George Nash 93636cbd20 Reduce ops for DNNL ep (#10056) ... * Add Reduce Ops to DNNL ep Combine the Reduction ops into one class Add ReduceL1, ReduceL2, ReduceSum, ReduceMax, ReduceMin, and ReduceProd, ReduceSumSquare, ReduceLogSum, and ReduceLogSumExp Reduce code now also handles the keepdims attribute Also updated code to use HandleNegativeAxis function from the providers/common.h code instead of manually calculating. In code documentation exists to help explain complex reduction op code Add elementwise ops to Reduction op capability code removed keepdims check from the Reduction op capability code. Updated the error_tolerance for LogGrad(DNNL EP only) after finding a few instances that the tests were a little out of tolerance. Signed-off-by: George Nash <george.nash@intel.com> * Documentation cleanup in dnnl_qattention Cleaned up the Comments documenting the QAttention operator For some reason a bunch of new lines were introduced to the comment making it harder to read. Signed-off-by: George Nash <george.nash@intel.com>		2021-12-16 07:31:16 -08:00
..
orttraining	Reduce ops for DNNL ep (#10056)	2021-12-16 07:31:16 -08:00
pytorch_frontend_examples	Sync ORTModule branch with master and fix tests (#6526)	2021-02-02 08:59:56 -08:00
tools	Enable OneHot kernel for ROCm EP and add Dockerfile for ROCm 4.3.1 (#9656)	2021-12-07 12:47:00 -08:00