Remove monkey_patch_vllm_dummy_weight_loader (#2064)
This commit is contained in:
@@ -13,7 +13,7 @@ class TestBenchLatency(unittest.TestCase):
|
||||
output_throughput = run_bench_latency(DEFAULT_MODEL_NAME_FOR_TEST, [])
|
||||
|
||||
if is_in_ci():
|
||||
assert output_throughput > 130, f"{output_throughput=}"
|
||||
self.assertGreater(output_throughput, 135)
|
||||
|
||||
def test_moe_default(self):
|
||||
output_throughput = run_bench_latency(
|
||||
@@ -21,7 +21,7 @@ class TestBenchLatency(unittest.TestCase):
|
||||
)
|
||||
|
||||
if is_in_ci():
|
||||
assert output_throughput > 125, f"{output_throughput=}"
|
||||
self.assertGreater(output_throughput, 125)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
Reference in New Issue
Block a user