CUDA: Fix non-contig rope (ggml-org#19338)

* Rename variables + fix rope_neox

Seems memory layout is shared with Vulkan so we can port fix from
ggml-org#19299

* Fix rope_multi

* Fix rope_vision

* Fix rope_norm

* Rename ne* to ne0* for consistent variable naming

* cont : consistent stride names

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

Author: ORippler