onnxruntime/include/onnxruntime/core
Scott McKay c02ae61cab
Make kernel hash stable in type reduced build (#6603)
* Add infrastructure so that a kernel definition has the full list of supported types and a list of types enabled in this build. We need to use the full list when calculating the kernel hash so that the hash value in an ORT format model is stable across builds with and without type reduction enabled.
2021-02-09 12:00:08 +10:00
..
common Remove condition from ORT_RETURN_IF[_NOT] macro output. (#6563) 2021-02-05 17:33:29 -08:00
framework Make kernel hash stable in type reduced build (#6603) 2021-02-09 12:00:08 +10:00
graph Let execution fall back to CPU EP if Compile of a partition on current EP fails (#6580) 2021-02-05 12:14:55 -08:00
optimizer Expose recompute configs to the frontend (#5318) 2020-10-02 09:49:47 -07:00
platform Cast Op performance fix. (#6509) 2021-02-04 14:52:37 -08:00
providers [CoreML EP] Add CI for CoreML EP (macOS) and add coreml_flags for EP options (#6481) 2021-01-28 12:25:46 -08:00
session [Mult-GPU inferencing] Add new API to get/set device id. Set correct device id in cuda allocator. (#6592) 2021-02-08 08:59:18 -08:00