onnxruntime

Enable direct tensorization and detensorization to many buffers in WinML (#5791)

* switch to work PC

* back with iterable of buffers

* add raw api tests

* tensorization

* last test

* all tests pass!

* small cleanup

* whitespace

* newline

* whitespace

* refactor common code into DisjointBufferHelpers

* remove unused file

* warning

* skip gpu tests when hardware not available

* Add error condition when createreference is invoked

* add null check to cretereference

* uncomment out check

Co-authored-by: Sheil Kumar <sheilk@microsoft.com>