ggml-cuda : support stablelm rope (#4156)
* ggml-cuda : support stablelm rope
* remove unused freq_base kernel parameter
* add n_dims parameter to llm_build_k_shift, default to n_rot via overload
* llama : fix llm_build_k_shift args
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
