llama.cpp

5a0e3ef6 - cuda: Add cublasLt_static linking when GGML_STATIC is enabled (#15622)

cuda: Add cublasLt_static linking when GGML_STATIC is enabled (#15622) Prior to this change, we faced undefined cublasLt references when attempting to compile 'llama-cli' with GGML_STATIC=ON on Linux. We add linking with CUDA::cublasLt_static when CUDA version is greater than 10.1.