mirror of
https://github.com/mudler/LocalAI.git
synced 2026-07-09 07:48:22 -04:00
38350d363e
qwen3-tts-cpp, omnivoice-cpp, acestep-cpp and vibevoice-cpp shipped rocm-* variants that silently ran on CPU ([Load] backend: CPU). Two coupled defects: - The Makefiles passed -DGGML_HIPBLAS=ON, but the vendored ggml only understands -DGGML_HIP=ON (GGML_HIPBLAS was removed upstream), so the ggml-hip backend target was never created and no GPU code was built. - The CMake foreach that links the ggml GPU backends into the module listed blas/cuda/metal/vulkan but not hip, so even a built ggml-hip would not have been linked and its static backend registration would never run. CUDA users were unaffected because cublas passes the correct GGML_CUDA=ON and the foreach already links cuda. Mirror the proven llama-cpp hipblas block (ROCm clang CC/CXX + AMDGPU_TARGETS) and add hip to each foreach. Upstream picks the best device via ggml_backend_init_best(), so no runtime flag is needed once HIP is compiled and linked. Assisted-by: Claude:claude-opus-4-8[1m] [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
54 lines
2.2 KiB
CMake
54 lines
2.2 KiB
CMake
cmake_minimum_required(VERSION 3.14)
|
|
project(goqwen3ttscpp LANGUAGES C CXX)
|
|
set(CMAKE_POSITION_INDEPENDENT_CODE ON)
|
|
set(CMAKE_EXPORT_COMPILE_COMMANDS ON)
|
|
|
|
set(QWENTTS_DIR ${CMAKE_CURRENT_SOURCE_DIR}/sources/qwentts.cpp)
|
|
|
|
# Override upstream's CMAKE_CUDA_ARCHITECTURES before add_subdirectory.
|
|
if(NOT DEFINED CMAKE_CUDA_ARCHITECTURES)
|
|
set(CMAKE_CUDA_ARCHITECTURES "75-virtual;80-virtual;86-real;89-real")
|
|
endif()
|
|
|
|
# Add the upstream project. Its own CMakeLists adds ggml + cpp-httplib + yyjson
|
|
# and builds qwen-core (STATIC, the qt_* impl). EXCLUDE_FROM_ALL keeps its CLI
|
|
# tools / tts-server / tests from building unless referenced.
|
|
add_subdirectory(${QWENTTS_DIR} qwentts EXCLUDE_FROM_ALL)
|
|
|
|
# Upstream generates version.h into its own CMAKE_CURRENT_BINARY_DIR and adds
|
|
# the top-level ${CMAKE_BINARY_DIR} to qwen-core's include path. Under
|
|
# add_subdirectory those two dirs differ (<build>/qwentts vs <build>), so
|
|
# qwen.cpp cannot find version.h. Point qwen-core at the subproject binary dir
|
|
# where version.h is actually generated. (Fix lives here, never in the fetched
|
|
# upstream checkout.)
|
|
target_include_directories(qwen-core PRIVATE ${CMAKE_BINARY_DIR}/qwentts)
|
|
|
|
add_library(goqwen3ttscpp MODULE cpp/goqwen3ttscpp.cpp)
|
|
target_link_libraries(goqwen3ttscpp PRIVATE qwen-core)
|
|
|
|
target_include_directories(goqwen3ttscpp PRIVATE ${QWENTTS_DIR}/src)
|
|
target_include_directories(goqwen3ttscpp SYSTEM PRIVATE ${QWENTTS_DIR}/ggml/include)
|
|
|
|
# Link GPU backends if the upstream ggml created them.
|
|
foreach(backend blas cuda hip metal vulkan sycl)
|
|
if(TARGET ggml-${backend})
|
|
target_link_libraries(goqwen3ttscpp PRIVATE ggml-${backend})
|
|
if(backend STREQUAL "cuda")
|
|
find_package(CUDAToolkit QUIET)
|
|
if(CUDAToolkit_FOUND)
|
|
target_link_libraries(goqwen3ttscpp PRIVATE CUDA::cudart)
|
|
endif()
|
|
endif()
|
|
endif()
|
|
endforeach()
|
|
|
|
if(MSVC)
|
|
target_compile_options(goqwen3ttscpp PRIVATE /W4 /wd4100 /wd4505)
|
|
else()
|
|
target_compile_options(goqwen3ttscpp PRIVATE -Wall -Wextra
|
|
-Wno-unused-parameter -Wno-unused-function)
|
|
endif()
|
|
|
|
set_property(TARGET goqwen3ttscpp PROPERTY CXX_STANDARD 17)
|
|
set_target_properties(goqwen3ttscpp PROPERTIES LIBRARY_OUTPUT_DIRECTORY ${CMAKE_BINARY_DIR})
|