Enable overlap by default (#2067)

This commit is contained in:
Lianmin Zheng
2024-11-19 22:07:58 -08:00
committed by GitHub
parent 699384cb01
commit 7d671e4ad2
17 changed files with 92 additions and 75 deletions

View File

@@ -97,8 +97,8 @@ class TestBenchServing(unittest.TestCase):
if is_in_ci():
self.assertLess(res["median_e2e_latency_ms"], 12000)
self.assertLess(res["median_ttft_ms"], 80)
self.assertLess(res["median_itl_ms"], 11)
self.assertLess(res["median_ttft_ms"], 86)
self.assertLess(res["median_itl_ms"], 10)
def test_moe_offline_throughput_default(self):
res = run_bench_serving(