sglangv0.5.2 & support Qwen3-Next-80B-A3B-Instruct

This commit is contained in:
maxiao1
2025-09-13 17:00:20 +08:00
commit 118f1fc726
2037 changed files with 515371 additions and 0 deletions

View File

@@ -0,0 +1,35 @@
"""
Usage:
python3 -m unittest test_overlap_schedule.TestOverlapSchedule.test_radix_attention_chunked_prefill
python3 test_overlap_schedule.py
"""
import unittest
from sglang.test.test_utils import CustomTestCase, run_mmlu_test
class TestOverlapSchedule(CustomTestCase):
def test_no_radix_attention_chunked_prefill(self):
run_mmlu_test(
disable_radix_cache=True, chunked_prefill_size=32, disable_overlap=True
)
def test_no_radix_attention_no_chunked_prefill(self):
run_mmlu_test(
disable_radix_cache=True, chunked_prefill_size=-1, disable_overlap=True
)
def test_radix_attention_chunked_prefill(self):
run_mmlu_test(
disable_radix_cache=False, chunked_prefill_size=32, disable_overlap=True
)
def test_radix_attention_no_chunked_prefill(self):
run_mmlu_test(
disable_radix_cache=False, chunked_prefill_size=-1, disable_overlap=True
)
if __name__ == "__main__":
unittest.main()