mirror of
https://git.adityakumar.xyz/llama.cpp.git
synced 2024-11-09 15:29:43 +00:00
62cfc54f77
Command that calculates some statistics over the errors introduced by quantization, like mean square error, max error and some percentile errors for layer weights. Should be useful for testing quantization improvements. Exposes some internal state from ggml and llama for testing
4 lines
199 B
CMake
4 lines
199 B
CMake
set(TARGET quantize-stats)
|
|
add_executable(${TARGET} quantize-stats.cpp)
|
|
target_link_libraries(${TARGET} PRIVATE llama ${CMAKE_THREAD_LIBS_INIT})
|
|
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|