llama.cpp

1244cdcf - ggml : do not define GGML_USE_CUDA when building with GGML_BACKEND_DL (#11211)

ggml : do not define GGML_USE_CUDA when building with GGML_BACKEND_DL (#11211) Build fails when using HIP and GGML_BACKEND_DL: ``` /usr/bin/ld: ../ggml/src/libggml.so: undefined reference to `ggml_backend_cuda_reg' collect2: error: ld returned 1 exit status ``` This patch fixes this.