llama.cpp

f445c0e6 - llama : fix llm_build_k_shift to use correct n_rot (#4889)

llama : fix llm_build_k_shift to use correct n_rot (#4889) * llama : fix llm_build_k_shift to use correct n_rot ggml-ci * llama : always use hparams.n_rot for ggml_rope_custom ggml-ci * convert : fix persimmon conversion to write correct n_rot