onnxruntime

0180c042 - Fix DML regression from allocator refactor and enable unrounded weight allocation in ORT API (#17030)

Fix DML regression from allocator refactor and enable unrounded weight allocation in ORT API (#17030) This addresses a DML performance regression from the following PR resulting in allocations not being rounded and pooled in the DML execution provider. https://github.com/microsoft/onnxruntime/pull/15833 This also fixes a pre-existing limitation that allocations during session initialization (primarily large weights and persistent resources) only bypassed rounding and pooling while using the Winml API. The allocator now also respects a caller's rounding mode parameter when provided.