Add V2-lite model test (#7390)

Co-authored-by: DiweiSun <105627594+DiweiSun@users.noreply.github.com>
This commit is contained in:
YanbingJiang
2025-07-04 13:25:50 +08:00
committed by GitHub
parent 8b1942c6cc
commit 4de0395343
6 changed files with 98 additions and 6 deletions

View File

@@ -20,7 +20,7 @@ from sglang.test.test_utils import (
class TestBenchOneBatch(CustomTestCase):
def test_bs1_small(self):
output_throughput = run_bench_one_batch(
_, output_throughput, _ = run_bench_one_batch(
DEFAULT_SMALL_MODEL_NAME_FOR_TEST, ["--cuda-graph-max-bs", "2"]
)
self.assertGreater(output_throughput, 50)