MCPcopy Create free account
hub / github.com/NVIDIA/TensorRT-LLM / apply_patches

Function apply_patches

triton_backend/all_models/tests/test_python_backend.py:123–130  ·  view source on GitHub ↗
()

Source from the content-addressed store, hash-verified

121
122@pytest.fixture(autouse=True)
123def apply_patches():
124 patch("model.pb_utils.Tensor", new=MockTritonTensor).start()
125 patch("model.pb_utils.InferenceResponse", new=MockTritonResponse).start()
126 patch("model.pb_utils.TritonError", new=MockTritonError).start()
127 patch("model.pb_utils.InferenceRequest", new=MockTritonRequest).start()
128 patch("model.pb_utils.get_input_tensor_by_name",
129 new=mock_pb_utils_get_input_tensor_by_name_side_effect).start()
130 patch("model.pb_utils.TritonModelException", new=Exception).start()
131
132
133@pytest.fixture

Callers

nothing calls this directly

Calls 1

startMethod · 0.45

Tested by

no test coverage detected