Files
LocalAI/backend/go/acestep-cpp/Makefile
Ettore Di Giacinto 2aedd2cf44 fix(backends): enable ROCm/HIP GPU offload for ggml audio backends (#10666)
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.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:claude-opus-4-8[1m] [Claude Code]
2026-07-03 20:28:11 +00:00

136 lines
4.5 KiB
Makefile

CMAKE_ARGS?=
BUILD_TYPE?=
NATIVE?=false
GOCMD?=go
GO_TAGS?=
JOBS?=$(shell nproc --ignore=1)
# acestep.cpp version
ACESTEP_REPO?=https://github.com/ace-step/acestep.cpp
ACESTEP_CPP_VERSION?=ed53caf164e4492a5620b2e3f2264629cf66da24
SO_TARGET?=libgoacestepcpp.so
CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF
ifeq ($(NATIVE),false)
CMAKE_ARGS+=-DGGML_NATIVE=OFF
endif
ifeq ($(BUILD_TYPE),cublas)
CMAKE_ARGS+=-DGGML_CUDA=ON
else ifeq ($(BUILD_TYPE),openblas)
CMAKE_ARGS+=-DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS
else ifeq ($(BUILD_TYPE),clblas)
CMAKE_ARGS+=-DGGML_CLBLAST=ON -DCLBlast_DIR=/some/path
else ifeq ($(BUILD_TYPE),hipblas)
# This ggml only understands GGML_HIP (GGML_HIPBLAS was removed upstream),
# so passing GGML_HIPBLAS silently produced a CPU-only build (see #10666).
ROCM_HOME ?= /opt/rocm
ROCM_PATH ?= /opt/rocm
export CXX=$(ROCM_HOME)/llvm/bin/clang++
export CC=$(ROCM_HOME)/llvm/bin/clang
AMDGPU_TARGETS ?= gfx908,gfx90a,gfx942,gfx950,gfx1030,gfx1100,gfx1101,gfx1102,gfx1151,gfx1200,gfx1201
CMAKE_ARGS+=-DGGML_HIP=ON -DAMDGPU_TARGETS=$(AMDGPU_TARGETS)
else ifeq ($(BUILD_TYPE),vulkan)
CMAKE_ARGS+=-DGGML_VULKAN=ON
else ifeq ($(OS),Darwin)
ifneq ($(BUILD_TYPE),metal)
CMAKE_ARGS+=-DGGML_METAL=OFF
else
CMAKE_ARGS+=-DGGML_METAL=ON
CMAKE_ARGS+=-DGGML_METAL_EMBED_LIBRARY=ON
endif
endif
ifeq ($(BUILD_TYPE),sycl_f16)
CMAKE_ARGS+=-DGGML_SYCL=ON \
-DCMAKE_C_COMPILER=icx \
-DCMAKE_CXX_COMPILER=icpx \
-DGGML_SYCL_F16=ON
endif
ifeq ($(BUILD_TYPE),sycl_f32)
CMAKE_ARGS+=-DGGML_SYCL=ON \
-DCMAKE_C_COMPILER=icx \
-DCMAKE_CXX_COMPILER=icpx
endif
sources/acestep.cpp:
mkdir -p sources/acestep.cpp
cd sources/acestep.cpp && \
git init && \
git remote add origin $(ACESTEP_REPO) && \
git fetch origin && \
git checkout $(ACESTEP_CPP_VERSION) && \
git submodule update --init --recursive --depth 1 --single-branch
# Detect OS
UNAME_S := $(shell uname -s)
# Only build CPU variants on Linux
ifeq ($(UNAME_S),Linux)
VARIANT_TARGETS = libgoacestepcpp-avx.so libgoacestepcpp-avx2.so libgoacestepcpp-avx512.so libgoacestepcpp-fallback.so
else
# On non-Linux (e.g., Darwin), build only fallback variant
VARIANT_TARGETS = libgoacestepcpp-fallback.so
endif
acestep-cpp: main.go goacestepcpp.go $(VARIANT_TARGETS)
CGO_ENABLED=0 $(GOCMD) build -tags "$(GO_TAGS)" -o acestep-cpp ./
package: acestep-cpp
bash package.sh
build: package
clean: purge
rm -rf libgoacestepcpp*.so package sources/acestep.cpp acestep-cpp
purge:
rm -rf build*
# Variants must build sequentially: each uses its own build-<name> directory,
# but parallel builds can still race on shared resources (jobserver, disk I/O).
.NOTPARALLEL:
# Build all variants (Linux only)
ifeq ($(UNAME_S),Linux)
libgoacestepcpp-avx.so: sources/acestep.cpp
$(info ${GREEN}I acestep-cpp build info:avx${RESET})
SO_TARGET=libgoacestepcpp-avx.so CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libgoacestepcpp-custom
rm -rf build-libgoacestepcpp-avx.so
libgoacestepcpp-avx2.so: sources/acestep.cpp
$(info ${GREEN}I acestep-cpp build info:avx2${RESET})
SO_TARGET=libgoacestepcpp-avx2.so CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=on -DGGML_AVX512=off -DGGML_FMA=on -DGGML_F16C=on -DGGML_BMI2=on" $(MAKE) libgoacestepcpp-custom
rm -rf build-libgoacestepcpp-avx2.so
libgoacestepcpp-avx512.so: sources/acestep.cpp
$(info ${GREEN}I acestep-cpp build info:avx512${RESET})
SO_TARGET=libgoacestepcpp-avx512.so CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=on -DGGML_AVX512=on -DGGML_FMA=on -DGGML_F16C=on -DGGML_BMI2=on" $(MAKE) libgoacestepcpp-custom
rm -rf build-libgoacestepcpp-avx512.so
endif
# Build fallback variant (all platforms)
libgoacestepcpp-fallback.so: sources/acestep.cpp
$(info ${GREEN}I acestep-cpp build info:fallback${RESET})
SO_TARGET=libgoacestepcpp-fallback.so CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libgoacestepcpp-custom
rm -rf build-libgoacestepcpp-fallback.so
libgoacestepcpp-custom: CMakeLists.txt cpp/goacestepcpp.cpp cpp/goacestepcpp.h
mkdir -p build-$(SO_TARGET) && \
cd build-$(SO_TARGET) && \
cmake .. $(CMAKE_ARGS) && \
cmake --build . --config Release -j$(JOBS) --target goacestepcpp && \
cd .. && \
(mv build-$(SO_TARGET)/libgoacestepcpp.so ./$(SO_TARGET) 2>/dev/null || \
mv build-$(SO_TARGET)/libgoacestepcpp.dylib ./$(SO_TARGET) 2>/dev/null)
test: acestep-cpp
@echo "Running acestep-cpp tests..."
bash test.sh
@echo "acestep-cpp tests completed."
all: acestep-cpp package