include llama.cpp since there were some edits
This commit is contained in:
zefie committed
1 parent
db7f28d087
commit
8c66990853
3918 files changed
+1640170
-1
No files matched your search
@@ -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()
|
||||
Reference in new issue
Block a user