vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

ggml : add ggml_cpu_has_avx_vnni() (#4589)

Browse source 
* 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 <ggerganov@gmail.com>

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
automaticcat 2023-12-30 15:07:48 +07:00 • committed by GitHub
parent a20f3c7465
commit 24a447e20a
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
5 changed files with 33 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

1
llama.cpp
View file

@ -10780,6 +10780,7 @@ const char * llama_print_system_info(void) {
s = "";
s += "AVX = " + std::to_string(ggml_cpu_has_avx()) + " | ";
s += "AVX_VNNI = " + std::to_string(ggml_cpu_has_avx_vnni()) + " | ";
s += "AVX2 = " + std::to_string(ggml_cpu_has_avx2()) + " | ";
s += "AVX512 = " + std::to_string(ggml_cpu_has_avx512()) + " | ";
s += "AVX512_VBMI = " + std::to_string(ggml_cpu_has_avx512_vbmi()) + " | ";