Files
ollama/CMakeLists.txt
Michael Yang 1a19df1f3a update vendored llama.cpp and ggml (#11823)
* TEMPORARY: Update the llama.cpp upstream to my fork's Granite Four branch

This will be redone once my branch is merged upstream in llama.cpp

* feat: Update all patches

There are a number that are no longer needed at all:

- 0003-embeddings: Embeddings entirely overhauled on master
- 0008-ensure-KV-cache-is-fully-defragmented: KV caching entirely
    overhauled on master
- 0019-metal-add-mean-kernel-14267: Merged upstream
- 0020-CUDA-add-mean-operation-14313: Merged upstream

* feat: Sync llama.cpp and ggml

* fix: Update rsync-filter for all moved/new/removed files

* fix: Add files missing from sync

* fix: Update ggml rsync-filter for new ggml-cpu/arch subdirs

* fix: Add ggml files missing from sync

* fix: Narrow llama.cpp rsync-filter to not include mtmd main tool cpp files

* fix: Remove mtmd main cpp files

* fix: Add missing include in sampling_ext.cpp

* fix: Update llama.go to use mtmd instead of clip/llava

* fix: Add patch for mtmd_input_text

* chore: Ignore *.patched in the patch directory

* fix: Fix support for arch-specific ggml-cpu source files with new arrangement

In https://github.com/ggml-org/llama.cpp/pull/13892, all arch-specific
implementations were split out into a nested tree structure under
ggml-cpu/arch. This conflicts with standard CGO layout where all
arch-specific source files are expected to live in the same directory as
the parent go module and use suffixes based on GOOS and GOARCH. As such,
there were really two options for getting this to work:

1. Add a patch on top of the GGML sync to rearrange the files to match the
GO layout convention
2. Use CGO directives to conditionally include the nested source files in
the compilation units

This commit does (2) in order to minimize the set of changes needed on top
of the upstream file layout. To get this to work, there are two key things
needed:

1. In cpu.go, #cgo directives are added to explicitly set __${GOARCH}__ in
the preprocessor directives
2. In arch-impls.c|cpp, use an #ifdef | #elif defined | #endif chain to
explicitly include the .c|.cpp files for the given architecture from the
nested directory

* fix: Use mtmd_helper to correctly load the bitmap for the image

* fix: Apply patch for mtmd_text_input

* fix: Add missing stb to llama.cpp rsync-filter

* fix: Add sync'ed stb vendored header

* fix: Use c++17 and include vendor for go wrapper modules

* fix: Update patch 0015 for upstream implementation of uuid

* feat: Bump to the latest tip of the branch

* fix: Update patches for bump

* feat: Bump back to the cenral repo and point at the latest master

This includes granite 4 and a number of other model architectures!

* fix: Revert changes to ggml export GPU UUID patch

* fix: Add patch for GGML_VERSION and GGML_COMMIT constants

* feat: Sync all patched code

* build: Include cmake/common.cmake in ggml sync

* build: Add top-level include for GNUINstallDirs in CMakeLists.txt

This is used to populate CMAKE_INSTALL_BINDIR

* fix: Add a patch to avoid power throttling API on non-msvc windows builds

* fix: Sync patch changes for ggml-cpu.c

* feat: Bump llama.cpp to 4a4f42

This picks up support for Kimi K2 and PLaMO-2

* feat: Sync llama.cpp

* fix: Handle multi-chunk image encodings from mtmd

* fix: Re-number patches after merge with `main`

* feat: Bump to 41e78c in the makefile

* fix: Fix Solar and argsort/copy patches after bump

* fix: Remove Gemma3n CUDA Graphs patch

It was implemented upstream:
https://github.com/ggml-org/llama.cpp/pull/14741

* feat: Sync llama.cpp / ggml after latest bump

* build: Remove unnecessary CFLAGS definitions in cpu.go

* fix: Remove unnecessary additions in the rsync-filter

* fix: Remove unused vendored code for chat template parsing

* Revert "fix: Remove Gemma3n CUDA Graphs patch"

This reverts commit d724caced3.

* fix: Update 0020 CUDA Graphs for gemma3n to keep both llama.cpp and ollama fixes

https://github.com/ollama/ollama/pull/11195#issuecomment-3137312394

* fix: Sync ggml-cuda.cu after keeping both style cuda graph fixes for gemma3n

* unwind mxfp4 patch

Prepare to bump ggml with their impl for mxfp4

* bump

* fix windows build error

* Convert tensors at load time

Repack the mxfp4 tensors as ggmls kernels expect them to be.

* convert mlp bf16 to f32

* buffer the conversion better

* reshape earlier

* openai swiglu

* add ids

* split qkv, gate_up

* fix nested alt tags

* fast attention

* remove debug messages

* fix lint

* remove redundant test

* remap values only if source/target are different

* add back i32->i32 copy

* refactor cpu quants

* clean up vendor

* update patch instructions

* clean up patches

* remove webgpu

* update mem

* also handle gpt-oss

* revert convert changes

---------

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: Daniel Hiltgen <daniel@ollama.com>
2025-08-14 14:42:58 -07:00

140 lines
5.1 KiB
CMake

cmake_minimum_required(VERSION 3.21)
project(Ollama C CXX)
include(CheckLanguage)
include(GNUInstallDirs)
find_package(Threads REQUIRED)
set(CMAKE_BUILD_TYPE Release)
set(BUILD_SHARED_LIBS ON)
set(CMAKE_CXX_STANDARD 17)
set(CMAKE_CXX_STANDARD_REQUIRED ON)
set(CMAKE_CXX_EXTENSIONS OFF)
set(GGML_BUILD ON)
set(GGML_SHARED ON)
set(GGML_CCACHE ON)
set(GGML_BACKEND_DL ON)
set(GGML_BACKEND_SHARED ON)
set(GGML_SCHED_MAX_COPIES 4)
set(GGML_LLAMAFILE ON)
set(GGML_CUDA_PEER_MAX_BATCH_SIZE 128)
set(GGML_CUDA_GRAPHS ON)
set(GGML_CUDA_FA ON)
set(GGML_CUDA_COMPRESSION_MODE default)
if((CMAKE_OSX_ARCHITECTURES AND NOT CMAKE_OSX_ARCHITECTURES MATCHES "arm64")
OR (NOT CMAKE_OSX_ARCHITECTURES AND NOT CMAKE_SYSTEM_PROCESSOR MATCHES "arm|aarch64|ARM64|ARMv[0-9]+"))
set(GGML_CPU_ALL_VARIANTS ON)
endif()
if (CMAKE_OSX_ARCHITECTURES MATCHES "x86_64")
set(CMAKE_BUILD_RPATH "@loader_path")
set(CMAKE_INSTALL_RPATH "@loader_path")
endif()
set(OLLAMA_BUILD_DIR ${CMAKE_BINARY_DIR}/lib/ollama)
set(OLLAMA_INSTALL_DIR ${CMAKE_INSTALL_PREFIX}/lib/ollama)
set(CMAKE_RUNTIME_OUTPUT_DIRECTORY ${OLLAMA_BUILD_DIR})
set(CMAKE_RUNTIME_OUTPUT_DIRECTORY_DEBUG ${OLLAMA_BUILD_DIR})
set(CMAKE_RUNTIME_OUTPUT_DIRECTORY_RELEASE ${OLLAMA_BUILD_DIR})
set(CMAKE_LIBRARY_OUTPUT_DIRECTORY ${OLLAMA_BUILD_DIR})
set(CMAKE_LIBRARY_OUTPUT_DIRECTORY_DEBUG ${OLLAMA_BUILD_DIR})
set(CMAKE_LIBRARY_OUTPUT_DIRECTORY_RELEASE ${OLLAMA_BUILD_DIR})
include_directories(${CMAKE_CURRENT_SOURCE_DIR}/ml/backend/ggml/ggml/src)
include_directories(${CMAKE_CURRENT_SOURCE_DIR}/ml/backend/ggml/ggml/src/include)
include_directories(${CMAKE_CURRENT_SOURCE_DIR}/ml/backend/ggml/ggml/src/ggml-cpu)
include_directories(${CMAKE_CURRENT_SOURCE_DIR}/ml/backend/ggml/ggml/src/ggml-cpu/amx)
add_compile_definitions(NDEBUG GGML_VERSION=0x0 GGML_COMMIT=0x0)
set(GGML_CPU ON)
add_subdirectory(${CMAKE_CURRENT_SOURCE_DIR}/ml/backend/ggml/ggml/src)
set_property(TARGET ggml PROPERTY EXCLUDE_FROM_ALL TRUE)
get_target_property(CPU_VARIANTS ggml-cpu MANUALLY_ADDED_DEPENDENCIES)
if(NOT CPU_VARIANTS)
set(CPU_VARIANTS "ggml-cpu")
endif()
install(TARGETS ggml-base ${CPU_VARIANTS}
RUNTIME_DEPENDENCIES
PRE_EXCLUDE_REGEXES ".*"
RUNTIME DESTINATION ${OLLAMA_INSTALL_DIR} COMPONENT CPU
LIBRARY DESTINATION ${OLLAMA_INSTALL_DIR} COMPONENT CPU
FRAMEWORK DESTINATION ${OLLAMA_INSTALL_DIR} COMPONENT CPU
)
check_language(CUDA)
if(CMAKE_CUDA_COMPILER)
if(CMAKE_VERSION VERSION_GREATER_EQUAL "3.24" AND NOT CMAKE_CUDA_ARCHITECTURES)
set(CMAKE_CUDA_ARCHITECTURES "native")
endif()
find_package(CUDAToolkit)
add_subdirectory(${CMAKE_CURRENT_SOURCE_DIR}/ml/backend/ggml/ggml/src/ggml-cuda)
install(TARGETS ggml-cuda
RUNTIME_DEPENDENCIES
DIRECTORIES ${CUDAToolkit_BIN_DIR} ${CUDAToolkit_LIBRARY_DIR}
PRE_INCLUDE_REGEXES cublas cublasLt cudart
PRE_EXCLUDE_REGEXES ".*"
RUNTIME DESTINATION ${OLLAMA_INSTALL_DIR} COMPONENT CUDA
LIBRARY DESTINATION ${OLLAMA_INSTALL_DIR} COMPONENT CUDA
)
endif()
set(WINDOWS_AMDGPU_TARGETS_EXCLUDE_REGEX "^gfx(906|908|90a|1200|1201):xnack[+-]$"
CACHE STRING
"Regular expression describing AMDGPU_TARGETS not supported on Windows. Override to force building these targets. Default \"^gfx(906|908|90a|1200|1201):xnack[+-]$\"."
)
check_language(HIP)
if(CMAKE_HIP_COMPILER)
set(HIP_PLATFORM "amd")
find_package(hip REQUIRED)
if(NOT AMDGPU_TARGETS)
list(FILTER AMDGPU_TARGETS INCLUDE REGEX "^gfx(900|94[012]|101[02]|1030|110[012]|120[01])$")
elseif(WIN32 AND WINDOWS_AMDGPU_TARGETS_EXCLUDE_REGEX)
list(FILTER AMDGPU_TARGETS EXCLUDE REGEX ${WINDOWS_AMDGPU_TARGETS_EXCLUDE_REGEX})
endif()
if(AMDGPU_TARGETS)
add_subdirectory(${CMAKE_CURRENT_SOURCE_DIR}/ml/backend/ggml/ggml/src/ggml-hip)
if (WIN32)
target_compile_definitions(ggml-hip PRIVATE GGML_CUDA_NO_PEER_COPY)
endif()
target_compile_definitions(ggml-hip PRIVATE GGML_HIP_NO_VMM)
set(OLLAMA_HIP_INSTALL_DIR ${OLLAMA_INSTALL_DIR}/rocm)
install(TARGETS ggml-hip
RUNTIME_DEPENDENCY_SET rocm
RUNTIME DESTINATION ${OLLAMA_INSTALL_DIR} COMPONENT HIP
LIBRARY DESTINATION ${OLLAMA_INSTALL_DIR} COMPONENT HIP
)
install(RUNTIME_DEPENDENCY_SET rocm
DIRECTORIES ${HIP_BIN_INSTALL_DIR} ${HIP_LIB_INSTALL_DIR}
PRE_INCLUDE_REGEXES hipblas rocblas amdhip64 rocsolver amd_comgr hsa-runtime64 rocsparse tinfo rocprofiler-register drm drm_amdgpu numa elf
PRE_EXCLUDE_REGEXES ".*"
POST_EXCLUDE_REGEXES "system32"
RUNTIME DESTINATION ${OLLAMA_HIP_INSTALL_DIR} COMPONENT HIP
LIBRARY DESTINATION ${OLLAMA_HIP_INSTALL_DIR} COMPONENT HIP
)
foreach(HIP_LIB_BIN_INSTALL_DIR IN ITEMS ${HIP_BIN_INSTALL_DIR} ${HIP_LIB_INSTALL_DIR})
if(EXISTS ${HIP_LIB_BIN_INSTALL_DIR}/rocblas)
install(DIRECTORY ${HIP_LIB_BIN_INSTALL_DIR}/rocblas DESTINATION ${OLLAMA_HIP_INSTALL_DIR} COMPONENT HIP)
break()
endif()
endforeach()
endif()
endif()