5ecff35151
On my Mac, the direct Q4_1 product is marginally slower (~69 vs ~55 us for Q4_0). The SIMD-ified ggml version is now almost 2X slower (~121 us). On a Ryzen 7950X CPU, the direct product for Q4_1 quantization is faster than the AVX2 implementation (~60 vs ~62 us). --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
13 lines
171 B
CMake
13 lines
171 B
CMake
# dependencies
|
|
|
|
find_package(Threads REQUIRED)
|
|
|
|
# third-party
|
|
|
|
include_directories(${CMAKE_CURRENT_SOURCE_DIR})
|
|
|
|
if (EMSCRIPTEN)
|
|
else()
|
|
add_subdirectory(vdot)
|
|
endif()
|