llama.cpp

b925f1f1 - cuBLAS: fall back to pageable memory if pinned alloc fails (#1233)

cuBLAS: fall back to pageable memory if pinned alloc fails (#1233) * cuBLAS: fall back to pageable memory if pinned alloc fails * cuBLAS: do not use pinned memory if env variable GGML_CUDA_NO_PINNED is set