onnxruntime/include/onnxruntime/core
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
..
common Run clang-format in CI (#15524) 2023-04-18 09:26:58 -07:00
eager Run clang-format in CI (#15524) 2023-04-18 09:26:58 -07:00
framework Remove onnxruntime_PYBIND_EXPORT_OPSCHEMA definition from onnxruntime (#15776) 2023-05-03 13:08:35 -07:00
graph [js/web] WebGPU backend via JSEP (#14579) 2023-04-24 15:21:18 -07:00
optimizer fix compilation error in no absl build (#15769) 2023-05-02 08:20:49 -07:00
platform Run clang-format in CI (#15524) 2023-04-18 09:26:58 -07:00
providers Bring back SLN cuda kernel and use provider options to switch to standard implementation (#15660) 2023-05-01 18:35:26 -07:00
session Implement lite custom op API (#15778) 2023-05-04 09:49:17 -07:00