Steward Garcia ce18d727a4 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>

2023-12-29 18:52:15 +02:00

39 KiB

Raw Blame History

View Raw