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

4
Makefile
View File

@ -940,6 +940,10 @@ ggml/src/ggml-cuda/%.o: \
$(MCC) $(CXXFLAGS) $(MUSAFLAGS) -x musa -mtgpu -c -o $@ $<
endif # GGML_MUSA
ifndef GGML_NO_CPU_AARCH64
MK_CPPFLAGS += -DGGML_USE_CPU_AARCH64
endif
ifdef GGML_METAL
MK_CPPFLAGS += -DGGML_USE_METAL
MK_LDFLAGS += -framework Foundation -framework Metal -framework MetalKit