mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-07-21 19:18:55 +00:00
2fed37c8eb
* Outputs from model execution should always be returned in a newly allocated buffer or an pre-allocated buffer provided in fetches. When an initializer is providing a graph output (e.g. constant folding may result in this) we were returning an OrtValue that pointed to the initializer and not a separately allocated buffer with a copy. This was wrong as: - value wasn't returned in a pre-allocated fetch so whilst the value returned was correct, it was returned in the wrong place - user could alter the data in the initializer via the returned value * Add unit test with and without pre-allocated fetch. * Add some extra info around why we're handling this special case. |
||
|---|---|---|
| .. | ||
| cuda | ||
| allocation_planner_test.cc | ||
| allocator_test.cc | ||
| bfc_arena_test.cc | ||
| data_types_test.cc | ||
| distance_test.cc | ||
| dummy_allocator.cc | ||
| dummy_allocator.h | ||
| dummy_provider.cc | ||
| dummy_provider.h | ||
| endian_test.cc | ||
| execution_frame_test.cc | ||
| float_16_test.cc | ||
| inference_session_test.cc | ||
| insert_cast_transformer_test.cc | ||
| kernel_registry_test.cc | ||
| local_kernel_registry_test.cc | ||
| math_test.cc | ||
| mem_pattern_planner_test.cc | ||
| memcpy_transformer_test.cc | ||
| model_builder_utils.h | ||
| opaque_kernels_test.cc | ||
| parallel_executor_test.cc | ||
| random_test.cc | ||
| session_state_test.cc | ||
| shape_inference_test.cc | ||
| sparse_kernels_test.cc | ||
| tensor_test.cc | ||
| tensorutils_test.cc | ||
| test_main.cc | ||
| test_tensor_loader.cc | ||
| test_utils.cc | ||
| test_utils.h | ||
| TestAllocatorManager.cc | ||
| TestAllocatorManager.h | ||