llama.cpp

dd8ba934 - ggml: aarch64: Implement SVE F32 kernels for Mamba Sequential Scan Algorithm (#13882)

ggml: aarch64: Implement SVE F32 kernels for Mamba Sequential Scan Algorithm (#13882) * F32-Mamba-Seq_Scan-SVE * Fix formatting * ggml : missing space --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>