CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-16 11:27:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml-cpu: add nnpa compile flag

Browse Source 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
(cherry picked from commit 4a9f60c201)
This commit is contained in:
Aaron Teo
2025-06-20 17:53:38 +08:00
parent bb16041cae
commit 5801806f70
5 changed files with 20 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
ggml/src/ggml-cpu/CMakeLists.txt
View File

@@ -448,6 +448,7 @@ function(ggml_add_cpu_backend_variant_impl tag_name)
# TODO: Separation to determine activation of VX/VXE/VXE2
if (${S390X_M} MATCHES "8561|8562")
set(GGML_NNPA OFF)
message(STATUS "z15 target")
list(APPEND ARCH_FLAGS -march=z15)
elseif (${S390X_M} MATCHES "3931")
@@ -464,8 +465,14 @@ function(ggml_add_cpu_backend_variant_impl tag_name)
endif()
if (GGML_VXE)
message(STATUS "VX/VXE/VXE2 enabled")
list(APPEND ARCH_FLAGS -mvx -mzvector)
endif()
if (GGML_NNPA)
target_compile_definitions(${GGML_CPU_NAME} PRIVATE GGML_NNPA)
message(STATUS "NNPA enabled")
endif()
elseif (CMAKE_SYSTEM_PROCESSOR MATCHES "wasm")
message(STATUS "Wasm detected")
list (APPEND GGML_CPU_SOURCES ggml-cpu/arch/wasm/quants.c)