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

k-quants : allow to optionally disable at compile time (#1734)

Browse Source 
* k-quants : put behind optional compile flag LLAMA_K_QUANTS

* build : enable k-quants by default
This commit is contained in:
Georgi Gerganov
2023-06-07 10:59:52 +03:00
committed by GitHub
parent 5b57a5b726
commit 5c64a0952e
6 changed files with 250 additions and 228 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
CMakeLists.txt
View File

@ -72,6 +72,7 @@ set(LLAMA_CUDA_DMMV_X "32" CACHE STRING "llama: x stride for dmmv CUDA kern
set(LLAMA_CUDA_DMMV_Y "1" CACHE STRING "llama: y block size for dmmv CUDA kernels")
option(LLAMA_CLBLAST "llama: use CLBlast" OFF)
option(LLAMA_METAL "llama: use Metal" OFF)
option(LLAMA_K_QUANTS "llama: use k-quants" ON)
option(LLAMA_BUILD_TESTS "llama: build tests" ${LLAMA_STANDALONE})
option(LLAMA_BUILD_EXAMPLES "llama: build examples" ${LLAMA_STANDALONE})
@ -226,6 +227,10 @@ if (LLAMA_METAL)
)
endif()
if (LLAMA_K_QUANTS)
set(GGML_SOURCES_EXTRA ${GGML_SOURCES_EXTRA} k_quants.c k_quants.h)
endif()
if (LLAMA_CLBLAST)
find_package(CLBlast)
if (CLBlast_FOUND)
@ -396,11 +401,10 @@ endif()
add_library(ggml OBJECT
ggml.c
ggml.h
ggml-quants-k.h
ggml-quants-k.c
${GGML_SOURCES_CUDA}
${GGML_SOURCES_OPENCL}
${GGML_SOURCES_METAL}
${GGML_SOURCES_EXTRA}
)
target_include_directories(ggml PUBLIC .)