support more model in piecewise cuda graph (#11745)
This commit is contained in:
@@ -44,6 +44,18 @@ class TestPiecewiseCudaGraphCorrectness(CustomTestCase):
|
||||
metrics = run_eval(args)
|
||||
self.assertGreaterEqual(metrics["score"], 0.235)
|
||||
|
||||
def test_mmlu(self):
|
||||
args = SimpleNamespace(
|
||||
base_url=self.base_url,
|
||||
model=self.model,
|
||||
eval_name="mmlu",
|
||||
num_examples=64,
|
||||
num_threads=32,
|
||||
)
|
||||
|
||||
metrics = run_eval(args)
|
||||
self.assertGreaterEqual(metrics["score"], 0.65)
|
||||
|
||||
|
||||
class TestPiecewiseCudaGraphBenchmark(CustomTestCase):
|
||||
|
||||
|
||||
Reference in New Issue
Block a user