clip : enable gpu backend (#4205)
* clip: enable CUDA backend
* add missing kernels
* add enough padding for alignment
* remove ggml_repeat of clip.cpp
* add metal backend
* llava : fixes
- avoid ggml_repeat
- use GGML_USE_ instead of CLIP_USE_ macros
- remove unused vars
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
