Patrice Vignola 3482180ec2 DML EP add a registration for Shape and Size (#13442) ... ### Description Add a DML registration for Shape to avoid copying back to the CPU just to get the shape of a GPU tensor. ### Motivation and Context When using free dimensions, many Transformers models extensively use the `Shape` operator. This causes hundreds of GPU->CPU copy that should be completely avoidable. Note that this change also uses the same heuristics as other providers (e.g. CUDA) to force some tensors on the CPU in certain situations. Co-authored-by: Patrice Vignola <pavignol@microsoft.com>		2022-11-08 19:29:37 -08:00
..
c_cxx
execution_providers/images
images
python	Bumping up version number to 1.14.0 on main branch (#13401)	2022-10-21 19:16:44 -04:00
ABI_Dev_Notes.md	skip windows GPU check if changes only in doc (#13248)	2022-10-11 13:51:44 +08:00
Android_testing.md
C_API_Guidelines.md
cmake_guideline.md
Coding_Conventions_and_Standards.md
ContribOperators.md	QuickGelu Fusion (#12417)	2022-10-28 18:12:07 +08:00
FAQ.md
How_To_Update_ONNX_Dev_Notes.md
Memory_Optimizer.md	Add guidelines for ORTModule (#13553)	2022-11-04 19:42:10 +08:00
Model_Test.md
NotesOnThreading.md
ONNX_Runtime_Server_Usage.md
onnxruntime_dependencies.dot
onnxruntime_dependencies.png
onnxruntime_extensions.md
OperatorKernels.md	DML EP add a registration for Shape and Size (#13442)	2022-11-08 19:29:37 -08:00
ORT_Format_Update_in_1.13.md
ORTMobilePackageOperatorTypeSupport.md
ORTModule_Training_Guidelines.md	Add guidelines for ORTModule (#13553)	2022-11-04 19:42:10 +08:00
PR_Guidelines.md
Privacy.md
Python_Dev_Notes.md
Reduced_Operator_Kernel_build.md
ReleaseManagement.md
Roadmap.md
Server.md
TVM_EP.md
Versioning.md
WinML_principles.md