from types import SimpleNamespace
from sglang.srt.utils import kill_process_tree
from sglang.test.ci.ci_register import register_amd_ci, register_cuda_ci
from sglang.test.run_eval import run_eval
from sglang.test.kits.eval_accuracy_kit import MMLUMixin
from sglang.test.test_utils import (
DEFAULT_MODEL_NAME_FOR_TEST,
DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
@@ -17,7 +16,11 @@ register_cuda_ci(est_time=60, suite="stage-b-test-1-gpu-small")
register_amd_ci(est_time=60, suite="stage-b-test-1-gpu-small-amd")
class TestPageSize(CustomTestCase):
class TestPageSize(CustomTestCase, MMLUMixin):
mmlu_score_threshold = 0.65
mmlu_num_examples = 64
mmlu_num_threads = 32
@classmethod
def setUpClass(cls):
os.environ["SGLANG_DEBUG_MEMORY_POOL"] = "1"
@@ -34,18 +37,6 @@ class TestPageSize(CustomTestCase):
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)
self.assertGreaterEqual(metrics["score"], 0.65)
if __name__ == "__main__":
unittest.main()