root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-26 11:24:35 +00:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity
gg/llama-refactor-0
llama.cpp/examples/gguf-hash/CMakeLists.txt

23 lines
728 B
CMake
Raw Permalink Normal View History

gguf-hash: model wide and per tensor hashing using xxhash and sha1 (#8048) CLI to hash GGUF files to detect difference on a per model and per tensor level The hash type we support is: - `--xxh64`: use xhash 64bit hash mode (default) - `--sha1`: use sha1 - `--uuid`: use uuid - `--sha256`: use sha256 While most POSIX systems already have hash checking programs like sha256sum, it is designed to check entire files. This is not ideal for our purpose if we want to check for consistency of the tensor data even if the metadata content of the gguf KV store has been updated. This program is designed to hash a gguf tensor payload on a 'per tensor layer' in addition to a 'entire tensor model' hash. The intent is that the entire tensor layer can be checked first but if there is any detected inconsistencies, then the per tensor hash can be used to narrow down the specific tensor layer that has inconsistencies. Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-07-07 12:58:43 +00:00
set(TARGET llama-gguf-hash)
add_executable(${TARGET} gguf-hash.cpp)
install(TARGETS ${TARGET} RUNTIME)
# clibs dependencies
include_directories(deps/)
llama : disable warnings for 3rd party sha1 dependency (#10527)
2024-11-26 20:01:47 +00:00
gguf-hash: model wide and per tensor hashing using xxhash and sha1 (#8048) CLI to hash GGUF files to detect difference on a per model and per tensor level The hash type we support is: - `--xxh64`: use xhash 64bit hash mode (default) - `--sha1`: use sha1 - `--uuid`: use uuid - `--sha256`: use sha256 While most POSIX systems already have hash checking programs like sha256sum, it is designed to check entire files. This is not ideal for our purpose if we want to check for consistency of the tensor data even if the metadata content of the gguf KV store has been updated. This program is designed to hash a gguf tensor payload on a 'per tensor layer' in addition to a 'entire tensor model' hash. The intent is that the entire tensor layer can be checked first but if there is any detected inconsistencies, then the per tensor hash can be used to narrow down the specific tensor layer that has inconsistencies. Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-07-07 12:58:43 +00:00
add_library(xxhash OBJECT deps/xxhash/xxhash.c deps/xxhash/xxhash.h)
target_link_libraries(${TARGET} PRIVATE xxhash)
llama : disable warnings for 3rd party sha1 dependency (#10527)
2024-11-26 20:01:47 +00:00
gguf-hash: model wide and per tensor hashing using xxhash and sha1 (#8048) CLI to hash GGUF files to detect difference on a per model and per tensor level The hash type we support is: - `--xxh64`: use xhash 64bit hash mode (default) - `--sha1`: use sha1 - `--uuid`: use uuid - `--sha256`: use sha256 While most POSIX systems already have hash checking programs like sha256sum, it is designed to check entire files. This is not ideal for our purpose if we want to check for consistency of the tensor data even if the metadata content of the gguf KV store has been updated. This program is designed to hash a gguf tensor payload on a 'per tensor layer' in addition to a 'entire tensor model' hash. The intent is that the entire tensor layer can be checked first but if there is any detected inconsistencies, then the per tensor hash can be used to narrow down the specific tensor layer that has inconsistencies. Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-07-07 12:58:43 +00:00
add_library(sha1 OBJECT deps/sha1/sha1.c deps/sha1/sha1.h)
target_link_libraries(${TARGET} PRIVATE sha1)
llama : disable warnings for 3rd party sha1 dependency (#10527)
2024-11-26 20:01:47 +00:00
if (NOT MSVC)
# disable warnings in 3rd party code
target_compile_options(sha1 PRIVATE -w)
endif()
gguf-hash: model wide and per tensor hashing using xxhash and sha1 (#8048) CLI to hash GGUF files to detect difference on a per model and per tensor level The hash type we support is: - `--xxh64`: use xhash 64bit hash mode (default) - `--sha1`: use sha1 - `--uuid`: use uuid - `--sha256`: use sha256 While most POSIX systems already have hash checking programs like sha256sum, it is designed to check entire files. This is not ideal for our purpose if we want to check for consistency of the tensor data even if the metadata content of the gguf KV store has been updated. This program is designed to hash a gguf tensor payload on a 'per tensor layer' in addition to a 'entire tensor model' hash. The intent is that the entire tensor layer can be checked first but if there is any detected inconsistencies, then the per tensor hash can be used to narrow down the specific tensor layer that has inconsistencies. Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-07-07 12:58:43 +00:00
add_library(sha256 OBJECT deps/sha256/sha256.c deps/sha256/sha256.h)
target_link_libraries(${TARGET} PRIVATE sha256)
target_link_libraries(${TARGET} PRIVATE ggml ${CMAKE_THREAD_LIBS_INIT})
ggml : move AMX to the CPU backend (#10570) * ggml : move AMX to the CPU backend --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-11-29 20:54:58 +00:00
target_compile_features(${TARGET} PRIVATE cxx_std_17)
Reference in New Issue Copy Permalink