feat(backends): add ace-step.cpp (#8965)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto
2026-03-12 18:56:26 +01:00
committed by GitHub
parent 8f3efaed15
commit a738f8b0e4
17 changed files with 1355 additions and 3 deletions

View File

@@ -535,6 +535,19 @@ jobs:
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "8"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-12-acestep-cpp'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "acestep-cpp"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "8"
@@ -1069,6 +1082,32 @@ jobs:
backend: "whisper"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-nvidia-cuda-13-acestep-cpp'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "acestep-cpp"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
platforms: 'linux/arm64'
skip-drivers: 'false'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-cuda-13-arm64-acestep-cpp'
base-image: "ubuntu:24.04"
ubuntu-version: '2404'
runs-on: 'ubuntu-24.04-arm'
backend: "acestep-cpp"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
- build-type: 'cublas'
cuda-major-version: "13"
cuda-minor-version: "0"
@@ -1882,6 +1921,85 @@ jobs:
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
# acestep-cpp
- build-type: ''
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64,linux/arm64'
tag-latest: 'auto'
tag-suffix: '-cpu-acestep-cpp'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "acestep-cpp"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
- build-type: 'sycl_f32'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-intel-sycl-f32-acestep-cpp'
runs-on: 'ubuntu-latest'
base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
skip-drivers: 'false'
backend: "acestep-cpp"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
- build-type: 'sycl_f16'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-intel-sycl-f16-acestep-cpp'
runs-on: 'ubuntu-latest'
base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
skip-drivers: 'false'
backend: "acestep-cpp"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
- build-type: 'vulkan'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64,linux/arm64'
tag-latest: 'auto'
tag-suffix: '-gpu-vulkan-acestep-cpp'
runs-on: 'ubuntu-latest'
base-image: "ubuntu:24.04"
skip-drivers: 'false'
backend: "acestep-cpp"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
- build-type: 'cublas'
cuda-major-version: "12"
cuda-minor-version: "0"
platforms: 'linux/arm64'
skip-drivers: 'false'
tag-latest: 'auto'
tag-suffix: '-nvidia-l4t-arm64-acestep-cpp'
base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
runs-on: 'ubuntu-24.04-arm'
backend: "acestep-cpp"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2204'
- build-type: 'hipblas'
cuda-major-version: ""
cuda-minor-version: ""
platforms: 'linux/amd64'
tag-latest: 'auto'
tag-suffix: '-gpu-rocm-hipblas-acestep-cpp'
base-image: "rocm/dev-ubuntu-24.04:6.4.4"
runs-on: 'ubuntu-latest'
skip-drivers: 'false'
backend: "acestep-cpp"
dockerfile: "./backend/Dockerfile.golang"
context: "./"
ubuntu-version: '2404'
# voxtral
- build-type: ''
cuda-major-version: ""
@@ -2183,6 +2301,10 @@ jobs:
tag-suffix: "-metal-darwin-arm64-whisper"
build-type: "metal"
lang: "go"
- backend: "acestep-cpp"
tag-suffix: "-metal-darwin-arm64-acestep-cpp"
build-type: "metal"
lang: "go"
- backend: "voxtral"
tag-suffix: "-metal-darwin-arm64-voxtral"
build-type: "metal"

View File

@@ -30,6 +30,10 @@ jobs:
variable: "VOXTRAL_VERSION"
branch: "main"
file: "backend/go/voxtral/Makefile"
- repository: "ace-step/acestep.cpp"
variable: "ACESTEP_CPP_VERSION"
branch: "master"
file: "backend/go/acestep-cpp/Makefile"
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v6

View File

@@ -383,6 +383,36 @@ jobs:
run: |
make --jobs=5 --output-sync=target -C backend/python/voxcpm
make --jobs=5 --output-sync=target -C backend/python/voxcpm test
tests-acestep-cpp:
runs-on: ubuntu-latest
steps:
- name: Clone
uses: actions/checkout@v6
with:
submodules: true
- name: Dependencies
run: |
sudo apt-get update
sudo apt-get install -y build-essential cmake curl libopenblas-dev ffmpeg
- name: Setup Go
uses: actions/setup-go@v5
- name: Display Go version
run: go version
- name: Proto Dependencies
run: |
# Install protoc
curl -L -s https://github.com/protocolbuffers/protobuf/releases/download/v26.1/protoc-26.1-linux-x86_64.zip -o protoc.zip && \
unzip -j -d /usr/local/bin protoc.zip bin/protoc && \
rm protoc.zip
go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.2
go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@1958fcbe2ca8bd93af633f11e97d44e567e945af
PATH="$PATH:$HOME/go/bin" make protogen-go
- name: Build acestep-cpp
run: |
make --jobs=5 --output-sync=target -C backend/go/acestep-cpp
- name: Test acestep-cpp
run: |
make --jobs=5 --output-sync=target -C backend/go/acestep-cpp test
tests-voxtral:
runs-on: ubuntu-latest
steps:

View File

@@ -1,5 +1,5 @@
# Disable parallel execution for backend builds
.NOTPARALLEL: backends/diffusers backends/llama-cpp backends/outetts backends/piper backends/stablediffusion-ggml backends/whisper backends/faster-whisper backends/silero-vad backends/local-store backends/huggingface backends/rfdetr backends/kitten-tts backends/kokoro backends/chatterbox backends/llama-cpp-darwin backends/neutts build-darwin-python-backend build-darwin-go-backend backends/mlx backends/diffuser-darwin backends/mlx-vlm backends/mlx-audio backends/mlx-distributed backends/stablediffusion-ggml-darwin backends/vllm backends/vllm-omni backends/moonshine backends/pocket-tts backends/qwen-tts backends/faster-qwen3-tts backends/qwen-asr backends/nemo backends/voxcpm backends/whisperx backends/ace-step backends/fish-speech backends/voxtral
.NOTPARALLEL: backends/diffusers backends/llama-cpp backends/outetts backends/piper backends/stablediffusion-ggml backends/whisper backends/faster-whisper backends/silero-vad backends/local-store backends/huggingface backends/rfdetr backends/kitten-tts backends/kokoro backends/chatterbox backends/llama-cpp-darwin backends/neutts build-darwin-python-backend build-darwin-go-backend backends/mlx backends/diffuser-darwin backends/mlx-vlm backends/mlx-audio backends/mlx-distributed backends/stablediffusion-ggml-darwin backends/vllm backends/vllm-omni backends/moonshine backends/pocket-tts backends/qwen-tts backends/faster-qwen3-tts backends/qwen-asr backends/nemo backends/voxcpm backends/whisperx backends/ace-step backends/acestep-cpp backends/fish-speech backends/voxtral
GOCMD=go
GOTEST=$(GOCMD) test
@@ -476,6 +476,7 @@ BACKEND_SILERO_VAD = silero-vad|golang|.|false|true
BACKEND_STABLEDIFFUSION_GGML = stablediffusion-ggml|golang|.|--progress=plain|true
BACKEND_WHISPER = whisper|golang|.|false|true
BACKEND_VOXTRAL = voxtral|golang|.|false|true
BACKEND_ACESTEP_CPP = acestep-cpp|golang|.|false|true
# Python backends with root context
BACKEND_RERANKERS = rerankers|python|.|false|true
@@ -557,13 +558,14 @@ $(eval $(call generate-docker-build-target,$(BACKEND_NEMO)))
$(eval $(call generate-docker-build-target,$(BACKEND_VOXCPM)))
$(eval $(call generate-docker-build-target,$(BACKEND_WHISPERX)))
$(eval $(call generate-docker-build-target,$(BACKEND_ACE_STEP)))
$(eval $(call generate-docker-build-target,$(BACKEND_ACESTEP_CPP)))
$(eval $(call generate-docker-build-target,$(BACKEND_MLX_DISTRIBUTED)))
# Pattern rule for docker-save targets
docker-save-%: backend-images
docker save local-ai-backend:$* -o backend-images/$*.tar
docker-build-backends: docker-build-llama-cpp docker-build-rerankers docker-build-vllm docker-build-vllm-omni docker-build-transformers docker-build-outetts docker-build-diffusers docker-build-kokoro docker-build-faster-whisper docker-build-coqui docker-build-chatterbox docker-build-vibevoice docker-build-moonshine docker-build-pocket-tts docker-build-qwen-tts docker-build-fish-speech docker-build-faster-qwen3-tts docker-build-qwen-asr docker-build-nemo docker-build-voxcpm docker-build-whisperx docker-build-ace-step docker-build-voxtral docker-build-mlx-distributed
docker-build-backends: docker-build-llama-cpp docker-build-rerankers docker-build-vllm docker-build-vllm-omni docker-build-transformers docker-build-outetts docker-build-diffusers docker-build-kokoro docker-build-faster-whisper docker-build-coqui docker-build-chatterbox docker-build-vibevoice docker-build-moonshine docker-build-pocket-tts docker-build-qwen-tts docker-build-fish-speech docker-build-faster-qwen3-tts docker-build-qwen-asr docker-build-nemo docker-build-voxcpm docker-build-whisperx docker-build-ace-step docker-build-acestep-cpp docker-build-voxtral docker-build-mlx-distributed
########################################################
### Mock Backend for E2E Tests

View File

@@ -0,0 +1,54 @@
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 ${ACESTEP_DIR}/ggml/include)
# Link GPU backends if available (mirrors link_ggml_backends macro)
foreach(backend blas cuda metal vulkan)
if(TARGET ggml-${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})

View File

@@ -0,0 +1,127 @@
CMAKE_ARGS?=
BUILD_TYPE?=
NATIVE?=false
GOCMD?=go
GO_TAGS?=
JOBS?=$(shell nproc --ignore=1)
# acestep.cpp version
ACESTEP_REPO?=https://github.com/ace-step/acestep.cpp
ACESTEP_CPP_VERSION?=master
SO_TARGET?=libgoacestepcpp.so
CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF
ifeq ($(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)
CMAKE_ARGS+=-DGGML_HIPBLAS=ON
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)
test: acestep-cpp
@echo "Running acestep-cpp tests..."
bash test.sh
@echo "acestep-cpp tests completed."
all: acestep-cpp package

View File

@@ -0,0 +1,195 @@
package main
import (
"context"
"os"
"os/exec"
"path/filepath"
"testing"
"time"
pb "github.com/mudler/LocalAI/pkg/grpc/proto"
"google.golang.org/grpc"
"google.golang.org/grpc/credentials/insecure"
)
const (
testAddr = "localhost:50051"
startupWait = 5 * time.Second
)
func skipIfNoModel(t *testing.T) string {
t.Helper()
modelDir := os.Getenv("ACESTEP_MODEL_DIR")
if modelDir == "" {
t.Skip("ACESTEP_MODEL_DIR not set, skipping test (set to directory with GGUF models)")
}
if _, err := os.Stat(filepath.Join(modelDir, "acestep-5Hz-lm-0.6B-Q8_0.gguf")); os.IsNotExist(err) {
t.Skipf("LM model file not found in %s, skipping", modelDir)
}
if _, err := os.Stat(filepath.Join(modelDir, "Qwen3-Embedding-0.6B-Q8_0.gguf")); os.IsNotExist(err) {
t.Skipf("Text encoder model file not found in %s, skipping", modelDir)
}
if _, err := os.Stat(filepath.Join(modelDir, "acestep-v15-turbo-Q8_0.gguf")); os.IsNotExist(err) {
t.Skipf("DiT model file not found in %s, skipping", modelDir)
}
if _, err := os.Stat(filepath.Join(modelDir, "vae-BF16.gguf")); os.IsNotExist(err) {
t.Skipf("VAE model file not found in %s, skipping", modelDir)
}
return modelDir
}
func startServer(t *testing.T) *exec.Cmd {
t.Helper()
binary := os.Getenv("ACESTEP_BINARY")
if binary == "" {
binary = "./acestep-cpp"
}
if _, err := os.Stat(binary); os.IsNotExist(err) {
t.Skipf("Backend binary not found at %s, skipping", binary)
}
cmd := exec.Command(binary, "--addr", testAddr)
cmd.Stdout = os.Stderr
cmd.Stderr = os.Stderr
if err := cmd.Start(); err != nil {
t.Fatalf("Failed to start server: %v", err)
}
time.Sleep(startupWait)
return cmd
}
func stopServer(cmd *exec.Cmd) {
if cmd != nil && cmd.Process != nil {
cmd.Process.Kill()
cmd.Wait()
}
}
func dialGRPC(t *testing.T) *grpc.ClientConn {
t.Helper()
conn, err := grpc.Dial(testAddr,
grpc.WithTransportCredentials(insecure.NewCredentials()),
grpc.WithDefaultCallOptions(
grpc.MaxCallRecvMsgSize(50*1024*1024),
grpc.MaxCallSendMsgSize(50*1024*1024),
),
)
if err != nil {
t.Fatalf("Failed to dial gRPC: %v", err)
}
return conn
}
func TestServerHealth(t *testing.T) {
cmd := startServer(t)
defer stopServer(cmd)
conn := dialGRPC(t)
defer conn.Close()
client := pb.NewBackendClient(conn)
resp, err := client.Health(context.Background(), &pb.HealthMessage{})
if err != nil {
t.Fatalf("Health check failed: %v", err)
}
if string(resp.Message) != "OK" {
t.Fatalf("Expected OK, got %s", string(resp.Message))
}
}
func TestLoadModel(t *testing.T) {
modelDir := skipIfNoModel(t)
cmd := startServer(t)
defer stopServer(cmd)
conn := dialGRPC(t)
defer conn.Close()
client := pb.NewBackendClient(conn)
resp, err := client.LoadModel(context.Background(), &pb.ModelOptions{
ModelFile: filepath.Join(modelDir, "acestep-5Hz-lm-0.6B-Q8_0.gguf"),
Options: []string{
"text_encoder_model:" + filepath.Join(modelDir, "Qwen3-Embedding-0.6B-Q8_0.gguf"),
"dit_model:" + filepath.Join(modelDir, "acestep-v15-turbo-Q8_0.gguf"),
"vae_model:" + filepath.Join(modelDir, "vae-BF16.gguf"),
},
})
if err != nil {
t.Fatalf("LoadModel failed: %v", err)
}
if !resp.Success {
t.Fatalf("LoadModel returned failure: %s", resp.Message)
}
}
func TestSoundGeneration(t *testing.T) {
modelDir := skipIfNoModel(t)
tmpDir, err := os.MkdirTemp("", "acestep-test")
if err != nil {
t.Fatal(err)
}
defer os.RemoveAll(tmpDir)
outputFile := filepath.Join(tmpDir, "output.wav")
cmd := startServer(t)
defer stopServer(cmd)
conn := dialGRPC(t)
defer conn.Close()
client := pb.NewBackendClient(conn)
// Load models
loadResp, err := client.LoadModel(context.Background(), &pb.ModelOptions{
ModelFile: filepath.Join(modelDir, "acestep-5Hz-lm-0.6B-Q8_0.gguf"),
Options: []string{
"text_encoder_model:" + filepath.Join(modelDir, "Qwen3-Embedding-0.6B-Q8_0.gguf"),
"dit_model:" + filepath.Join(modelDir, "acestep-v15-turbo-Q8_0.gguf"),
"vae_model:" + filepath.Join(modelDir, "vae-BF16.gguf"),
},
})
if err != nil {
t.Fatalf("LoadModel failed: %v", err)
}
if !loadResp.Success {
t.Fatalf("LoadModel returned failure: %s", loadResp.Message)
}
// Generate music
duration := float32(10.0)
temperature := float32(0.85)
bpm := int32(120)
caption := "A cheerful electronic dance track"
timesig := "4/4"
_, err = client.SoundGeneration(context.Background(), &pb.SoundGenerationRequest{
Text: caption,
Caption: &caption,
Dst: outputFile,
Duration: &duration,
Temperature: &temperature,
Bpm: &bpm,
Timesignature: &timesig,
})
if err != nil {
t.Fatalf("SoundGeneration failed: %v", err)
}
// Verify output file exists and has content
info, err := os.Stat(outputFile)
if os.IsNotExist(err) {
t.Fatal("Output audio file was not created")
}
if err != nil {
t.Fatalf("Failed to stat output file: %v", err)
}
t.Logf("Output file size: %d bytes", info.Size())
// WAV header is 44 bytes minimum; any real audio should be much larger
if info.Size() < 1000 {
t.Errorf("Output file too small (%d bytes), expected real audio data", info.Size())
}
}

View File

@@ -0,0 +1,306 @@
#include "goacestepcpp.h"
#include "ggml-backend.h"
#include "audio-io.h"
#include "bpe.h"
#include "cond-enc.h"
#include "dit-sampler.h"
#include "dit.h"
#include "gguf-weights.h"
#include "philox.h"
#include "qwen3-enc.h"
#include "qwen3-lm.h"
#include "request.h"
#include "vae.h"
#include <cmath>
#include <cstdio>
#include <cstdlib>
#include <cstring>
#include <random>
#include <string>
#include <vector>
// Global model contexts (loaded once, reused across requests)
static DiTGGML g_dit = {};
static DiTGGMLConfig g_dit_cfg;
static VAEGGML g_vae = {};
static bool g_dit_loaded = false;
static bool g_vae_loaded = false;
static bool g_is_turbo = false;
// Silence latent [15000, 64] — read once from DiT GGUF
static std::vector<float> g_silence_full;
// Paths for per-request loading (text encoder, tokenizer)
static std::string g_text_enc_path;
static std::string g_dit_path;
static std::string g_lm_path;
static void ggml_log_cb(enum ggml_log_level level, const char * log, void * data) {
const char * level_str;
if (!log)
return;
switch (level) {
case GGML_LOG_LEVEL_DEBUG:
level_str = "DEBUG";
break;
case GGML_LOG_LEVEL_INFO:
level_str = "INFO";
break;
case GGML_LOG_LEVEL_WARN:
level_str = "WARN";
break;
case GGML_LOG_LEVEL_ERROR:
level_str = "ERROR";
break;
default:
level_str = "?????";
break;
}
fprintf(stderr, "[%-5s] ", level_str);
fputs(log, stderr);
fflush(stderr);
}
int load_model(const char * lm_model_path, const char * text_encoder_path,
const char * dit_model_path, const char * vae_model_path) {
ggml_log_set(ggml_log_cb, nullptr);
ggml_backend_load_all();
g_lm_path = lm_model_path;
g_text_enc_path = text_encoder_path;
g_dit_path = dit_model_path;
// Load DiT model
fprintf(stderr, "[acestep-cpp] Loading DiT from %s\n", dit_model_path);
dit_ggml_init_backend(&g_dit);
if (!dit_ggml_load(&g_dit, dit_model_path, g_dit_cfg, nullptr, 0.0f)) {
fprintf(stderr, "[acestep-cpp] FATAL: failed to load DiT from %s\n", dit_model_path);
return 1;
}
g_dit_loaded = true;
// Read DiT GGUF metadata + silence_latent
{
GGUFModel gf = {};
if (gf_load(&gf, dit_model_path)) {
g_is_turbo = gf_get_bool(gf, "acestep.is_turbo");
const void * sl_data = gf_get_data(gf, "silence_latent");
if (sl_data) {
g_silence_full.resize(15000 * 64);
memcpy(g_silence_full.data(), sl_data, 15000 * 64 * sizeof(float));
fprintf(stderr, "[acestep-cpp] silence_latent: [15000, 64] loaded\n");
} else {
fprintf(stderr, "[acestep-cpp] FATAL: silence_latent not found in %s\n", dit_model_path);
gf_close(&gf);
return 2;
}
gf_close(&gf);
} else {
fprintf(stderr, "[acestep-cpp] FATAL: cannot read GGUF metadata from %s\n", dit_model_path);
return 2;
}
}
// Load VAE model
fprintf(stderr, "[acestep-cpp] Loading VAE from %s\n", vae_model_path);
vae_ggml_load(&g_vae, vae_model_path);
g_vae_loaded = true;
fprintf(stderr, "[acestep-cpp] All models loaded successfully (turbo=%d)\n", g_is_turbo);
return 0;
}
int generate_music(const char * caption, const char * lyrics, int bpm,
const char * keyscale, const char * timesignature,
float duration, float temperature, bool instrumental,
int seed, const char * dst, int threads) {
if (!g_dit_loaded || !g_vae_loaded) {
fprintf(stderr, "[acestep-cpp] ERROR: models not loaded\n");
return 1;
}
const int FRAMES_PER_SECOND = 25;
// Defaults
if (duration <= 0)
duration = 30.0f;
std::string cap_str = caption ? caption : "";
std::string lyrics_str = (instrumental || !lyrics) ? "" : lyrics;
std::string ks_str = keyscale ? keyscale : "N/A";
std::string ts_str = timesignature ? timesignature : "4/4";
std::string lang_str = "unknown";
char bpm_str[16];
if (bpm > 0) {
snprintf(bpm_str, sizeof(bpm_str), "%d", bpm);
} else {
snprintf(bpm_str, sizeof(bpm_str), "N/A");
}
int num_steps = 8;
float guidance_scale = g_is_turbo ? 1.0f : 7.0f;
float shift = 1.0f;
if (seed < 0) {
std::random_device rd;
seed = (int)(rd() & 0x7FFFFFFF);
}
// Compute T (latent frames at 25Hz)
int T = (int)(duration * FRAMES_PER_SECOND);
T = ((T + g_dit_cfg.patch_size - 1) / g_dit_cfg.patch_size) * g_dit_cfg.patch_size;
int S = T / g_dit_cfg.patch_size;
if (T > 15000) {
fprintf(stderr, "[acestep-cpp] ERROR: T=%d exceeds max 15000\n", T);
return 2;
}
int Oc = g_dit_cfg.out_channels; // 64
int ctx_ch = g_dit_cfg.in_channels - Oc; // 128
fprintf(stderr, "[acestep-cpp] T=%d, S=%d, duration=%.1fs, seed=%d\n", T, S, duration, seed);
// 1. Load BPE tokenizer from text encoder GGUF
BPETokenizer tok;
if (!load_bpe_from_gguf(&tok, g_text_enc_path.c_str())) {
fprintf(stderr, "[acestep-cpp] FATAL: failed to load BPE tokenizer\n");
return 3;
}
// 2. Build formatted prompts (matches dit-vae.cpp text2music template)
std::string instruction = "Fill the audio semantic mask based on the given conditions:";
char metas[512];
snprintf(metas, sizeof(metas),
"- bpm: %s\n- timesignature: %s\n- keyscale: %s\n- duration: %d seconds\n",
bpm_str, ts_str.c_str(), ks_str.c_str(), (int)duration);
std::string text_str = std::string("# Instruction\n") + instruction + "\n\n" +
"# Caption\n" + cap_str + "\n\n" +
"# Metas\n" + metas + "<|endoftext|>\n";
std::string lyric_str = std::string("# Languages\n") + lang_str + "\n\n# Lyric\n" +
lyrics_str + "<|endoftext|>";
// 3. Tokenize
auto text_ids = bpe_encode(&tok, text_str.c_str(), true);
auto lyric_ids = bpe_encode(&tok, lyric_str.c_str(), true);
int S_text = (int)text_ids.size();
int S_lyric = (int)lyric_ids.size();
fprintf(stderr, "[acestep-cpp] caption: %d tokens, lyrics: %d tokens\n", S_text, S_lyric);
// 4. Text encoder forward
Qwen3GGML text_enc = {};
qwen3_init_backend(&text_enc);
if (!qwen3_load_text_encoder(&text_enc, g_text_enc_path.c_str())) {
fprintf(stderr, "[acestep-cpp] FATAL: failed to load text encoder\n");
return 4;
}
int H_text = text_enc.cfg.hidden_size; // 1024
std::vector<float> text_hidden(H_text * S_text);
qwen3_forward(&text_enc, text_ids.data(), S_text, text_hidden.data());
fprintf(stderr, "[acestep-cpp] TextEncoder forward done\n");
// 5. Lyric embedding
std::vector<float> lyric_embed(H_text * S_lyric);
qwen3_embed_lookup(&text_enc, lyric_ids.data(), S_lyric, lyric_embed.data());
// 6. Condition encoder
CondGGML cond = {};
cond_ggml_init_backend(&cond);
if (!cond_ggml_load(&cond, g_dit_path.c_str())) {
fprintf(stderr, "[acestep-cpp] FATAL: failed to load condition encoder\n");
qwen3_free(&text_enc);
return 5;
}
const int S_ref = 750;
std::vector<float> silence_feats(S_ref * 64);
memcpy(silence_feats.data(), g_silence_full.data(), S_ref * 64 * sizeof(float));
int enc_S = 0;
std::vector<float> enc_hidden;
cond_ggml_forward(&cond, text_hidden.data(), S_text, lyric_embed.data(), S_lyric,
silence_feats.data(), S_ref, enc_hidden, &enc_S);
fprintf(stderr, "[acestep-cpp] ConditionEncoder done, enc_S=%d\n", enc_S);
qwen3_free(&text_enc);
cond_ggml_free(&cond);
// 7. Build context [T, ctx_ch] = silence[64] + mask[64]
std::vector<float> context(T * ctx_ch);
for (int t = 0; t < T; t++) {
const float * src = g_silence_full.data() + t * Oc;
for (int c = 0; c < Oc; c++) {
context[t * ctx_ch + c] = src[c];
}
for (int c = 0; c < Oc; c++) {
context[t * ctx_ch + Oc + c] = 1.0f;
}
}
// 8. Build schedule
std::vector<float> schedule(num_steps);
for (int i = 0; i < num_steps; i++) {
float t = 1.0f - (float)i / (float)num_steps;
schedule[i] = shift * t / (1.0f + (shift - 1.0f) * t);
}
// 9. Generate noise (Philox)
std::vector<float> noise(Oc * T);
philox_randn((long long)seed, noise.data(), Oc * T, true);
// 10. DiT generate
std::vector<float> output(Oc * T);
fprintf(stderr, "[acestep-cpp] DiT generate: T=%d, steps=%d, guidance=%.1f\n", T, num_steps, guidance_scale);
dit_ggml_generate(&g_dit, noise.data(), context.data(), enc_hidden.data(), enc_S,
T, 1, num_steps, schedule.data(), output.data(), guidance_scale,
nullptr, nullptr, -1);
fprintf(stderr, "[acestep-cpp] DiT generation done\n");
// 11. VAE decode
int T_audio_max = T * 1920;
std::vector<float> audio(2 * T_audio_max);
int T_audio = vae_ggml_decode_tiled(&g_vae, output.data(), T, audio.data(), T_audio_max, 256, 64);
if (T_audio < 0) {
fprintf(stderr, "[acestep-cpp] ERROR: VAE decode failed\n");
return 6;
}
fprintf(stderr, "[acestep-cpp] VAE decode done: %d samples (%.2fs @ 48kHz)\n", T_audio,
(float)T_audio / 48000.0f);
// 12. Peak normalization to -1.0 dB
{
float peak = 0.0f;
int n_samples = 2 * T_audio;
for (int i = 0; i < n_samples; i++) {
float a = audio[i] < 0 ? -audio[i] : audio[i];
if (a > peak) {
peak = a;
}
}
if (peak > 1e-6f) {
const float target_amp = powf(10.0f, -1.0f / 20.0f);
float gain = target_amp / peak;
for (int i = 0; i < n_samples; i++) {
audio[i] *= gain;
}
}
}
// 13. Write WAV output
if (!audio_write_wav(dst, audio.data(), T_audio, 48000)) {
fprintf(stderr, "[acestep-cpp] ERROR: failed to write %s\n", dst);
return 7;
}
fprintf(stderr, "[acestep-cpp] Wrote %s: %d samples (%.2fs @ 48kHz stereo)\n",
dst, T_audio, (float)T_audio / 48000.0f);
return 0;
}

View File

@@ -0,0 +1,11 @@
#include <cstddef>
#include <cstdint>
extern "C" {
int load_model(const char *lm_model_path, const char *text_encoder_path,
const char *dit_model_path, const char *vae_model_path);
int generate_music(const char *caption, const char *lyrics, int bpm,
const char *keyscale, const char *timesignature,
float duration, float temperature, bool instrumental,
int seed, const char *dst, int threads);
}

View File

@@ -0,0 +1,82 @@
package main
import (
"fmt"
"os"
"strings"
"github.com/mudler/LocalAI/pkg/grpc/base"
pb "github.com/mudler/LocalAI/pkg/grpc/proto"
)
var (
CppLoadModel func(lmModelPath, textEncoderPath, ditModelPath, vaeModelPath string) int
CppGenerateMusic func(caption, lyrics string, bpm int, keyscale, timesignature string, duration, temperature float32, instrumental bool, seed int, dst string, threads int) int
)
type AceStepCpp struct {
base.SingleThread
}
func (a *AceStepCpp) Load(opts *pb.ModelOptions) error {
// ModelFile is the LM model path
lmModel := opts.ModelFile
var textEncoderModel, ditModel, vaeModel string
for _, oo := range opts.Options {
parts := strings.SplitN(oo, ":", 2)
if len(parts) != 2 {
fmt.Fprintf(os.Stderr, "Unrecognized option: %v\n", oo)
continue
}
switch parts[0] {
case "text_encoder_model":
textEncoderModel = parts[1]
case "dit_model":
ditModel = parts[1]
case "vae_model":
vaeModel = parts[1]
default:
fmt.Fprintf(os.Stderr, "Unrecognized option: %v\n", oo)
}
}
if textEncoderModel == "" {
return fmt.Errorf("text_encoder_model option is required")
}
if ditModel == "" {
return fmt.Errorf("dit_model option is required")
}
if vaeModel == "" {
return fmt.Errorf("vae_model option is required")
}
if ret := CppLoadModel(lmModel, textEncoderModel, ditModel, vaeModel); ret != 0 {
return fmt.Errorf("failed to load acestep models (error code: %d)", ret)
}
return nil
}
func (a *AceStepCpp) SoundGeneration(req *pb.SoundGenerationRequest) error {
caption := req.GetCaption()
if caption == "" {
caption = req.GetText()
}
lyrics := req.GetLyrics()
bpm := int(req.GetBpm())
keyscale := req.GetKeyscale()
timesignature := req.GetTimesignature()
duration := req.GetDuration()
temperature := req.GetTemperature()
instrumental := req.GetInstrumental()
seed := 42
threads := 4
if ret := CppGenerateMusic(caption, lyrics, bpm, keyscale, timesignature, duration, temperature, instrumental, seed, req.GetDst(), threads); ret != 0 {
return fmt.Errorf("failed to generate music (error code: %d)", ret)
}
return nil
}

View File

@@ -0,0 +1,47 @@
package main
// Note: this is started internally by LocalAI and a server is allocated for each model
import (
"flag"
"os"
"github.com/ebitengine/purego"
grpc "github.com/mudler/LocalAI/pkg/grpc"
)
var (
addr = flag.String("addr", "localhost:50051", "the address to connect to")
)
type LibFuncs struct {
FuncPtr any
Name string
}
func main() {
// Get library name from environment variable, default to fallback
libName := os.Getenv("ACESTEP_LIBRARY")
if libName == "" {
libName = "./libgoacestepcpp-fallback.so"
}
gosd, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)
if err != nil {
panic(err)
}
libFuncs := []LibFuncs{
{&CppLoadModel, "load_model"},
{&CppGenerateMusic, "generate_music"},
}
for _, lf := range libFuncs {
purego.RegisterLibFunc(lf.FuncPtr, gosd, lf.Name)
}
flag.Parse()
if err := grpc.StartServer(*addr, &AceStepCpp{}); err != nil {
panic(err)
}
}

View File

@@ -0,0 +1,65 @@
#!/bin/bash
# Script to copy the appropriate libraries based on architecture
# This script is used in the final stage of the Dockerfile
set -e
CURDIR=$(dirname "$(realpath $0)")
REPO_ROOT="${CURDIR}/../../.."
# Create lib directory
mkdir -p $CURDIR/package/lib
cp -avf $CURDIR/acestep-cpp $CURDIR/package/
cp -fv $CURDIR/libgoacestepcpp-*.so $CURDIR/package/
cp -fv $CURDIR/run.sh $CURDIR/package/
# Detect architecture and copy appropriate libraries
if [ -f "/lib64/ld-linux-x86-64.so.2" ]; then
# x86_64 architecture
echo "Detected x86_64 architecture, copying x86_64 libraries..."
cp -arfLv /lib64/ld-linux-x86-64.so.2 $CURDIR/package/lib/ld.so
cp -arfLv /lib/x86_64-linux-gnu/libc.so.6 $CURDIR/package/lib/libc.so.6
cp -arfLv /lib/x86_64-linux-gnu/libgcc_s.so.1 $CURDIR/package/lib/libgcc_s.so.1
cp -arfLv /lib/x86_64-linux-gnu/libstdc++.so.6 $CURDIR/package/lib/libstdc++.so.6
cp -arfLv /lib/x86_64-linux-gnu/libm.so.6 $CURDIR/package/lib/libm.so.6
cp -arfLv /lib/x86_64-linux-gnu/libgomp.so.1 $CURDIR/package/lib/libgomp.so.1
cp -arfLv /lib/x86_64-linux-gnu/libgcc_s.so.1 $CURDIR/package/lib/libgcc_s.so.1
cp -arfLv /lib/x86_64-linux-gnu/libstdc++.so.6 $CURDIR/package/lib/libstdc++.so.6
cp -arfLv /lib/x86_64-linux-gnu/libdl.so.2 $CURDIR/package/lib/libdl.so.2
cp -arfLv /lib/x86_64-linux-gnu/librt.so.1 $CURDIR/package/lib/librt.so.1
cp -arfLv /lib/x86_64-linux-gnu/libpthread.so.0 $CURDIR/package/lib/libpthread.so.0
elif [ -f "/lib/ld-linux-aarch64.so.1" ]; then
# ARM64 architecture
echo "Detected ARM64 architecture, copying ARM64 libraries..."
cp -arfLv /lib/ld-linux-aarch64.so.1 $CURDIR/package/lib/ld.so
cp -arfLv /lib/aarch64-linux-gnu/libc.so.6 $CURDIR/package/lib/libc.so.6
cp -arfLv /lib/aarch64-linux-gnu/libgcc_s.so.1 $CURDIR/package/lib/libgcc_s.so.1
cp -arfLv /lib/aarch64-linux-gnu/libstdc++.so.6 $CURDIR/package/lib/libstdc++.so.6
cp -arfLv /lib/aarch64-linux-gnu/libm.so.6 $CURDIR/package/lib/libm.so.6
cp -arfLv /lib/aarch64-linux-gnu/libgomp.so.1 $CURDIR/package/lib/libgomp.so.1
cp -arfLv /lib/aarch64-linux-gnu/libgcc_s.so.1 $CURDIR/package/lib/libgcc_s.so.1
cp -arfLv /lib/aarch64-linux-gnu/libstdc++.so.6 $CURDIR/package/lib/libstdc++.so.6
cp -arfLv /lib/aarch64-linux-gnu/libdl.so.2 $CURDIR/package/lib/libdl.so.2
cp -arfLv /lib/aarch64-linux-gnu/librt.so.1 $CURDIR/package/lib/librt.so.1
cp -arfLv /lib/aarch64-linux-gnu/libpthread.so.0 $CURDIR/package/lib/libpthread.so.0
elif [ $(uname -s) = "Darwin" ]; then
echo "Detected Darwin"
else
echo "Error: Could not detect architecture"
exit 1
fi
# Package GPU libraries based on BUILD_TYPE
# The GPU library packaging script will detect BUILD_TYPE and copy appropriate GPU libraries
GPU_LIB_SCRIPT="${REPO_ROOT}/scripts/build/package-gpu-libs.sh"
if [ -f "$GPU_LIB_SCRIPT" ]; then
echo "Packaging GPU libraries for BUILD_TYPE=${BUILD_TYPE:-cpu}..."
source "$GPU_LIB_SCRIPT" "$CURDIR/package/lib"
package_gpu_libs
fi
echo "Packaging completed successfully"
ls -liah $CURDIR/package/
ls -liah $CURDIR/package/lib/

52
backend/go/acestep-cpp/run.sh Executable file
View File

@@ -0,0 +1,52 @@
#!/bin/bash
set -ex
# Get the absolute current dir where the script is located
CURDIR=$(dirname "$(realpath $0)")
cd /
echo "CPU info:"
if [ "$(uname)" != "Darwin" ]; then
grep -e "model\sname" /proc/cpuinfo | head -1
grep -e "flags" /proc/cpuinfo | head -1
fi
LIBRARY="$CURDIR/libgoacestepcpp-fallback.so"
if [ "$(uname)" != "Darwin" ]; then
if grep -q -e "\savx\s" /proc/cpuinfo ; then
echo "CPU: AVX found OK"
if [ -e $CURDIR/libgoacestepcpp-avx.so ]; then
LIBRARY="$CURDIR/libgoacestepcpp-avx.so"
fi
fi
if grep -q -e "\savx2\s" /proc/cpuinfo ; then
echo "CPU: AVX2 found OK"
if [ -e $CURDIR/libgoacestepcpp-avx2.so ]; then
LIBRARY="$CURDIR/libgoacestepcpp-avx2.so"
fi
fi
# Check avx 512
if grep -q -e "\savx512f\s" /proc/cpuinfo ; then
echo "CPU: AVX512F found OK"
if [ -e $CURDIR/libgoacestepcpp-avx512.so ]; then
LIBRARY="$CURDIR/libgoacestepcpp-avx512.so"
fi
fi
fi
export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
export ACESTEP_LIBRARY=$LIBRARY
# If there is a lib/ld.so, use it
if [ -f $CURDIR/lib/ld.so ]; then
echo "Using lib/ld.so"
echo "Using library: $LIBRARY"
exec $CURDIR/lib/ld.so $CURDIR/acestep-cpp "$@"
fi
echo "Using library: $LIBRARY"
exec $CURDIR/acestep-cpp "$@"

54
backend/go/acestep-cpp/test.sh Executable file
View File

@@ -0,0 +1,54 @@
#!/bin/bash
set -e
CURDIR=$(dirname "$(realpath $0)")
echo "Running acestep-cpp backend tests..."
# The test requires:
# - ACESTEP_MODEL_DIR: path to directory containing GGUF model files
# - ACESTEP_BINARY: path to the acestep-cpp binary (defaults to ./acestep-cpp)
#
# Tests that require the model will be skipped if ACESTEP_MODEL_DIR is not set
# or the directory does not contain the required model files.
cd "$CURDIR"
# Only auto-download models when ACESTEP_MODEL_DIR is not explicitly set
if [ -z "$ACESTEP_MODEL_DIR" ]; then
export ACESTEP_MODEL_DIR="./acestep-models"
if [ ! -d "$ACESTEP_MODEL_DIR" ]; then
echo "Creating acestep-models directory for tests..."
mkdir -p "$ACESTEP_MODEL_DIR"
REPO_ID="Serveurperso/ACE-Step-1.5-GGUF"
echo "Repository: ${REPO_ID}"
echo ""
# Files to download (smallest quantizations for testing)
FILES=(
"acestep-5Hz-lm-0.6B-Q8_0.gguf"
"Qwen3-Embedding-0.6B-Q8_0.gguf"
"acestep-v15-turbo-Q8_0.gguf"
"vae-BF16.gguf"
)
BASE_URL="https://huggingface.co/${REPO_ID}/resolve/main"
for file in "${FILES[@]}"; do
dest="${ACESTEP_MODEL_DIR}/${file}"
if [ -f "${dest}" ]; then
echo " [skip] ${file} (already exists)"
else
echo " [download] ${file}..."
curl -L -o "${dest}" "${BASE_URL}/${file}" --progress-bar
echo " [done] ${file}"
fi
done
fi
fi
# Run Go tests
go test -v -timeout 600s .
echo "All acestep-cpp tests passed."

View File

@@ -364,6 +364,29 @@
default: "cpu-ace-step-development"
nvidia-cuda-13: "cuda13-ace-step-development"
nvidia-cuda-12: "cuda12-ace-step-development"
- &acestepcpp
name: "acestep-cpp"
description: |
ACE-Step 1.5 C++ backend using GGML. Native C++ implementation of ACE-Step music generation with GPU support through GGML backends.
Generates stereo 48kHz audio from text descriptions and optional lyrics via a two-stage pipeline: text-to-code (ace-qwen3 LLM) + code-to-audio (DiT-VAE).
urls:
- https://github.com/ace-step/acestep.cpp
tags:
- music-generation
- sound-generation
alias: "acestep-cpp"
capabilities:
default: "cpu-acestep-cpp"
nvidia: "cuda12-acestep-cpp"
nvidia-cuda-13: "cuda13-acestep-cpp"
nvidia-cuda-12: "cuda12-acestep-cpp"
intel: "intel-sycl-f16-acestep-cpp"
metal: "metal-acestep-cpp"
amd: "rocm-acestep-cpp"
vulkan: "vulkan-acestep-cpp"
nvidia-l4t: "nvidia-l4t-arm64-acestep-cpp"
nvidia-l4t-cuda-12: "nvidia-l4t-arm64-acestep-cpp"
nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-acestep-cpp"
- &faster-whisper
icon: https://avatars.githubusercontent.com/u/1520500?s=200&v=4
description: |
@@ -1845,6 +1868,107 @@
uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-ace-step"
mirrors:
- localai/localai-backends:master-metal-darwin-arm64-ace-step
## acestep-cpp
- !!merge <<: *acestepcpp
name: "nvidia-l4t-arm64-acestep-cpp"
uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-acestep-cpp"
mirrors:
- localai/localai-backends:latest-nvidia-l4t-arm64-acestep-cpp
- !!merge <<: *acestepcpp
name: "nvidia-l4t-arm64-acestep-cpp-development"
uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-acestep-cpp"
mirrors:
- localai/localai-backends:master-nvidia-l4t-arm64-acestep-cpp
- !!merge <<: *acestepcpp
name: "cuda13-nvidia-l4t-arm64-acestep-cpp"
uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-acestep-cpp"
mirrors:
- localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-acestep-cpp
- !!merge <<: *acestepcpp
name: "cuda13-nvidia-l4t-arm64-acestep-cpp-development"
uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-acestep-cpp"
mirrors:
- localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-acestep-cpp
- !!merge <<: *acestepcpp
name: "cpu-acestep-cpp"
uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-acestep-cpp"
mirrors:
- localai/localai-backends:latest-cpu-acestep-cpp
- !!merge <<: *acestepcpp
name: "metal-acestep-cpp"
uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-acestep-cpp"
mirrors:
- localai/localai-backends:latest-metal-darwin-arm64-acestep-cpp
- !!merge <<: *acestepcpp
name: "metal-acestep-cpp-development"
uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-acestep-cpp"
mirrors:
- localai/localai-backends:master-metal-darwin-arm64-acestep-cpp
- !!merge <<: *acestepcpp
name: "cpu-acestep-cpp-development"
uri: "quay.io/go-skynet/local-ai-backends:master-cpu-acestep-cpp"
mirrors:
- localai/localai-backends:master-cpu-acestep-cpp
- !!merge <<: *acestepcpp
name: "cuda12-acestep-cpp"
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-acestep-cpp"
mirrors:
- localai/localai-backends:latest-gpu-nvidia-cuda-12-acestep-cpp
- !!merge <<: *acestepcpp
name: "rocm-acestep-cpp"
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-acestep-cpp"
mirrors:
- localai/localai-backends:latest-gpu-rocm-hipblas-acestep-cpp
- !!merge <<: *acestepcpp
name: "intel-sycl-f32-acestep-cpp"
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-acestep-cpp"
mirrors:
- localai/localai-backends:latest-gpu-intel-sycl-f32-acestep-cpp
- !!merge <<: *acestepcpp
name: "intel-sycl-f16-acestep-cpp"
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-acestep-cpp"
mirrors:
- localai/localai-backends:latest-gpu-intel-sycl-f16-acestep-cpp
- !!merge <<: *acestepcpp
name: "vulkan-acestep-cpp"
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-acestep-cpp"
mirrors:
- localai/localai-backends:latest-gpu-vulkan-acestep-cpp
- !!merge <<: *acestepcpp
name: "vulkan-acestep-cpp-development"
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-acestep-cpp"
mirrors:
- localai/localai-backends:master-gpu-vulkan-acestep-cpp
- !!merge <<: *acestepcpp
name: "cuda12-acestep-cpp-development"
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-acestep-cpp"
mirrors:
- localai/localai-backends:master-gpu-nvidia-cuda-12-acestep-cpp
- !!merge <<: *acestepcpp
name: "rocm-acestep-cpp-development"
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-acestep-cpp"
mirrors:
- localai/localai-backends:master-gpu-rocm-hipblas-acestep-cpp
- !!merge <<: *acestepcpp
name: "intel-sycl-f32-acestep-cpp-development"
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-acestep-cpp"
mirrors:
- localai/localai-backends:master-gpu-intel-sycl-f32-acestep-cpp
- !!merge <<: *acestepcpp
name: "intel-sycl-f16-acestep-cpp-development"
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-acestep-cpp"
mirrors:
- localai/localai-backends:master-gpu-intel-sycl-f16-acestep-cpp
- !!merge <<: *acestepcpp
name: "cuda13-acestep-cpp"
uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-acestep-cpp"
mirrors:
- localai/localai-backends:latest-gpu-nvidia-cuda-13-acestep-cpp
- !!merge <<: *acestepcpp
name: "cuda13-acestep-cpp-development"
uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-acestep-cpp"
mirrors:
- localai/localai-backends:master-gpu-nvidia-cuda-13-acestep-cpp
## kokoro
- !!merge <<: *kokoro
name: "kokoro-development"

View File

@@ -675,7 +675,7 @@ func (c *ModelConfig) GuessUsecases(u ModelConfigUsecase) bool {
}
if (u & FLAG_SOUND_GENERATION) == FLAG_SOUND_GENERATION {
soundGenBackends := []string{"transformers-musicgen", "ace-step", "mock-backend"}
soundGenBackends := []string{"transformers-musicgen", "ace-step", "acestep-cpp", "mock-backend"}
if !slices.Contains(soundGenBackends, c.Backend) {
return false
}

View File

@@ -725,6 +725,83 @@
- "inference_steps:8"
- "guidance_scale:7.0"
- "batch_size:1"
- name: "acestep-cpp-turbo"
license: mit
tags:
- music
- audio
- music-generation
- sound-generation
- acestep-cpp
- ace-step-1.5
- gguf
url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
urls:
- https://huggingface.co/Serveurperso/ACE-Step-1.5-GGUF
- https://github.com/ace-step/acestep.cpp
description: |
ACE-Step 1.5 Turbo (C++ / GGML) — native C++ music generation from text descriptions and lyrics.
Two-stage pipeline: text-to-code (Qwen3 LM) + code-to-audio (DiT-VAE). Stereo 48kHz output.
Uses Q8_0 quantized models for a good balance of quality and speed.
overrides:
name: acestep-cpp-turbo
backend: acestep-cpp
parameters:
model: acestep-cpp/acestep-5Hz-lm-0.6B-Q8_0.gguf
known_usecases:
- sound_generation
- tts
options:
- "text_encoder_model:acestep-cpp/Qwen3-Embedding-0.6B-Q8_0.gguf"
- "dit_model:acestep-cpp/acestep-v15-turbo-Q8_0.gguf"
- "vae_model:acestep-cpp/vae-BF16.gguf"
files:
- filename: acestep-cpp/acestep-5Hz-lm-0.6B-Q8_0.gguf
uri: huggingface://Serveurperso/ACE-Step-1.5-GGUF/acestep-5Hz-lm-0.6B-Q8_0.gguf
- filename: acestep-cpp/Qwen3-Embedding-0.6B-Q8_0.gguf
uri: huggingface://Serveurperso/ACE-Step-1.5-GGUF/Qwen3-Embedding-0.6B-Q8_0.gguf
- filename: acestep-cpp/acestep-v15-turbo-Q8_0.gguf
uri: huggingface://Serveurperso/ACE-Step-1.5-GGUF/acestep-v15-turbo-Q8_0.gguf
- filename: acestep-cpp/vae-BF16.gguf
uri: huggingface://Serveurperso/ACE-Step-1.5-GGUF/vae-BF16.gguf
- name: "acestep-cpp-turbo-4b"
license: mit
tags:
- music
- audio
- music-generation
- sound-generation
- acestep-cpp
- ace-step-1.5
- gguf
url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
urls:
- https://huggingface.co/Serveurperso/ACE-Step-1.5-GGUF
- https://github.com/ace-step/acestep.cpp
description: |
ACE-Step 1.5 Turbo (C++ / GGML) with 4B LM — higher quality music generation from text and lyrics.
Uses the larger 4B parameter LM for better metadata/code generation. Stereo 48kHz output.
overrides:
name: acestep-cpp-turbo-4b
backend: acestep-cpp
parameters:
model: acestep-cpp/acestep-5Hz-lm-4B-Q8_0.gguf
known_usecases:
- sound_generation
- tts
options:
- "text_encoder_model:acestep-cpp/Qwen3-Embedding-0.6B-Q8_0.gguf"
- "dit_model:acestep-cpp/acestep-v15-turbo-Q8_0.gguf"
- "vae_model:acestep-cpp/vae-BF16.gguf"
files:
- filename: acestep-cpp/acestep-5Hz-lm-4B-Q8_0.gguf
uri: huggingface://Serveurperso/ACE-Step-1.5-GGUF/acestep-5Hz-lm-4B-Q8_0.gguf
- filename: acestep-cpp/Qwen3-Embedding-0.6B-Q8_0.gguf
uri: huggingface://Serveurperso/ACE-Step-1.5-GGUF/Qwen3-Embedding-0.6B-Q8_0.gguf
- filename: acestep-cpp/acestep-v15-turbo-Q8_0.gguf
uri: huggingface://Serveurperso/ACE-Step-1.5-GGUF/acestep-v15-turbo-Q8_0.gguf
- filename: acestep-cpp/vae-BF16.gguf
uri: huggingface://Serveurperso/ACE-Step-1.5-GGUF/vae-BF16.gguf
- name: "qwen3-coder-next-mxfp4_moe"
url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
urls: