llama.cpp

86f5623d - llama : fix MiniCPM inference after Granite Four changes (#14850)

llama : fix MiniCPM inference after Granite Four changes (#14850) MiniCPM models use the llm_build_granite constructor which was changed in the Granite Four PR to use hparams.rope_finetuned instead of a use_rope parameter. MiniCPM models need rope enabled by default. Fixes inference from gibberish to correct responses.