From 24a447e20af425fa44cf10feaa632b6bb596c80f Mon Sep 17 00:00:00 2001 From: automaticcat Date: Sat, 30 Dec 2023 15:07:48 +0700 Subject: ggml : add ggml_cpu_has_avx_vnni() (#4589) * feat: add avx_vnni based on intel documents * ggml: add avx vnni based on intel document * llama: add avx vnni information display * docs: add more details about using oneMKL and oneAPI for intel processors * docs: add more details about using oneMKL and oneAPI for intel processors * docs: add more details about using oneMKL and oneAPI for intel processors * docs: add more details about using oneMKL and oneAPI for intel processors * docs: add more details about using oneMKL and oneAPI for intel processors * Update ggml.c Fix indentation upgate Co-authored-by: Georgi Gerganov --------- Co-authored-by: Georgi Gerganov --- ggml.h | 1 + 1 file changed, 1 insertion(+) (limited to 'ggml.h') diff --git a/ggml.h b/ggml.h index 67d6bc4f..64f4e45e 100644 --- a/ggml.h +++ b/ggml.h @@ -2198,6 +2198,7 @@ extern "C" { // GGML_API int ggml_cpu_has_avx (void); + GGML_API int ggml_cpu_has_avx_vnni (void); GGML_API int ggml_cpu_has_avx2 (void); GGML_API int ggml_cpu_has_avx512 (void); GGML_API int ggml_cpu_has_avx512_vbmi(void); -- cgit v1.2.3