mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-07-19 17:17:40 +00:00
* cuda : fix rope non-cont ggml-ci * cont : fix multi-rope + add test ggml-ci * sycl : try fix ggml-ci * cont : fix sycl + clean-up cuda ggml-ci