onnxruntime/onnxruntime/core
2021-03-04 20:42:40 +10:00
..
codegen Add python 3.8/3.9 support for Windows GPU and Linux ARM64 (#6615) 2021-02-11 16:43:35 -08:00
common Add support for op kernel type control required types, require int64 for some ops (#6832) 2021-03-01 19:04:29 -08:00
dll
flatbuffers Add ability to track per operator types in reduced build config. (#6428) 2021-01-29 07:59:51 +10:00
framework Change OpKernel class to be shared with shared providers (#6837) 2021-03-02 00:53:48 -08:00
graph Update Attention and QAttention to support pruned model (#6819) 2021-02-27 09:50:16 -08:00
language_interop_ops
mlas Threading support for Hybrid core architecture (#6728) 2021-02-17 15:35:07 -08:00
optimizer Add comment (#6860) 2021-03-02 18:54:25 -08:00
platform Remove condition from ORT_RETURN_IF[_NOT] macro output. (#6563) 2021-02-05 17:33:29 -08:00
profile Pipeline Parallel Experimental Python API (#5815) 2021-01-15 12:07:28 +08:00
protobuf
providers Add check that the first 2 Loop subgraph inputs have an shape (could be explicit or inferred) as we need to know the rank the subgraph expects. Other inputs to the subgraph are more opaque so we can just pass them through. (#6891) 2021-03-04 20:42:40 +10:00
session Support optional inputs/outputs in custom op development (#6727) 2021-03-03 05:59:23 -08:00
util MLAS: improve quantized depthwise convolution (#6513) 2021-02-01 21:22:27 -08:00