onnxruntime/onnxruntime/core
Suffian Khan 7196d4206f
Adding Transpose3d and Transpose4d special case kernels for Rocm (#5837)
* add transpose3d; seeing memory fault on rocm3.7

* cleaned up code; commit to switch machines

* tested working on gcr-openpai-35; 168 ex/sec

* remove debug HCC_ENABLE_PRINTF
2020-11-18 17:47:19 -08:00
..
codegen Add ability to filter GraphViewer using IndexedSubGraph. (#5614) 2020-11-04 07:08:18 +10:00
common Support multi-loop parallel sections, use multi-loop sections in GRU (#5602) 2020-11-10 12:24:57 +00:00
dll
flatbuffers Support for Sparse Initializers (#5540) 2020-10-27 10:32:06 -07:00
framework Prevent saving a model containing fused nodes as we don't have any way to save the compiled kernels so the saved model will be invalid. (#5840) 2020-11-18 16:17:07 +10:00
graph ORT fuzz testing (#5771) 2020-11-18 16:07:36 -08:00
language_interop_ops Change the OrtCustomOp invocation as a constant. (#5506) 2020-11-02 10:38:07 -08:00
mlas Add QLinearConv NHWC transformer (#5824) 2020-11-17 20:51:02 -08:00
optimizer Add QLinearConv NHWC transformer (#5824) 2020-11-17 20:51:02 -08:00
platform Remove Env::Task wrapper around std::function (#5753) 2020-11-10 20:22:07 +00:00
profile
protobuf
providers Adding Transpose3d and Transpose4d special case kernels for Rocm (#5837) 2020-11-18 17:47:19 -08:00
session Prevent saving a model containing fused nodes as we don't have any way to save the compiled kernels so the saved model will be invalid. (#5840) 2020-11-18 16:17:07 +10:00
util Quantize LSTM (#5595) 2020-11-18 11:21:49 -08:00