[GPU] Fixed stateful KV cache issues + minor improvements

[vladimir-paramuzov]

Details:

• Fixed state initializer handling in shape inference of read_value primitive
• Added an exception for shape_of subgraphs markup for read_value to terminate mark propagation for this node
• Extended KV cache func tests for the cases with gather (from beam search) and state initializer subgraph
• Added output partial shape parameter for broadcast to have better compile-time shape inference and less dynamic dimensions if ngraph was able to propagate part of the dimensions and make those static