Report committed workspace estimates after graph partitioning
Move workspace reporting out of GetCapabilityForEP and into the completed
GraphPartitioner::Partition boundary. Track workspace estimates as pending during
capability probing and commit them only for nodes that ORT actually assigns.
Replace the generic safety-margin workspace with the MatMulNBits Level-1
estimate before CUDA's budget decision. Preserve workspace estimates across the
layout-transformation deferred-commit path, and report non-workspace, workspace,
and total estimated memory once per resource-accounted EP.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Copilot-Session: cdd38fe6-fcf3-45c2-acea-b8e6206a7839