RandySheriffH 8e610f25d8 Implement lite custom op API (#15778) ... Implement a set of new APIs for lightweight custom ops registration, to save efforts from schema-composing. A few highlights: - Support build-time type inference; - Support function-as-op for "stateless" ops; - Support structure-as-op for "stateful" ops; - Support varied input/output forms such as span, scalar, and tensors, either optional or non-optional. --------- Co-authored-by: Randy Shuai <rashuai@microsoft.com>		2023-05-04 09:49:17 -07:00
..
cuda_ops.cu
custom_op_utils.cc	Create a new C API KernelContext_GetAllocator() for Custom Op scenario (#15591)	2023-04-23 21:54:35 -07:00
custom_op_utils.h	Single-schema-multi-kernel (#15184)	2023-04-27 13:39:59 -07:00
fns_candy_style_transfer.c
onnx_protobuf.h
test_allocator.cc	Run clang-format in CI (#15524)	2023-04-18 09:26:58 -07:00
test_fixture.h	Run clang-format in CI (#15524)	2023-04-18 09:26:58 -07:00
test_inference.cc	Implement lite custom op API (#15778)	2023-05-04 09:49:17 -07:00
test_io_types.cc	Run clang-format in CI (#15524)	2023-04-18 09:26:58 -07:00
test_model_loading.cc	Run clang-format in CI (#15524)	2023-04-18 09:26:58 -07:00
test_nontensor_types.cc	Run clang-format in CI (#15524)	2023-04-18 09:26:58 -07:00
test_ort_format_models.cc
test_run_options.cc
test_session_options.cc
utils.cc
utils.h