mirror of
https://github.com/mudler/LocalAI.git
synced 2026-07-05 13:57:28 -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>
55 lines
2.4 KiB
CMake
55 lines
2.4 KiB
CMake
cmake_minimum_required(VERSION 3.14)
|
|
project(goacestepcpp LANGUAGES C CXX)
|
|
set(CMAKE_POSITION_INDEPENDENT_CODE ON)
|
|
set(CMAKE_EXPORT_COMPILE_COMMANDS ON)
|
|
|
|
set(ACESTEP_DIR ${CMAKE_CURRENT_SOURCE_DIR}/sources/acestep.cpp)
|
|
|
|
# Override upstream's CMAKE_CUDA_ARCHITECTURES before add_subdirectory.
|
|
# Upstream sets 120a/121a for CUDA >= 12.8, but those archs require a newer
|
|
# toolkit than 12.8.x ships. Pre-defining this variable makes the upstream
|
|
# "if(NOT DEFINED CMAKE_CUDA_ARCHITECTURES)" guard skip its broken defaults.
|
|
if(NOT DEFINED CMAKE_CUDA_ARCHITECTURES)
|
|
set(CMAKE_CUDA_ARCHITECTURES "75-virtual;80-virtual;86-real;89-real")
|
|
endif()
|
|
|
|
# EXCLUDE_FROM_ALL: only build targets we explicitly depend on (acestep-core, ggml),
|
|
# skip upstream standalone executables (ace-understand, dit-vae, etc.)
|
|
add_subdirectory(${ACESTEP_DIR} acestep EXCLUDE_FROM_ALL)
|
|
|
|
add_library(goacestepcpp MODULE cpp/goacestepcpp.cpp)
|
|
target_link_libraries(goacestepcpp PRIVATE acestep-core ggml ggml-base ggml-cpu)
|
|
|
|
# Include dirs matching link_ggml_backends macro, but with absolute paths
|
|
target_include_directories(goacestepcpp PRIVATE ${ACESTEP_DIR}/src ${ACESTEP_DIR})
|
|
target_include_directories(goacestepcpp SYSTEM PRIVATE ${ACESTEP_DIR}/ggml/include)
|
|
|
|
# Link GPU backends if available (mirrors link_ggml_backends macro)
|
|
foreach(backend blas cuda hip metal vulkan)
|
|
if(TARGET ggml-${backend})
|
|
target_link_libraries(goacestepcpp PRIVATE ggml-${backend})
|
|
string(TOUPPER ${backend} BACKEND_UPPER)
|
|
target_compile_definitions(goacestepcpp PRIVATE ACESTEP_HAVE_${BACKEND_UPPER})
|
|
if(backend STREQUAL "cuda")
|
|
find_package(CUDAToolkit QUIET)
|
|
if(CUDAToolkit_FOUND)
|
|
target_link_libraries(goacestepcpp PRIVATE CUDA::cudart)
|
|
endif()
|
|
endif()
|
|
endif()
|
|
endforeach()
|
|
|
|
if(MSVC)
|
|
target_compile_options(goacestepcpp PRIVATE /W4 /wd4100 /wd4505)
|
|
else()
|
|
target_compile_options(goacestepcpp PRIVATE -Wall -Wextra -Wshadow -Wconversion
|
|
-Wno-unused-parameter -Wno-unused-function -Wno-sign-conversion)
|
|
endif()
|
|
|
|
if(CMAKE_CXX_COMPILER_ID MATCHES "GNU" AND CMAKE_CXX_COMPILER_VERSION VERSION_LESS 9.0)
|
|
target_link_libraries(goacestepcpp PRIVATE stdc++fs)
|
|
endif()
|
|
|
|
set_property(TARGET goacestepcpp PROPERTY CXX_STANDARD 17)
|
|
set_target_properties(goacestepcpp PROPERTIES LIBRARY_OUTPUT_DIRECTORY ${CMAKE_BINARY_DIR})
|