mirror of
https://github.com/mudler/LocalAI.git
synced 2026-05-29 11:07:18 -04:00
7a4ca8f60d
Adds a Go native gRPC backend that dlopens librfdetrcpp.so (built from
mudler/rf-detr.cpp at the pinned RFDETR_VERSION) via purego and exposes
the rfdetr.cpp inference pipeline through LocalAI's existing Detect RPC.
Supports all 5 RF-DETR detection variants (Nano/Small/Base/Medium/Large)
and 6 segmentation variants (SegNano/SegSmall/SegMedium/SegLarge/
SegXLarge/Seg2XLarge) with F32/F16/Q8_0/Q4_K quantizations. Pre-built
GGUFs ship at mudler/rfdetr-cpp-* on HuggingFace.
Detection returns Bbox + class_name + confidence; segmentation also
returns PNG-encoded per-detection masks via the rfdetr_capi accessor
functions (rfdetr_capi_get_detection_{class_id,box,score,class_name,
mask_png}).
End-to-end verified through POST /v1/detection: HTTP -> gRPC -> purego
dlopen -> rfdetr.cpp -> ggml -> response (9 detections on the detection
model, 21 detections + valid PNG masks on the seg-nano model against
the kitchen fixture).
Wiring:
- backend/go/rfdetr-cpp/{main.go,gorfdetrcpp.go,CMakeLists.txt,
Makefile,run.sh,package.sh,test.sh,.gitignore}
- Top-level Makefile: BACKEND_RFDETR_CPP, docker-build target,
.NOTPARALLEL, prepare-test-extra, test-extra
- backend/go/rfdetr-cpp/Makefile: `test` target invoked by test-extra
- .github/backend-matrix.yml: CPU + CUDA-12/13 + L4T CUDA-12/13
(arm64) + HIP + Vulkan (amd64 + arm64) + SYCL f32/f16
- backend/index.yaml: rfdetr-cpp meta anchor + latest/development
image entries for every matrix tag-suffix
- .github/workflows/bump_deps.yaml: RFDETR_VERSION pin tracking
(mudler/rf-detr.cpp branch main)
- gallery/index.yaml: 11 rfdetr-cpp-* entries (nano + 4 detection
variants + 6 seg variants), all backed by mudler/rfdetr-cpp-*
on HuggingFace with sha256 pinning on the F16 default
- core/gallery/importers/rfdetr.go: GGUF auto-routing for HF imports
(mudler/rfdetr-cpp-* repos route to rfdetr-cpp, Transformer-format
repos stay on the Python rfdetr backend; explicit preferences.backend
overrides both heuristics)
- core/gallery/importers/rfdetr_test.go: table-driven coverage of the
auto-routing + a live mudler/rfdetr-cpp-nano cross-check
scripts/changed-backends.js needs no change: the existing
Dockerfile.golang -> backend/go/${item.backend}/ branch already routes
the 9 rfdetr-cpp matrix entries to the correct backend path.
Assisted-by: Claude:claude-opus-4-7 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
136 lines
4.5 KiB
Makefile
136 lines
4.5 KiB
Makefile
CMAKE_ARGS?=
|
|
BUILD_TYPE?=
|
|
NATIVE?=false
|
|
|
|
GOCMD?=go
|
|
GO_TAGS?=
|
|
JOBS?=$(shell nproc --ignore=1)
|
|
|
|
# rt-detr.cpp (GitHub redirects the historical mudler/rt-detr.cpp to the new
|
|
# mudler/rf-detr.cpp slug). Pin to a specific commit if you need a stable
|
|
# build; leaving this on `master` always picks up the latest C-API surface
|
|
# (incl. the per-detection accessor functions used by gorfdetrcpp.go).
|
|
RFDETR_REPO?=https://github.com/mudler/rf-detr.cpp.git
|
|
RFDETR_VERSION?=main
|
|
|
|
ifeq ($(NATIVE),false)
|
|
CMAKE_ARGS+=-DGGML_NATIVE=OFF
|
|
endif
|
|
|
|
# Forward LocalAI's BUILD_TYPE to the matching ggml backend switch.
|
|
ifeq ($(BUILD_TYPE),cublas)
|
|
CMAKE_ARGS+=-DGGML_CUDA=ON -DRFDETR_GGML_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
|
|
else ifeq ($(BUILD_TYPE),hipblas)
|
|
ROCM_HOME ?= /opt/rocm
|
|
ROCM_PATH ?= /opt/rocm
|
|
export CXX=$(ROCM_HOME)/llvm/bin/clang++
|
|
export CC=$(ROCM_HOME)/llvm/bin/clang
|
|
AMDGPU_TARGETS?=gfx908,gfx90a,gfx942,gfx950,gfx1030,gfx1100,gfx1101,gfx1102,gfx1200,gfx1201
|
|
CMAKE_ARGS+=-DGGML_HIPBLAS=ON -DRFDETR_GGML_HIPBLAS=ON -DAMDGPU_TARGETS=$(AMDGPU_TARGETS)
|
|
else ifeq ($(BUILD_TYPE),vulkan)
|
|
CMAKE_ARGS+=-DGGML_VULKAN=ON -DRFDETR_GGML_VULKAN=ON
|
|
else ifeq ($(OS),Darwin)
|
|
ifneq ($(BUILD_TYPE),metal)
|
|
CMAKE_ARGS+=-DGGML_METAL=OFF
|
|
else
|
|
CMAKE_ARGS+=-DGGML_METAL=ON
|
|
CMAKE_ARGS+=-DGGML_METAL_EMBED_LIBRARY=ON
|
|
CMAKE_ARGS+=-DRFDETR_GGML_METAL=ON
|
|
endif
|
|
endif
|
|
|
|
ifeq ($(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/rt-detr.cpp:
|
|
mkdir -p sources && \
|
|
git clone --recursive $(RFDETR_REPO) sources/rt-detr.cpp && \
|
|
cd sources/rt-detr.cpp && \
|
|
git checkout $(RFDETR_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 = librfdetrcpp-avx.so librfdetrcpp-avx2.so librfdetrcpp-avx512.so librfdetrcpp-fallback.so
|
|
else
|
|
# On non-Linux (e.g., Darwin), build only fallback variant
|
|
VARIANT_TARGETS = librfdetrcpp-fallback.so
|
|
endif
|
|
|
|
rfdetr-cpp: main.go gorfdetrcpp.go $(VARIANT_TARGETS)
|
|
CGO_ENABLED=0 $(GOCMD) build -tags "$(GO_TAGS)" -o rfdetr-cpp ./
|
|
|
|
package: rfdetr-cpp
|
|
bash package.sh
|
|
|
|
build: package
|
|
|
|
clean: purge
|
|
rm -rf librfdetrcpp*.so rfdetr-cpp package sources
|
|
|
|
purge:
|
|
rm -rf build*
|
|
|
|
# Build all variants (Linux only)
|
|
ifeq ($(UNAME_S),Linux)
|
|
librfdetrcpp-avx.so: sources/rt-detr.cpp
|
|
rm -rfv build-$@
|
|
$(info ${GREEN}I rfdetr-cpp build info:avx${RESET})
|
|
SO_TARGET=$@ CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) librfdetrcpp-custom
|
|
rm -rfv build-$@
|
|
|
|
librfdetrcpp-avx2.so: sources/rt-detr.cpp
|
|
rm -rfv build-$@
|
|
$(info ${GREEN}I rfdetr-cpp build info:avx2${RESET})
|
|
SO_TARGET=$@ CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=on -DGGML_AVX512=off -DGGML_FMA=on -DGGML_F16C=on -DGGML_BMI2=on" $(MAKE) librfdetrcpp-custom
|
|
rm -rfv build-$@
|
|
|
|
librfdetrcpp-avx512.so: sources/rt-detr.cpp
|
|
rm -rfv build-$@
|
|
$(info ${GREEN}I rfdetr-cpp build info:avx512${RESET})
|
|
SO_TARGET=$@ CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=on -DGGML_AVX512=on -DGGML_FMA=on -DGGML_F16C=on -DGGML_BMI2=on" $(MAKE) librfdetrcpp-custom
|
|
rm -rfv build-$@
|
|
endif
|
|
|
|
# Build fallback variant (all platforms)
|
|
librfdetrcpp-fallback.so: sources/rt-detr.cpp
|
|
rm -rfv build-$@
|
|
$(info ${GREEN}I rfdetr-cpp build info:fallback${RESET})
|
|
SO_TARGET=$@ CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) librfdetrcpp-custom
|
|
rm -rfv build-$@
|
|
|
|
librfdetrcpp-custom: CMakeLists.txt
|
|
mkdir -p build-$(SO_TARGET) && \
|
|
cd build-$(SO_TARGET) && \
|
|
cmake .. $(CMAKE_ARGS) && \
|
|
cmake --build . --config Release -j$(JOBS) && \
|
|
cd .. && \
|
|
mv build-$(SO_TARGET)/librfdetrcpp.so ./$(SO_TARGET)
|
|
|
|
all: rfdetr-cpp package
|
|
|
|
# `test` is invoked by the top-level Makefile's `test-extra` target. It builds
|
|
# the backend binary + the fallback shared library (needed for dlopen at
|
|
# runtime), then runs test.sh which downloads the test models + COCO image
|
|
# and exercises the gRPC Load/Detect wire path via the Go smoke test in
|
|
# main_test.go for both the detection and segmentation models.
|
|
test: rfdetr-cpp librfdetrcpp-fallback.so
|
|
bash test.sh
|