tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-26 19:55:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml : automatic selection of best CPU backend (#10606)

Browse Source 
* ggml : automatic selection of best CPU backend

* amx : minor opt

* add GGML_AVX_VNNI to enable avx-vnni, fix checks
This commit is contained in:
Diego Devesa
2024-12-01 16:12:41 +01:00
committed by GitHub
parent 86dc11c5bc
commit 3420909dff
12 changed files with 599 additions and 156 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
ggml/CMakeLists.txt
View File

@ -96,6 +96,7 @@ option(GGML_CPU_HBM "ggml: use memkind for CPU HBM" OFF)
option(GGML_CPU_AARCH64 "ggml: use runtime weight conversion of Q4_0 to Q4_X_X" ON)
option(GGML_AVX "ggml: enable AVX" ${INS_ENB})
option(GGML_AVX_VNNI "ggml: enable AVX-VNNI" OFF)
option(GGML_AVX2 "ggml: enable AVX2" ${INS_ENB})
option(GGML_AVX512 "ggml: enable AVX512" OFF)
option(GGML_AVX512_VBMI "ggml: enable AVX512-VBMI" OFF)