onnxruntime

Fix prune_graph and gpt attention fusion scripts (#15147)

Fix two issues: (1) GPT attention fusion: get_parent could return None when the input is
initializer, add a check (2) ONNX node could have optional inputs and outputs. During
prune_graph, we shall exclude empty inputs/outputs. Here we exclude ""
from output_name_to_node and input_name_to_nodes.

Add an option allow_remove_graph_inputs in prune_graph