b6759
CUDA: use fastdiv + ggml_cuda_mad for mmvf (#16557) * CUDA: use fastdiv + ggml_cuda_mad for mmvf * use bf16 directly + fix formatting * Add exception for HIP code
CUDA: use fastdiv + ggml_cuda_mad for mmvf (#16557) * CUDA: use fastdiv + ggml_cuda_mad for mmvf * use bf16 directly + fix formatting * Add exception for HIP code