[NPU] Model marshalling: fallback to copying weights for all unhandled Constant nodes

[razvanapetroaie]

Details:

• The new model marshalling algorithm is not handling subgraphs properly. See this code passage: the attribute is added only on ov::Constant nodes found at depth level one. Models within models, which may be registered as "subgraph operators" (e.g. TensorIterator) are omitted. In this current state, the attribute is required on all constant nodes, otherwise the run will fail at the deserialization stage.
• As a temporary fix to unblock this PR, all constant nodes that have been omitted will have their weights copied in a separate buffer. We may consider this a safety measure for now, with no real impact on performance. The impact can be great if, say, a model has a huge submodel within it, but the data we've gathered so far suggests these cases are not frequent (none of our models from the CI validation jobs use this feature).

Tickets:

• CVS-177414