This commit is contained in:
Lianmin Zheng
2025-08-09 16:00:10 -07:00
committed by GitHub
parent a886564a18
commit ef48d5547e
9 changed files with 120 additions and 75 deletions

View File

@@ -56,7 +56,7 @@ class TestBenchServing(CustomTestCase):
f"### test_offline_throughput_non_stream_small_batch_size\n"
f"Output throughput: {res['output_throughput']:.2f} token/s\n"
)
self.assertGreater(res["output_throughput"], 1050)
self.assertGreater(res["output_throughput"], 1045)
def test_offline_throughput_without_radix_cache(self):
res = run_bench_serving(