llama.cpp

4683cb40 - CUDA: don't convert BF16 weights to FP32 (ggml/1174)

CUDA: don't convert BF16 weights to FP32 (ggml/1174) * add bf16 support * use convert_from_bf16_cuda instead of convert_unary_cuda for f32 * revert 7ec5085 * move functionality into convert_unary with constexpr