llama.cpp
652d559e - llama : move the graph node budget into the model classes (#32648)

Commit
1 day ago
llama : move the graph node budget into the model classes (#32648) graph_max_nodes() picked the nodes-per-tensor factor from lists of architectures. Each model class now gives it through a new virtual, llama_model::graph_nodes_per_tensor(), which defaults to 8. The architectures that need 32 or 64 override it in models.h, and DFlash keeps its hparams-based rule in dflash.cpp. LoRA adapter nodes are now added for every architecture, not only for the ones on the default factor.
Author
Parents
Loading