ggml : optimize llamafile's cpu matrix multiplication for ppc64le#10156

ggerganov merged 1 commit intoggml-org:masterggml-org/llama.cpp:masterfrom

amritahs-ibm:sgemm_ppc_mma1amritahs-ibm/llama.cpp:sgemm_ppc_mma1Copy head branch name to clipboard