Add V2-lite model test (#7390)

Co-authored-by: DiweiSun <105627594+DiweiSun@users.noreply.github.com>
2025-07-03 22:25:50 -07:00
parent 8b1942c6cc
commit 4de0395343
6 changed files with 98 additions and 6 deletions
@@ -67,7 +67,7 @@ class TestFlashMLAAttnBackend(unittest.TestCase):

 class TestFlashMLAAttnLatency(unittest.TestCase):
    def test_latency(self):
-        output_throughput = run_bench_one_batch(
+        _, output_throughput, _ = run_bench_one_batch(
            DEFAULT_MODEL_NAME_FOR_TEST_MLA,
            [
                "--attention-backend",