Edward Chen a71f7d3339 [NNAPI EP] Add some support for MatMul with batch inputs (#12261) ... MatMul allows multiplying batches of matrices. This change enables limited support of batch inputs in the NNAPI EP. Some limitations: - Broadcasting is not supported. A and B must have the same leading dimensions. - Only float inputs are supported. QDQ MatMul or QLinearMatMul with batch inputs is not supported yet. Note that NNAPI's ANEURALNETWORKS_BATCH_MATMUL is pretty much what we need, but it is only available from NNAPI feature level 6. This change composes a bunch of NNAPI operations to achieve a similar result but this is not ideal.		2022-07-22 11:21:45 -07:00
..
contrib_ops	Fix a bug in beam search custom attention mask allocation (#12240)	2022-07-20 23:42:54 -07:00
core	[NNAPI EP] Add some support for MatMul with batch inputs (#12261)	2022-07-22 11:21:45 -07:00
gsl
python	fix bug: output of Concat is quantized twice in qdq format (#12254)	2022-07-21 14:55:47 -07:00
test	[NNAPI EP] Add some support for MatMul with batch inputs (#12261)	2022-07-22 11:21:45 -07:00
tool/etw
wasm	EP factory creation cleanup and enhancements. (#11798)	2022-06-16 07:01:41 +10:00
__init__.py
ReformatSource.ps1
ReformatSourcePython.bat
VSCodeCoverage.runsettings