Files
LocalAI/backend/go/face-detect/Makefile
LocalAI [bot] 5b7b914b4f chore(recon): re-pin voice/face-detect to squashed release commits (+ graph-cache fix) (#10591)
chore(recon): re-pin voice/face-detect to squashed release commits

The voice-detect.cpp and face-detect.cpp engine repos were squashed to a single
release commit, which orphaned the previous pins (voice 3d51077, face 06914b0).
Re-pin to the new single-commit SHAs (voice 1db1759, face e22260d).

These also fold in a real correctness fix: the persistent graph-cache fingerprint
now includes op_params, so two structurally identical GGML_OP_CUSTOM graphs (a
blocked 3x3 vs a blocked 1x1 strided conv) can no longer false-hit the cache and
replay the wrong kernel. voice CI was failing test_blocked/conv1x1_s2 with an
out-of-bounds write on the GGML_NATIVE=OFF build; both engine repos are now green
and WeSpeaker embed parity is 1.0 vs golden.


Assisted-by: Claude:claude-opus-4-8 [Claude Code]

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
2026-06-29 18:48:47 +02:00

111 lines
4.5 KiB
Makefile

# face-detect backend Makefile.
#
# Upstream pin lives below as FACEDETECT_VERSION?=e22260d5d5490b37b021b7f795079f386d553afd
# can find and update it - matches the voice-detect / parakeet.cpp / whisper.cpp
# convention).
#
# Local dev shortcut: if you already have an out-of-tree face-detect.cpp build,
# symlink the .so + header into this directory and skip the clone/cmake steps:
#
# ln -sf /path/to/face-detect.cpp/build-shared/libfacedetect.so .
# ln -sf /path/to/face-detect.cpp/include/facedetect_capi.h .
# go build -o face-detect-grpc .
#
# The default target below does the proper clone-at-pin + cmake build so CI does
# not need a side-checkout.
FACEDETECT_VERSION?=e22260d5d5490b37b021b7f795079f386d553afd
FACEDETECT_REPO?=https://github.com/mudler/face-detect.cpp
GOCMD?=go
GO_TAGS?=
JOBS?=$(shell nproc 2>/dev/null || sysctl -n hw.ncpu 2>/dev/null || echo 4)
BUILD_TYPE?=
NATIVE?=false
# Resolve the target arch. The backend matrix / Docker build pass TARGETARCH
# (amd64|arm64); fall back to uname -m (aarch64|x86_64) for a local build.
RECON_ARCH?=$(or $(TARGETARCH),$(shell uname -m))
# Build ggml + the vendored libjpeg-turbo statically into libfacedetect.so (PIC)
# so the shared lib is self-contained: dlopen needs no libggml*.so alongside it,
# only system libs (libstdc++/libgomp/libc) the runtime image already provides.
# The vendored jpeg symbols are hidden via -Wl,--exclude-libs,ALL on the C++
# side, so only the facedetect_capi_* surface is exported.
CMAKE_ARGS?=-DCMAKE_BUILD_TYPE=Release -DFACEDETECT_SHARED=ON -DFACEDETECT_BUILD_CLI=OFF -DFACEDETECT_BUILD_TESTS=OFF -DBUILD_SHARED_LIBS=OFF -DCMAKE_POSITION_INDEPENDENT_CODE=ON
ifeq ($(NATIVE),false)
CMAKE_ARGS+=-DGGML_NATIVE=OFF
endif
# face-detect.cpp gates its GGML backends behind FACEDETECT_GGML_* options and
# does set(GGML_CUDA ${FACEDETECT_GGML_CUDA} CACHE BOOL "" FORCE), so a bare
# -DGGML_CUDA=ON is overwritten back to OFF. Forward the FACEDETECT_GGML_*
# options instead. (openblas is not gated, so -DGGML_BLAS passes through.)
ifeq ($(BUILD_TYPE),cublas)
CMAKE_ARGS+=-DFACEDETECT_GGML_CUDA=ON
# Opt-in cuDNN implicit-GEMM conv path (kills im2col on GPU, SCRFD 2.3x
# vs torch-cuDNN parity). Only the arm64 + CUDA 13 image (GB10/Jetson/L4T)
# ships libcudnn9 + the -dev headers, so gate cuDNN to that variant.
# x86 CUDA images carry no cuDNN -> enabling it there is a link failure.
ifeq ($(CUDA_MAJOR_VERSION),13)
ifneq (,$(filter arm64 aarch64,$(RECON_ARCH)))
CMAKE_ARGS+=-DFACEDETECT_GGML_CUDNN=ON
endif
endif
else ifeq ($(BUILD_TYPE),openblas)
CMAKE_ARGS+=-DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS
else ifeq ($(BUILD_TYPE),hipblas)
CMAKE_ARGS+=-DFACEDETECT_GGML_HIP=ON
else ifeq ($(BUILD_TYPE),vulkan)
CMAKE_ARGS+=-DFACEDETECT_GGML_VULKAN=ON
else ifeq ($(BUILD_TYPE),metal)
CMAKE_ARGS+=-DFACEDETECT_GGML_METAL=ON
endif
.PHONY: face-detect-grpc package build clean purge test all
all: face-detect-grpc
# Clone the upstream face-detect.cpp source at the pinned commit. Directory acts
# as the target so make only re-clones when missing. After a FACEDETECT_VERSION
# bump, run 'make purge && make' to refetch.
sources/face-detect.cpp:
mkdir -p sources/face-detect.cpp
cd sources/face-detect.cpp && \
git init -q && \
git remote add origin $(FACEDETECT_REPO) && \
git fetch --depth 1 origin $(FACEDETECT_VERSION) && \
git checkout FETCH_HEAD && \
git submodule update --init --recursive --depth 1 --single-branch
# Build the shared lib + header out-of-tree, then stage them next to the Go
# sources so purego.Dlopen("libfacedetect.so") and the cgo-less build both pick
# them up.
libfacedetect.so: sources/face-detect.cpp
cmake -B sources/face-detect.cpp/build-shared -S sources/face-detect.cpp $(CMAKE_ARGS)
cmake --build sources/face-detect.cpp/build-shared --config Release -j$(JOBS) --target facedetect
cp -fv sources/face-detect.cpp/build-shared/libfacedetect.so* ./ 2>/dev/null || true
cp -fv sources/face-detect.cpp/include/facedetect_capi.h ./
face-detect-grpc: libfacedetect.so main.go gofacedetect.go options.go
CGO_ENABLED=0 $(GOCMD) build -tags "$(GO_TAGS)" -o face-detect-grpc .
package: face-detect-grpc
bash package.sh
build: package
# Test target. The embed/detect/verify/analyze smoke specs are gated on
# FACEDETECT_BACKEND_TEST_MODEL + FACEDETECT_BACKEND_TEST_IMAGE; without them the
# heavy specs auto-skip and only the pure-Go parsing specs run.
test:
LD_LIBRARY_PATH=$(CURDIR):$$LD_LIBRARY_PATH $(GOCMD) test ./... -count=1
clean: purge
rm -rf libfacedetect.so* facedetect_capi.h package face-detect-grpc
purge:
rm -rf sources/face-detect.cpp