Graph Inputs Collection Changed in Llama.cpp to Stabilize Pipeline Parallelism

The official source reports this update: b11254: ggml : collect all input tensors into graph_inputs. ggml : collect all input tensors into graph_inputs ( #29634 ) graph_inputs was populated while splitting the graph, so it only contained the inputs that are used as srcs of some node. With pipeline parallelism (n_copies > 1), each graph input contributes n_copies leafs to graph_copy, so switching between batches that consume different inputs (e.g. token batches that do not use the embeddings input vs image batches that do) changed the graph composition.