mirror of
https://github.com/mudler/LocalAI.git
synced 2026-07-30 09:57:57 -04:00
5af51273c2
Upstream sets CUDA_ARCHITECTURES to `native` on the engine_runtime target whenever CMAKE_CUDA_ARCHITECTURES is unset at root scope, and docs/build/ linux.md says so outright. ggml's own default does not rescue it: it list(APPEND)s in the ggml subdirectory scope, which never reaches the root scope where the engine_runtime property is decided. No CI runner has a GPU for `native` to enumerate, so both cublas entries would have gone red on the very commit that first turns a CUDA build on. Pin the list in backend/cpp/audio-cpp/Makefile, selected by CUDA_MAJOR_VERSION, which Dockerfile.audio-cpp now forwards from the CI build-arg it was previously discarding. The values are copied from ggml's own version guards rather than invented, so engine_runtime and ggml compile for the same set: CUDA 12 keeps the Maxwell/Pascal/Volta virtual archs and stops at 120a-real, CUDA 13 drops them and adds 121a-real. The `a` suffix is used rather than `f` because the latter needs CMake 3.31.8 and Ubuntu Noble ships 3.28.3. Verified by driving CMake 3.28.3's own CUDA architecture validator over both lists, with 120f-virtual as the rejected control. Drop the vulkan matrix entry, its two gallery entries, the vulkan capability key on both metas and the Vulkan tag. Every other vulkan backend gets its Mesa ICD drivers from .docker/install-base-deps.sh, which package-gpu-libs.sh then bundles; Dockerfile.audio-cpp calls neither and installs only libvulkan-dev and glslc, so the image would ship a Vulkan loader that finds no GPU. No CI job runs a vulkan image against real hardware, so that would have passed green and failed in users' hands. BUILD_TYPE=vulkan stays supported for local builds. Also note on the cublas entries that cuda-major-version now selects the architecture list and that cuda-minor-version and the base-image tag encode the same toolkit, and correct the stale entry counts on matrixEntryKey. Assisted-by: Claude:claude-opus-5 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
114 lines
4.8 KiB
Makefile
114 lines
4.8 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?=e800d435d130dc776baf6f3e6129bb62b1495c89
|
|
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.
|
|
CUDA_MAJOR_VERSION ?=
|
|
ifeq ($(CUDA_MAJOR_VERSION),13)
|
|
CUDA_ARCHITECTURES ?= 75-virtual;80-virtual;86-real;89-real;120a-real;121a-real
|
|
else
|
|
CUDA_ARCHITECTURES ?= 50-virtual;61-virtual;70-virtual;75-virtual;80-virtual;86-real;89-real;120a-real
|
|
endif
|
|
|
|
ifeq ($(BUILD_TYPE),cublas)
|
|
CMAKE_ARGS += -DENGINE_ENABLE_CUDA=ON "-DCMAKE_CUDA_ARCHITECTURES=$(CUDA_ARCHITECTURES)"
|
|
else ifeq ($(BUILD_TYPE),vulkan)
|
|
CMAKE_ARGS += -DENGINE_ENABLE_VULKAN=ON
|
|
else ifeq ($(UNAME_S),Darwin)
|
|
CMAKE_ARGS += -DENGINE_ENABLE_METAL=ON
|
|
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
|