diff --git a/Makefile b/Makefile index 373b4abf..3efcd421 100644 --- a/Makefile +++ b/Makefile @@ -6,7 +6,7 @@ BINARY_NAME=local-ai DETECT_LIBS?=true # llama.cpp versions -CPPLLAMA_VERSION?=d98f2a35fcf4a8d3e660ad48cd19e2a1f3d5b2ef +CPPLLAMA_VERSION?=e83ba3e460651b20a594e9f2f0f0bffb998d3ce1 # whisper.cpp version WHISPER_REPO?=https://github.com/ggml-org/whisper.cpp diff --git a/backend/cpp/llama/CMakeLists.txt b/backend/cpp/llama/CMakeLists.txt index a519bb10..b68332f7 100644 --- a/backend/cpp/llama/CMakeLists.txt +++ b/backend/cpp/llama/CMakeLists.txt @@ -79,7 +79,7 @@ add_executable(${TARGET} grpc-server.cpp utils.hpp json.hpp httplib.h) target_include_directories(${TARGET} PRIVATE ../llava) target_include_directories(${TARGET} PRIVATE ${CMAKE_SOURCE_DIR}) -target_link_libraries(${TARGET} PRIVATE common llama mtmd ${CMAKE_THREAD_LIBS_INIT} absl::flags hw_grpc_proto +target_link_libraries(${TARGET} PRIVATE common llama mtmd mtmd_helper ${CMAKE_THREAD_LIBS_INIT} absl::flags hw_grpc_proto absl::flags_parse gRPC::${_REFLECTION} gRPC::${_GRPC_GRPCPP} diff --git a/backend/cpp/llama/grpc-server.cpp b/backend/cpp/llama/grpc-server.cpp index bac46095..a8b21ef3 100644 --- a/backend/cpp/llama/grpc-server.cpp +++ b/backend/cpp/llama/grpc-server.cpp @@ -433,7 +433,7 @@ public: throw std::runtime_error("This server does not support multimodal"); } for (auto & file : files) { - mtmd::bitmap bmp(mtmd_helper_bitmap_init_from_buf(file.data(), file.size())); + mtmd::bitmap bmp(mtmd_helper_bitmap_init_from_buf(ctx_server.mctx, file.data(), file.size())); if (!bmp.ptr) { throw std::runtime_error("Failed to load image/audio"); } @@ -625,7 +625,7 @@ public: throw std::runtime_error("This server does not support multimodal"); } for (auto & file : files) { - mtmd::bitmap bmp(mtmd_helper_bitmap_init_from_buf(file.data(), file.size())); + mtmd::bitmap bmp(mtmd_helper_bitmap_init_from_buf(ctx_server.mctx, file.data(), file.size())); if (!bmp.ptr) { throw std::runtime_error("Failed to load image/audio"); }