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

backend cpu: add online flow for aarch64 Q4_0 GEMV/GEMM kernels (#9921)

Browse Source 
* backend-cpu: add online flow for aarch64 Q4_0 GEMV/GEMM kernels

---------

Co-authored-by: Diego Devesa <slarengh@gmail.com>
This commit is contained in:
Charles Xu
2024-11-15 01:28:50 +01:00
committed by GitHub
parent ae8de6d50a
commit 1607a5e5b0
9 changed files with 273 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
ggml/CMakeLists.txt
View File

@ -92,6 +92,7 @@ else()
endif()
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_AVX2 "ggml: enable AVX2" ${INS_ENB})