mirror of
https://github.com/mudler/LocalAI.git
synced 2026-06-28 10:27:30 -04:00
d3a26f961d
* fix(ik-llama): port multimodal path to mtmd API and bump to f96eaddb (#10534) The IK_LLAMA_VERSION bump to f96eaddba8bed6a9a5e628bbf6a566775c70b49c pulls in upstream commit "Prune examples/llava", which deletes examples/llava (clip.* / llava.*). The ik-llama backend's grpc-server.cpp built a local `myclip` library from those files and called the removed clip/llava C API, so the bump no longer builds. ik_llama keeps its multimodal stack in the surviving `mtmd` library (examples/mtmd/, public headers mtmd.h + mtmd-helper.h). This ports the backend's multimodal path onto the high-level mtmd_* / mtmd_helper_* API in place, leaving the text path (which still uses ik_llama's retained old common API) untouched: - Makefile: bump IK_LLAMA_VERSION to f96eaddb. - prepare.sh: drop the clip/llava source copy + sed block; mtmd is a library target, no source copy needed. - CMakeLists.txt: remove the `myclip` target; link `mtmd` and add its include dir; build grpc-server as C++17 (mtmd headers require it). - patches: drop 0002 (targeted the deleted examples/llava/clip.cpp; the mtmd clip.cpp never calls ggml_quantize_chunk, so the fix is unneeded). Keep 0001 (verified still applies). - grpc-server.cpp / utils.hpp: replace clip_model_load + clip_image_load_from_bytes + llava_image_embed_make_with_clip_img + the manual [img-N] prefix splitting and per-image llava_embd_batch decode loop with mtmd_init_from_file (moved after the model load, which it requires), mtmd_helper_bitmap_init_from_buf, mtmd_tokenize and mtmd_helper_eval_chunks. Legacy [img-N] tags are translated, in order, into mtmd media markers (mtmd_default_marker()); the post-image suffix text stays on the normal token path so the sampling loop is unchanged. Supersedes #10534. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-8 [Claude Code] * fix(ik-llama): align json alias to ordered_json to resolve mtmd.h conflict (#10534) mtmd.h declares `using json = nlohmann::ordered_json` at global scope (and its mtmd.cpp depends on it), while ik_llama's whole server/common stack also uses ordered_json. Our grpc-server.cpp/utils.hpp kept a plain `nlohmann::json` alias, which now collides with mtmd.h once it is included for the multimodal port: "conflicting declaration 'using json = ...'". Switch our two aliases to ordered_json to match; it is API-compatible (utils.hpp already used ordered_json for its log helper) and our json never crosses into an unordered-json API. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-8 [Claude Code] --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
74 lines
2.7 KiB
CMake
74 lines
2.7 KiB
CMake
## Multimodal support is provided by the in-tree `mtmd` library target
|
|
## (examples/mtmd/), which the grpc-server links and includes below. clip/llava
|
|
## were pruned upstream; the high-level mtmd_* / mtmd_helper_* API is used instead.
|
|
|
|
set(TARGET grpc-server)
|
|
set(CMAKE_CXX_STANDARD 17)
|
|
cmake_minimum_required(VERSION 3.15)
|
|
set(TARGET grpc-server)
|
|
set(_PROTOBUF_LIBPROTOBUF libprotobuf)
|
|
set(_REFLECTION grpc++_reflection)
|
|
|
|
if (${CMAKE_SYSTEM_NAME} MATCHES "Darwin")
|
|
if (CMAKE_HOST_SYSTEM_PROCESSOR MATCHES "arm64")
|
|
set(HOMEBREW_DEFAULT_PREFIX "/opt/homebrew")
|
|
else()
|
|
set(HOMEBREW_DEFAULT_PREFIX "/usr/local")
|
|
endif()
|
|
link_directories("${HOMEBREW_DEFAULT_PREFIX}/lib")
|
|
include_directories("${HOMEBREW_DEFAULT_PREFIX}/include")
|
|
endif()
|
|
|
|
find_package(absl CONFIG REQUIRED)
|
|
find_package(Protobuf CONFIG REQUIRED)
|
|
find_package(gRPC CONFIG REQUIRED)
|
|
|
|
find_program(_PROTOBUF_PROTOC protoc)
|
|
set(_GRPC_GRPCPP grpc++)
|
|
find_program(_GRPC_CPP_PLUGIN_EXECUTABLE grpc_cpp_plugin)
|
|
|
|
include_directories(${CMAKE_CURRENT_BINARY_DIR})
|
|
include_directories(${Protobuf_INCLUDE_DIRS})
|
|
|
|
message(STATUS "Using protobuf version ${Protobuf_VERSION} | Protobuf_INCLUDE_DIRS: ${Protobuf_INCLUDE_DIRS} | CMAKE_CURRENT_BINARY_DIR: ${CMAKE_CURRENT_BINARY_DIR}")
|
|
|
|
# Proto file
|
|
get_filename_component(hw_proto "../../../../../../backend/backend.proto" ABSOLUTE)
|
|
get_filename_component(hw_proto_path "${hw_proto}" PATH)
|
|
|
|
set(hw_proto_srcs "${CMAKE_CURRENT_BINARY_DIR}/backend.pb.cc")
|
|
set(hw_proto_hdrs "${CMAKE_CURRENT_BINARY_DIR}/backend.pb.h")
|
|
set(hw_grpc_srcs "${CMAKE_CURRENT_BINARY_DIR}/backend.grpc.pb.cc")
|
|
set(hw_grpc_hdrs "${CMAKE_CURRENT_BINARY_DIR}/backend.grpc.pb.h")
|
|
|
|
add_custom_command(
|
|
OUTPUT "${hw_proto_srcs}" "${hw_proto_hdrs}" "${hw_grpc_srcs}" "${hw_grpc_hdrs}"
|
|
COMMAND ${_PROTOBUF_PROTOC}
|
|
ARGS --grpc_out "${CMAKE_CURRENT_BINARY_DIR}"
|
|
--cpp_out "${CMAKE_CURRENT_BINARY_DIR}"
|
|
-I "${hw_proto_path}"
|
|
--plugin=protoc-gen-grpc="${_GRPC_CPP_PLUGIN_EXECUTABLE}"
|
|
"${hw_proto}"
|
|
DEPENDS "${hw_proto}")
|
|
|
|
add_library(hw_grpc_proto
|
|
${hw_grpc_srcs}
|
|
${hw_grpc_hdrs}
|
|
${hw_proto_srcs}
|
|
${hw_proto_hdrs} )
|
|
|
|
add_executable(${TARGET} grpc-server.cpp json.hpp)
|
|
# mtmd public headers (mtmd.h / mtmd-helper.h) live in examples/mtmd/.
|
|
# Linking the mtmd target also propagates this include dir, but we add it
|
|
# explicitly for clarity.
|
|
target_include_directories(${TARGET} PRIVATE ../mtmd)
|
|
target_link_libraries(${TARGET} PRIVATE common llama mtmd ${CMAKE_THREAD_LIBS_INIT} absl::flags hw_grpc_proto
|
|
absl::flags_parse
|
|
gRPC::${_REFLECTION}
|
|
gRPC::${_GRPC_GRPCPP}
|
|
protobuf::${_PROTOBUF_LIBPROTOBUF})
|
|
target_compile_features(${TARGET} PRIVATE cxx_std_17)
|
|
if(TARGET BUILD_INFO)
|
|
add_dependencies(${TARGET} BUILD_INFO)
|
|
endif()
|