mirror of
https://github.com/mudler/LocalAI.git
synced 2026-09-13 06:45:26 -04:00
Ettore Di Giacinto
24e5992569
The pinned audio.cpp revision supports HIP, but LocalAI neither builds a ROCm image nor accepts its backend option. AMD hosts therefore fall back to the CPU image. Build and publish the HIP variant, connect it to AMD capability selection, and accept both upstream HIP names. Assisted-by: Codex:gpt-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
180 lines
8.8 KiB
Makefile
180 lines
8.8 KiB
Makefile
# audio.cpp backend Makefile.
|
|
#
|
|
# Upstream pin lives below in the AUDIO_CPP_VERSION variable, so
|
|
# .github/bump_deps.sh can find and update it, matching the llama-cpp / ds4
|
|
# convention. That script seds every line matching the variable name followed by
|
|
# an assignment, so this comment deliberately spells the name on its own: a
|
|
# comment repeating the full assignment token gets rewritten and mangled by the
|
|
# first auto-bump (backend/cpp/ds4/Makefile shows the damage). The clone
|
|
# recipe is a make target (not a prepare.sh) so 'make purge && make' is a clean
|
|
# rebuild and so the bump bot can see the pin.
|
|
|
|
AUDIO_CPP_VERSION?=43001a7e0f452d80f4588e613f13332940dd4d3a
|
|
AUDIO_CPP_REPO?=https://github.com/0xShug0/audio.cpp
|
|
|
|
CURRENT_MAKEFILE_DIR := $(dir $(abspath $(lastword $(MAKEFILE_LIST))))
|
|
BUILD_DIR := build
|
|
|
|
BUILD_TYPE ?=
|
|
NATIVE ?= false
|
|
JOBS ?= $(shell nproc 2>/dev/null || sysctl -n hw.ncpu 2>/dev/null || echo 4)
|
|
|
|
UNAME_S := $(shell uname -s)
|
|
|
|
# AUDIOCPP_DEPLOYMENT_BUILD compiles the model_specs/*.json catalog into
|
|
# engine_runtime, so the shipped package needs no model_specs directory and a
|
|
# safetensors model tree still resolves its family spec.
|
|
CMAKE_ARGS ?= -DCMAKE_BUILD_TYPE=Release -DAUDIOCPP_DEPLOYMENT_BUILD=ON
|
|
|
|
# CMAKE_CUDA_ARCHITECTURES must be set explicitly for a cublas build, and this
|
|
# is not a tuning knob: upstream's CMakeLists sets CUDA_ARCHITECTURES to
|
|
# `native` on the engine_runtime target whenever the root-scope variable is
|
|
# unset (audio.cpp/CMakeLists.txt, the `if (CMAKE_CUDA_ARCHITECTURES)` branch
|
|
# next to the istft/torch_random .cu sources), and docs/build/linux.md says so
|
|
# outright: "Leave CMAKE_CUDA_ARCHITECTURES unset to build for the GPUs present
|
|
# at build time (native)". No CI runner has a GPU, so `native` has nothing to
|
|
# enumerate. ggml's own default (external/ggml/src/ggml-cuda/CMakeLists.txt)
|
|
# does not rescue this: it list(APPEND)s in the ggml subdirectory scope, which
|
|
# never reaches the root scope where the engine_runtime property is decided.
|
|
#
|
|
# The values below are ggml's list for the matching toolkit, copied rather than
|
|
# invented, so the two targets compile for exactly the same set:
|
|
# - CUDA 13 drops the Maxwell/Pascal/Volta virtual archs (50/61/70).
|
|
# - 121a-real needs CUDA >= 12.9, so the CUDA 12 list (built against 12.8)
|
|
# stops at 120a-real.
|
|
# - `a`-suffixed archs are used rather than ggml's rejected 120f-virtual: the
|
|
# `f` suffix needs CMake >= 3.31.8, and Ubuntu Noble ships 3.28.3. The
|
|
# 3.28 validator (Modules/Internal/CMakeCUDAArchitecturesValidate.cmake)
|
|
# accepts `[0-9]+a?(-real|-virtual)?`.
|
|
#
|
|
# Setting it here also pins ggml's copy, since its default is guarded by
|
|
# `if (NOT DEFINED CMAKE_CUDA_ARCHITECTURES)`. CUDA_MAJOR_VERSION is the CI
|
|
# build-arg, forwarded by Dockerfile.audio-cpp.
|
|
#
|
|
# An EMPTY major maps to `native`, NOT to the CUDA 12 list. Only CI declares a
|
|
# major; a developer running `BUILD_TYPE=cublas make` locally declares none, and
|
|
# the CUDA 12 list contains 120a-real, which needs nvcc >= 12.8. Falling through
|
|
# to it turned every local build on a CUDA 12.0-12.7 host into a compile error,
|
|
# where upstream's documented behaviour ("Leave CMAKE_CUDA_ARCHITECTURES unset
|
|
# to build for the GPUs present at build time") worked. `native` restores that.
|
|
# It does require a GPU to enumerate, so the escape hatch for a GPU-less local
|
|
# cross-build is to set CUDA_ARCHITECTURES on the command line, which the ?=
|
|
# assignments below leave untouched.
|
|
CUDA_MAJOR_VERSION ?=
|
|
ifeq ($(CUDA_MAJOR_VERSION),13)
|
|
CUDA_ARCHITECTURES ?= 75-virtual;80-virtual;86-real;89-real;120a-real;121a-real
|
|
else ifeq ($(CUDA_MAJOR_VERSION),12)
|
|
CUDA_ARCHITECTURES ?= 50-virtual;61-virtual;70-virtual;75-virtual;80-virtual;86-real;89-real;120a-real
|
|
else ifeq ($(CUDA_MAJOR_VERSION),)
|
|
CUDA_ARCHITECTURES ?= native
|
|
else ifeq ($(BUILD_TYPE),cublas)
|
|
# Gated on cublas because the variable means nothing to any other build, so a
|
|
# stray CUDA_MAJOR_VERSION in the environment must not break `make clean` or
|
|
# a CPU build. It does still error for `BUILD_TYPE=cublas make clean`, which
|
|
# is the right trade: that invocation is asking about a CUDA build tree.
|
|
$(error CUDA_MAJOR_VERSION=$(CUDA_MAJOR_VERSION) has no architecture list here (12 and 13 do). Leave it empty for a native build, or pass CUDA_ARCHITECTURES explicitly.)
|
|
endif
|
|
|
|
ifeq ($(BUILD_TYPE),cublas)
|
|
CMAKE_ARGS += -DENGINE_ENABLE_CUDA=ON "-DCMAKE_CUDA_ARCHITECTURES=$(CUDA_ARCHITECTURES)"
|
|
else ifeq ($(BUILD_TYPE),hipblas)
|
|
ROCM_HOME ?= /opt/rocm
|
|
ROCM_PATH ?= /opt/rocm
|
|
export CXX=$(ROCM_HOME)/llvm/bin/clang++
|
|
export CC=$(ROCM_HOME)/llvm/bin/clang
|
|
AMDGPU_TARGETS ?= gfx908,gfx90a,gfx942,gfx950,gfx1030,gfx1100,gfx1101,gfx1102,gfx1151,gfx1200,gfx1201
|
|
CMAKE_ARGS += -DENGINE_ENABLE_HIP=ON -DAMDGPU_TARGETS=$(AMDGPU_TARGETS)
|
|
else ifeq ($(BUILD_TYPE),vulkan)
|
|
CMAKE_ARGS += -DENGINE_ENABLE_VULKAN=ON
|
|
else ifeq ($(UNAME_S),Darwin)
|
|
# Metal. ggml embeds the shader library by default (GGML_METAL_EMBED_LIBRARY
|
|
# defaults to GGML_METAL), so the package needs no .metallib beside the
|
|
# binary. Darwin builds go through scripts/build/audio-cpp-darwin.sh.
|
|
CMAKE_ARGS += -DENGINE_ENABLE_METAL=ON
|
|
# AppleClang ships no OpenMP runtime and Homebrew's libomp is keg-only, so
|
|
# neither libomp.dylib nor omp.h is symlinked into /opt/homebrew and CMake's
|
|
# FindOpenMP cannot find them on its own (the workflow's `brew link libomp`
|
|
# is a no-op for a keg-only formula, and its failure is swallowed).
|
|
# audio.cpp calls find_package(OpenMP REQUIRED COMPONENTS CXX) whenever
|
|
# ENGINE_ENABLE_OPENMP is ON, so with no hint the macOS build dies at
|
|
# configure time before compiling anything. OpenMP_ROOT is honoured by the
|
|
# find_library/find_path calls inside FindOpenMP under CMP0074, which is NEW
|
|
# here because audio.cpp requires CMake 3.20.
|
|
#
|
|
# If the keg is absent, turn OpenMP off rather than fail: the tree's only
|
|
# <omp.h> include is guarded by #ifdef _OPENMP and a #pragma omp without
|
|
# -fopenmp is simply ignored, so an OpenMP-less build is CORRECT. It is not
|
|
# cheap, though: 108 `#pragma omp` directives across ~30 files (roformer,
|
|
# demucs, chatterbox, moss, supertonic, seed_vc, framework/audio/dsp) are
|
|
# compiled out, and clang says nothing about an ignored omp pragma unless
|
|
# -Wsource-uses-openmp is on. A green package that is quietly single-threaded
|
|
# in every host DSP loop gets blamed on Metal, not on packaging, so the
|
|
# fallback announces itself.
|
|
ifeq ($(origin LIBOMP_PREFIX),undefined)
|
|
LIBOMP_PREFIX := $(shell brew --prefix libomp 2>/dev/null)
|
|
endif
|
|
# Nested ifneq rather than $(and ...): $(and) needs GNU make 3.81, and while
|
|
# that is what Apple ships, an older make expands it to empty and would take
|
|
# the OpenMP-OFF branch with no way to tell that from a genuinely missing
|
|
# keg. Two plain conditionals cannot fail that way.
|
|
LIBOMP_USABLE :=
|
|
ifneq ($(wildcard $(LIBOMP_PREFIX)/lib/libomp.dylib),)
|
|
ifneq ($(wildcard $(LIBOMP_PREFIX)/include/omp.h),)
|
|
LIBOMP_USABLE := yes
|
|
endif
|
|
endif
|
|
ifeq ($(LIBOMP_USABLE),yes)
|
|
CMAKE_ARGS += "-DOpenMP_ROOT=$(LIBOMP_PREFIX)"
|
|
else
|
|
$(warning audio-cpp: libomp not found at '$(LIBOMP_PREFIX)'; building without OpenMP (single-threaded host DSP). Install it with `brew install libomp`, or set LIBOMP_PREFIX.)
|
|
CMAKE_ARGS += -DENGINE_ENABLE_OPENMP=OFF
|
|
endif
|
|
else
|
|
# Portable Linux CPU. Upstream wires this to GGML_BACKEND_DL +
|
|
# GGML_CPU_ALL_VARIANTS + $ORIGIN rpath, so one build serves every CPU
|
|
# tier instead of an AVX-tier image fan-out.
|
|
CMAKE_ARGS += -DENGINE_ENABLE_CPU_ALL_VARIANTS=ON
|
|
endif
|
|
|
|
ifneq ($(NATIVE),true)
|
|
CMAKE_ARGS += -DENGINE_ENABLE_NATIVE_CPU=OFF
|
|
endif
|
|
|
|
.PHONY: all grpc-server package test test-engine clean purge
|
|
all: grpc-server
|
|
|
|
# Clone the upstream source at the pinned commit. The directory is the target
|
|
# so make only re-clones when it is missing. After bumping AUDIO_CPP_VERSION,
|
|
# run 'make purge && make' to refetch.
|
|
audio.cpp:
|
|
mkdir -p audio.cpp
|
|
cd audio.cpp && \
|
|
git init -q && \
|
|
git remote add origin $(AUDIO_CPP_REPO) && \
|
|
git fetch --depth 1 origin $(AUDIO_CPP_VERSION) && \
|
|
git checkout FETCH_HEAD
|
|
|
|
grpc-server: audio.cpp
|
|
mkdir -p $(BUILD_DIR)
|
|
cd $(BUILD_DIR) && cmake $(CMAKE_ARGS) $(CURRENT_MAKEFILE_DIR) && \
|
|
cmake --build . --config Release -j $(JOBS)
|
|
cp $(BUILD_DIR)/grpc-server grpc-server
|
|
|
|
package: grpc-server
|
|
bash package.sh
|
|
|
|
test:
|
|
@echo "audio-cpp: standalone unit tests run from the repo root via 'make test-backend-cpp'"
|
|
|
|
# Engine-linked tests. Needs the upstream checkout and a full engine build.
|
|
test-engine: audio.cpp
|
|
mkdir -p $(BUILD_DIR)
|
|
cd $(BUILD_DIR) && cmake $(CMAKE_ARGS) -DAUDIO_CPP_GRPC_BUILD_TESTS=ON $(CURRENT_MAKEFILE_DIR) && \
|
|
cmake --build . --config Release -j $(JOBS) && ctest --output-on-failure --no-tests=error
|
|
|
|
clean:
|
|
rm -rf $(BUILD_DIR) grpc-server package
|
|
|
|
purge: clean
|
|
rm -rf audio.cpp
|