include llama.cpp since there were some edits

This commit is contained in:
zefie committed 2026-11-01 16:32:35 -05:00
1 parent db7f28d087
commit 8c66990853
3918 files changed
+1640170 -1

No files matched your search

+36
View File
@@ -0,0 +1,36 @@
# cmake/FindNCCL.cmake
# NVIDIA does not distribute CMake files with NCCl, therefore use this file to find it instead.
find_path(NCCL_INCLUDE_DIR
NAMES nccl.h
HINTS ${NCCL_ROOT} $ENV{NCCL_ROOT} $ENV{CUDA_HOME} /usr/local/cuda
PATH_SUFFIXES include
)
find_library(NCCL_LIBRARY
NAMES nccl
HINTS ${NCCL_ROOT} $ENV{NCCL_ROOT} $ENV{CUDA_HOME} /usr/local/cuda
PATH_SUFFIXES lib lib64
)
include(FindPackageHandleStandardArgs)
find_package_handle_standard_args(NCCL
DEFAULT_MSG
NCCL_LIBRARY NCCL_INCLUDE_DIR
)
if(NCCL_FOUND)
set(NCCL_LIBRARIES ${NCCL_LIBRARY})
set(NCCL_INCLUDE_DIRS ${NCCL_INCLUDE_DIR})
if(NOT TARGET NCCL::NCCL)
add_library(NCCL::NCCL UNKNOWN IMPORTED)
set_target_properties(NCCL::NCCL PROPERTIES
IMPORTED_LOCATION "${NCCL_LIBRARY}"
INTERFACE_INCLUDE_DIRECTORIES "${NCCL_INCLUDE_DIR}"
)
endif()
endif()
mark_as_advanced(NCCL_INCLUDE_DIR NCCL_LIBRARY)
+22
View File
@@ -0,0 +1,22 @@
find_package(Git)
# the commit's SHA1
execute_process(COMMAND
"${GIT_EXECUTABLE}" describe --match=NeVeRmAtCh --always --abbrev=8
WORKING_DIRECTORY "${CMAKE_SOURCE_DIR}"
OUTPUT_VARIABLE GIT_SHA1
ERROR_QUIET OUTPUT_STRIP_TRAILING_WHITESPACE)
# the date of the commit
execute_process(COMMAND
"${GIT_EXECUTABLE}" log -1 --format=%ad --date=local
WORKING_DIRECTORY "${CMAKE_SOURCE_DIR}"
OUTPUT_VARIABLE GIT_DATE
ERROR_QUIET OUTPUT_STRIP_TRAILING_WHITESPACE)
# the subject of the commit
execute_process(COMMAND
"${GIT_EXECUTABLE}" log -1 --format=%s
WORKING_DIRECTORY "${CMAKE_SOURCE_DIR}"
OUTPUT_VARIABLE GIT_COMMIT_SUBJECT
ERROR_QUIET OUTPUT_STRIP_TRAILING_WHITESPACE)
+128
View File
@@ -0,0 +1,128 @@
function(ggml_get_flags CCID CCVER)
set(C_FLAGS "")
set(CXX_FLAGS "")
if (CCID MATCHES "Clang" OR CCID MATCHES "IntelLLVM")
set(C_FLAGS -Wunreachable-code-break -Wunreachable-code-return)
set(CXX_FLAGS -Wunreachable-code-break -Wunreachable-code-return -Wmissing-prototypes -Wextra-semi)
if (CCID STREQUAL "IntelLLVM")
# for Intel DPC++ and LLVM SYCL, using debug does not disable optimization
list(APPEND C_FLAGS -Rno-debug-disables-optimization)
list(APPEND CXX_FLAGS -Rno-debug-disables-optimization)
endif()
if (
(CCID STREQUAL "Clang" AND CCVER VERSION_GREATER_EQUAL 3.8.0) OR
(CCID STREQUAL "AppleClang" AND CCVER VERSION_GREATER_EQUAL 7.3.0)
)
list(APPEND C_FLAGS -Wdouble-promotion)
endif()
elseif (CCID STREQUAL "GNU")
set(C_FLAGS -Wdouble-promotion)
set(CXX_FLAGS -Wno-array-bounds)
if (CCVER VERSION_GREATER_EQUAL 8.1.0)
list(APPEND CXX_FLAGS -Wextra-semi)
endif()
endif()
set(GF_C_FLAGS ${C_FLAGS} PARENT_SCOPE)
set(GF_CXX_FLAGS ${CXX_FLAGS} PARENT_SCOPE)
endfunction()
function(ggml_get_system_arch)
if (CMAKE_OSX_ARCHITECTURES STREQUAL "arm64" OR
CMAKE_GENERATOR_PLATFORM_LWR STREQUAL "arm64" OR
(CMAKE_GENERATOR_PLATFORM_LWR STREQUAL "arm64ec" AND MSVC AND NOT CMAKE_C_COMPILER_ID STREQUAL "Clang") OR
(NOT CMAKE_OSX_ARCHITECTURES AND NOT CMAKE_GENERATOR_PLATFORM_LWR AND
CMAKE_SYSTEM_PROCESSOR MATCHES "^(aarch64|arm.*|ARM64)$"))
set(GGML_SYSTEM_ARCH "ARM" PARENT_SCOPE)
elseif (CMAKE_OSX_ARCHITECTURES STREQUAL "x86_64" OR
CMAKE_GENERATOR_PLATFORM_LWR MATCHES "^(x86_64|i686|amd64|x64|win32)$" OR
(NOT CMAKE_OSX_ARCHITECTURES AND NOT CMAKE_GENERATOR_PLATFORM_LWR AND
CMAKE_SYSTEM_PROCESSOR MATCHES "^(x86_64|i686|AMD64|amd64)$"))
set(GGML_SYSTEM_ARCH "x86" PARENT_SCOPE)
elseif (${CMAKE_SYSTEM_PROCESSOR} MATCHES "ppc|power")
set(GGML_SYSTEM_ARCH "PowerPC" PARENT_SCOPE)
elseif (${CMAKE_SYSTEM_PROCESSOR} MATCHES "loongarch64")
set(GGML_SYSTEM_ARCH "loongarch64" PARENT_SCOPE)
elseif (${CMAKE_SYSTEM_PROCESSOR} MATCHES "riscv64")
set(GGML_SYSTEM_ARCH "riscv64" PARENT_SCOPE)
elseif (${CMAKE_SYSTEM_PROCESSOR} MATCHES "s390x")
set(GGML_SYSTEM_ARCH "s390x" PARENT_SCOPE)
else()
set(GGML_SYSTEM_ARCH "UNKNOWN" PARENT_SCOPE)
endif()
endfunction()
# Determines which FlashAttention vector kernel template instances to compile, returns them in OUT_SRCS.
function(ggml_cuda_fattn_vec_instances DIR OUT_SRCS)
set(FA_TYPES q4_0 q4_1 q5_0 q5_1 q8_0 bf16 f16)
string(TOLOWER "${GGML_CUDA_FA_QUANTS}" FA_QUANTS)
string(STRIP "${FA_QUANTS}" FA_QUANTS)
if (GGML_CUDA_FA_ALL_QUANTS)
message(WARNING "GGML_CUDA_FA_ALL_QUANTS is deprecated, use GGML_CUDA_FA_QUANTS=all instead")
set(FA_QUANTS all)
endif()
if (NOT FA_QUANTS)
message(FATAL_ERROR "GGML_CUDA_FA_QUANTS must not be empty")
endif()
if (FA_QUANTS STREQUAL "all")
set(FA_COMBINATIONS "")
foreach (TYPE_V IN LISTS FA_TYPES)
foreach (TYPE_K IN LISTS FA_TYPES)
list(APPEND FA_COMBINATIONS ${TYPE_K}-${TYPE_V})
endforeach()
endforeach()
else()
set(FA_COMBINATIONS f16-f16)
string(REPLACE "," ";" FA_SELECTED "${FA_QUANTS}")
foreach (COMBINATION IN LISTS FA_SELECTED)
string(STRIP "${COMBINATION}" COMBINATION)
if (NOT COMBINATION MATCHES "^([a-z0-9_]+)-([a-z0-9_]+)$")
message(FATAL_ERROR "GGML_CUDA_FA_QUANTS: \"${COMBINATION}\" is not \"all\" or a <type_K>-<type_V> combination")
endif()
set(TYPE_K ${CMAKE_MATCH_1})
set(TYPE_V ${CMAKE_MATCH_2})
foreach (TYPE ${TYPE_K} ${TYPE_V})
if (NOT TYPE IN_LIST FA_TYPES)
message(FATAL_ERROR
"GGML_CUDA_FA_QUANTS: unknown type \"${TYPE}\" in \"${COMBINATION}\", must be one of: ${FA_TYPES}")
endif()
endforeach()
list(APPEND FA_COMBINATIONS ${TYPE_K}-${TYPE_V})
endforeach()
endif()
list(REMOVE_DUPLICATES FA_COMBINATIONS)
string(REPLACE ";" "," FA_QUANTS_DEFINE "${FA_QUANTS}")
add_compile_definitions(GGML_CUDA_FA_QUANTS="${FA_QUANTS_DEFINE}")
foreach (TYPE_V IN LISTS FA_TYPES)
foreach (TYPE_K IN LISTS FA_TYPES)
if ("${TYPE_K}-${TYPE_V}" IN_LIST FA_COMBINATIONS)
set(COMPILED 1)
else()
set(COMPILED 0)
endif()
string(TOUPPER "GGML_CUDA_FA_${TYPE_K}_${TYPE_V}" COMBINATION_DEF)
add_compile_definitions(${COMBINATION_DEF}=${COMPILED})
endforeach()
endforeach()
message(STATUS "FlashAttention K-V type combinations: ${FA_COMBINATIONS}")
set(SRCS "")
foreach (COMBINATION IN LISTS FA_COMBINATIONS)
set(SRC "${DIR}/template-instances/fattn-vec-instance-${COMBINATION}.cu")
if (NOT EXISTS "${SRC}")
message(FATAL_ERROR "FlashAttention template instance \"${SRC}\" does not exist")
endif()
list(APPEND SRCS "${SRC}")
endforeach()
set(${OUT_SRCS} ${SRCS} PARENT_SCOPE)
endfunction()
+216
View File
@@ -0,0 +1,216 @@
@PACKAGE_INIT@
@GGML_VARIABLES_EXPANDED@
# Find all dependencies before creating any target.
include(CMakeFindDependencyMacro)
find_dependency(Threads)
if (NOT GGML_SHARED_LIB)
set(GGML_BASE_INTERFACE_LINK_LIBRARIES "")
set(GGML_CPU_INTERFACE_LINK_LIBRARIES "")
set(GGML_CPU_INTERFACE_LINK_OPTIONS "")
if (APPLE AND GGML_ACCELERATE)
find_library(ACCELERATE_FRAMEWORK Accelerate)
if(NOT ACCELERATE_FRAMEWORK)
set(${CMAKE_FIND_PACKAGE_NAME}_FOUND 0)
return()
endif()
list(APPEND GGML_CPU_INTERFACE_LINK_LIBRARIES ${ACCELERATE_FRAMEWORK})
endif()
if (GGML_OPENMP_ENABLED)
find_dependency(OpenMP)
set(GGML_OPENMP_INTERFACE_LINK_LIBRARIES "")
if (TARGET OpenMP::OpenMP_C)
list(APPEND GGML_OPENMP_INTERFACE_LINK_LIBRARIES OpenMP::OpenMP_C)
endif()
if (TARGET OpenMP::OpenMP_CXX)
list(APPEND GGML_OPENMP_INTERFACE_LINK_LIBRARIES OpenMP::OpenMP_CXX)
endif()
list(APPEND GGML_BASE_INTERFACE_LINK_LIBRARIES ${GGML_OPENMP_INTERFACE_LINK_LIBRARIES})
list(APPEND GGML_CPU_INTERFACE_LINK_LIBRARIES ${GGML_OPENMP_INTERFACE_LINK_LIBRARIES})
endif()
if (GGML_CPU_HBM)
find_library(memkind memkind)
if(NOT memkind)
set(${CMAKE_FIND_PACKAGE_NAME}_FOUND 0)
return()
endif()
list(APPEND GGML_CPU_INTERFACE_LINK_LIBRARIES memkind)
endif()
if (GGML_BLAS)
find_dependency(BLAS)
list(APPEND GGML_BLAS_INTERFACE_LINK_LIBRARIES ${BLAS_LIBRARIES})
list(APPEND GGML_BLAS_INTERFACE_LINK_OPTIONS ${BLAS_LINKER_FLAGS})
endif()
if (GGML_CUDA)
set(GGML_CUDA_INTERFACE_LINK_LIBRARIES "")
find_dependency(CUDAToolkit)
if (GGML_STATIC)
list(APPEND GGML_CUDA_INTERFACE_LINK_LIBRARIES $<LINK_ONLY:CUDA::cudart_static>)
if (WIN32)
list(APPEND GGML_CUDA_INTERFACE_LINK_LIBRARIES $<LINK_ONLY:CUDA::cublas> $<LINK_ONLY:CUDA::cublasLt>)
else()
list(APPEND GGML_CUDA_INTERFACE_LINK_LIBRARIES $<LINK_ONLY:CUDA::cublas_static> $<LINK_ONLY:CUDA::cublasLt_static>)
endif()
endif()
if (NOT GGML_CUDA_NO_VMM)
list(APPEND GGML_CUDA_INTERFACE_LINK_LIBRARIES $<LINK_ONLY:CUDA::cuda_driver>)
endif()
endif()
if (GGML_METAL)
find_library(FOUNDATION_LIBRARY Foundation)
find_library(METAL_FRAMEWORK Metal)
find_library(METALKIT_FRAMEWORK MetalKit)
if(NOT FOUNDATION_LIBRARY OR NOT METAL_FRAMEWORK OR NOT METALKIT_FRAMEWORK)
set(${CMAKE_FIND_PACKAGE_NAME}_FOUND 0)
return()
endif()
set(GGML_METAL_INTERFACE_LINK_LIBRARIES
${FOUNDATION_LIBRARY} ${METAL_FRAMEWORK} ${METALKIT_FRAMEWORK})
endif()
if (GGML_OPENCL)
find_dependency(OpenCL)
set(GGML_OPENCL_INTERFACE_LINK_LIBRARIES $<LINK_ONLY:OpenCL::OpenCL>)
endif()
if (GGML_VULKAN)
find_dependency(Vulkan)
set(GGML_VULKAN_INTERFACE_LINK_LIBRARIES $<LINK_ONLY:Vulkan::Vulkan>)
endif()
if (GGML_HIP)
find_dependency(hip)
find_dependency(hipblas)
find_dependency(rocblas)
set(GGML_HIP_INTERFACE_LINK_LIBRARIES hip::host roc::rocblas roc::hipblas)
endif()
if (GGML_SYCL)
set(GGML_SYCL_INTERFACE_LINK_LIBRARIES "")
find_package(DNNL)
if (${DNNL_FOUND} AND GGML_SYCL_TARGET STREQUAL "INTEL")
list(APPEND GGML_SYCL_INTERFACE_LINK_LIBRARIES DNNL::dnnl)
endif()
if (WIN32)
find_dependency(IntelSYCL)
find_dependency(MKL)
list(APPEND GGML_SYCL_INTERFACE_LINK_LIBRARIES IntelSYCL::SYCL_CXX MKL::MKL MKL::MKL_SYCL)
endif()
endif()
endif()
set_and_check(GGML_INCLUDE_DIR "@PACKAGE_GGML_INCLUDE_INSTALL_DIR@")
set_and_check(GGML_LIB_DIR "@PACKAGE_GGML_LIB_INSTALL_DIR@")
#set_and_check(GGML_BIN_DIR "@PACKAGE_GGML_BIN_INSTALL_DIR@")
if (NOT GGML_SHARED_LIB AND GGML_CPU_KLEIDIAI)
unset(KLEIDIAI_LIBRARY CACHE)
unset(KLEIDIAI_LIBRARY)
find_library(KLEIDIAI_LIBRARY kleidiai
REQUIRED
HINTS ${GGML_LIB_DIR}
NO_CMAKE_FIND_ROOT_PATH)
list(APPEND GGML_CPU_INTERFACE_LINK_LIBRARIES ${KLEIDIAI_LIBRARY})
endif()
if(NOT TARGET ggml::ggml)
find_package(Threads REQUIRED)
unset(GGML_LIBRARY CACHE)
find_library(GGML_LIBRARY ggml
REQUIRED
HINTS ${GGML_LIB_DIR}
NO_CMAKE_FIND_ROOT_PATH)
add_library(ggml::ggml UNKNOWN IMPORTED)
set_target_properties(ggml::ggml
PROPERTIES
IMPORTED_LOCATION "${GGML_LIBRARY}"
INTERFACE_INCLUDE_DIRECTORIES "${GGML_INCLUDE_DIR}")
unset(GGML_BASE_LIBRARY CACHE)
find_library(GGML_BASE_LIBRARY ggml-base
REQUIRED
HINTS ${GGML_LIB_DIR}
NO_CMAKE_FIND_ROOT_PATH)
add_library(ggml::ggml-base UNKNOWN IMPORTED)
set_target_properties(ggml::ggml-base
PROPERTIES
IMPORTED_LOCATION "${GGML_BASE_LIBRARY}"
INTERFACE_INCLUDE_DIRECTORIES "${GGML_INCLUDE_DIR}"
INTERFACE_LINK_LIBRARIES "${GGML_BASE_INTERFACE_LINK_LIBRARIES}")
set(_ggml_all_targets "")
if (NOT GGML_BACKEND_DL)
foreach(_ggml_backend ${GGML_AVAILABLE_BACKENDS})
string(REPLACE "-" "_" _ggml_backend_pfx "${_ggml_backend}")
string(TOUPPER "${_ggml_backend_pfx}" _ggml_backend_pfx)
unset(${_ggml_backend_pfx}_LIBRARY CACHE)
find_library(${_ggml_backend_pfx}_LIBRARY ${_ggml_backend}
REQUIRED
HINTS ${GGML_LIB_DIR}
NO_CMAKE_FIND_ROOT_PATH)
message(STATUS "Found ${${_ggml_backend_pfx}_LIBRARY}")
add_library(ggml::${_ggml_backend} UNKNOWN IMPORTED)
set_target_properties(ggml::${_ggml_backend}
PROPERTIES
INTERFACE_INCLUDE_DIRECTORIES "${GGML_INCLUDE_DIR}"
IMPORTED_LINK_INTERFACE_LANGUAGES "CXX"
IMPORTED_LOCATION "${${_ggml_backend_pfx}_LIBRARY}"
INTERFACE_COMPILE_FEATURES c_std_90
POSITION_INDEPENDENT_CODE ON)
string(REGEX MATCH "^ggml-cpu" is_cpu_variant "${_ggml_backend}")
if(is_cpu_variant)
list(APPEND GGML_CPU_INTERFACE_LINK_LIBRARIES "ggml::ggml-base")
set_target_properties(ggml::${_ggml_backend}
PROPERTIES
INTERFACE_LINK_LIBRARIES "${GGML_CPU_INTERFACE_LINK_LIBRARIES}")
if(GGML_CPU_INTERFACE_LINK_OPTIONS)
set_target_properties(ggml::${_ggml_backend}
PROPERTIES
INTERFACE_LINK_OPTIONS "${GGML_CPU_INTERFACE_LINK_OPTIONS}")
endif()
else()
list(APPEND ${_ggml_backend_pfx}_INTERFACE_LINK_LIBRARIES "ggml::ggml-base")
set_target_properties(ggml::${_ggml_backend}
PROPERTIES
INTERFACE_LINK_LIBRARIES "${${_ggml_backend_pfx}_INTERFACE_LINK_LIBRARIES}")
if(${_ggml_backend_pfx}_INTERFACE_LINK_OPTIONS)
set_target_properties(ggml::${_ggml_backend}
PROPERTIES
INTERFACE_LINK_OPTIONS "${${_ggml_backend_pfx}_INTERFACE_LINK_OPTIONS}")
endif()
endif()
list(APPEND _ggml_all_targets ggml::${_ggml_backend})
endforeach()
endif()
list(APPEND GGML_INTERFACE_LINK_LIBRARIES ggml::ggml-base "${_ggml_all_targets}")
set_target_properties(ggml::ggml
PROPERTIES
INTERFACE_LINK_LIBRARIES "${GGML_INTERFACE_LINK_LIBRARIES}")
add_library(ggml::all INTERFACE IMPORTED)
set_target_properties(ggml::all
PROPERTIES
INTERFACE_LINK_LIBRARIES "${_ggml_all_targets}")
endif()
check_required_components(ggml)