LocalAI/backend/cpp/ds4/Makefile

# ds4 backend Makefile.
#
# Upstream pin lives below as DS4_VERSION?=8db89fe083ae4d17c9a2428ccd29803d3ae8f577
# (.github/bump_deps.sh) can find and update it - matches the
# llama-cpp / ik-llama-cpp / turboquant convention.

DS4_VERSION?=8db89fe083ae4d17c9a2428ccd29803d3ae8f577
DS4_REPO?=https://github.com/antirez/ds4

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)

CMAKE_ARGS ?= -DCMAKE_BUILD_TYPE=Release

# nvcc must be told the target architecture explicitly for a cublas build, and
# this is not a tuning knob. Upstream's Makefile leaves CUDA_ARCH empty and its
# `cuda` target REFUSES to build without one, offering `cuda-spark`
# (CUDA_ARCH=sm_121) and `cuda-generic` (CUDA_ARCH=native) instead. We drive its
# object targets directly, which bypasses that guard: nvcc then compiles with no
# -arch at all, and the kernels run as JIT'd PTX for its default architecture.
# On GB10 (sm_121) that silently produced corrupt inference output above a
# ~128-token prefill batch and ~77x slower prefill (4.21 t/s vs 325.70 t/s,
# measured on the same box with the same model). No CI runner has a GPU, so
# `native` has nothing to enumerate there.
#
# Upstream's CUDA_ARCH takes a SINGLE value (see its sm_120/sm_121 special cases
# and the `-arch=$(CUDA_ARCH)` fallback), so it cannot express the fat binary
# these images need. NVCC_ARCH_FLAGS is overridden instead: a command-line
# assignment wins over the `:=` in upstream's Makefile, and its NVCCFLAGS
# expands whatever we pass.
#
# The architecture lists are copied from backend/go/vllm-cpp/Makefile rather
# than invented, so the two CUDA images cover the same GPUs: amd64 datacenter +
# consumer, and l4t/arm64 covering Orin (87), Thor (110) and GB10 (121a).
#
# -DDS4_CUDA_HAVE_MXF4=1 is deliberately NOT set. Upstream only defines it for
# single-arch sm_120/sm_121 builds and guards the code with a plain #ifdef
# rather than __CUDA_ARCH__, so it cannot be combined with older archs in one
# fat binary. It gates an optional MXFP4 indexer fast path whose #ifndef branch
# returns 0 and falls back to the generic path, so omitting it costs some speed
# on GB10, not correctness. Revisit if upstream adds __CUDA_ARCH__ guards.
#
# An EMPTY CUDA_MAJOR_VERSION means a local developer build, not CI: fall back
# to upstream's own `native` handling, which needs a GPU present but is what a
# developer building on their own machine wants. Both variables are `?=` so an
# explicit value on the command line always wins.
UNAME_M := $(shell uname -m)
CUDA_MAJOR_VERSION ?=
ifeq ($(BUILD_TYPE),cublas)
ifeq ($(CUDA_MAJOR_VERSION),13)
ifeq ($(UNAME_M),aarch64)
    DS4_NVCC_ARCH_FLAGS ?= -gencode arch=compute_87,code=sm_87 \
                           -gencode arch=compute_90a,code=sm_90a \
                           -gencode arch=compute_100a,code=sm_100a \
                           -gencode arch=compute_110,code=sm_110 \
                           -gencode arch=compute_121a,code=sm_121a
else
    DS4_NVCC_ARCH_FLAGS ?= -gencode arch=compute_80,code=sm_80 \
                           -gencode arch=compute_86,code=sm_86 \
                           -gencode arch=compute_89,code=sm_89 \
                           -gencode arch=compute_90a,code=sm_90a \
                           -gencode arch=compute_100a,code=sm_100a \
                           -gencode arch=compute_103a,code=sm_103a \
                           -gencode arch=compute_120a,code=sm_120a \
                           -gencode arch=compute_121a,code=sm_121a
endif
    DS4_ARCH_MAKEVARS := NVCC_ARCH_FLAGS="$(DS4_NVCC_ARCH_FLAGS)"
else ifeq ($(CUDA_MAJOR_VERSION),)
    # Local build: let upstream resolve the host GPU.
    DS4_ARCH_MAKEVARS := CUDA_ARCH=native
else
    $(error CUDA_MAJOR_VERSION=$(CUDA_MAJOR_VERSION) has no architecture list here (13 does). Leave it empty for a native build, or pass DS4_NVCC_ARCH_FLAGS explicitly.)
endif
endif

# Upstream splits distributed inference, tensor-parallel transport, the SSD
# expert cache, and layer placement into GPU-agnostic translation units. They
# are shared by every GPU mode, so append them unconditionally below.
ifeq ($(BUILD_TYPE),cublas)
    CMAKE_ARGS += -DDS4_GPU=cuda
    DS4_OBJ_TARGET := ds4.o ds4_cuda.o ds4_distributed.o ds4_tp.o ds4_ssd.o ds4_layer_pack.o \
        cuda/mmq/ds4_ggml_stubs.o cuda/mmq/ds4_mmq.o cuda/mmq/ds4_mmq_d2r.o \
        cuda/mmq/quantize.o cuda/mmq/mmid.o cuda/mmq/mmvq.o cuda/mmq/ds4_repack.o
else ifeq ($(UNAME_S),Darwin)
    CMAKE_ARGS += -DDS4_GPU=metal
    DS4_OBJ_TARGET := ds4.o ds4_metal.o ds4_distributed.o ds4_tp.o ds4_ssd.o ds4_layer_pack.o
else
    # CPU reference path (Linux only - macOS CPU path is broken by VM bug per ds4 README).
    CMAKE_ARGS += -DDS4_GPU=cpu
    DS4_OBJ_TARGET := ds4_cpu.o ds4_distributed.o ds4_tp.o ds4_ssd.o ds4_layer_pack.o
endif

ifneq ($(NATIVE),true)
    CMAKE_ARGS += -DDS4_NATIVE=OFF
endif

.PHONY: grpc-server package clean purge test all
all: grpc-server

# Clone the upstream ds4 source at the pinned commit. Directory acts as the
# target so make only re-clones when missing. After a DS4_VERSION bump,
# run 'make purge && make' to refetch (or rely on CI's clean build).
ds4:
	mkdir -p ds4
	cd ds4 && \
	git init -q && \
	git remote add origin $(DS4_REPO) && \
	git fetch --depth 1 origin $(DS4_VERSION) && \
	git checkout FETCH_HEAD

# Build ds4's engine object files via its own Makefile, which already encodes
# the right per-platform compile flags (Objective-C/Metal on Darwin, nvcc on Linux+CUDA).
ds4/ds4.o: ds4
ifeq ($(BUILD_TYPE),cublas)
	+$(MAKE) -C ds4 $(DS4_ARCH_MAKEVARS) $(DS4_OBJ_TARGET)
else ifeq ($(UNAME_S),Darwin)
	+$(MAKE) -C ds4 ds4.o ds4_metal.o ds4_distributed.o ds4_tp.o ds4_ssd.o ds4_layer_pack.o
else
	+$(MAKE) -C ds4 ds4_cpu.o ds4_distributed.o ds4_tp.o ds4_ssd.o ds4_layer_pack.o
endif

grpc-server: ds4/ds4.o
	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
	cp $(BUILD_DIR)/ds4-worker ds4-worker

package: grpc-server
	bash package.sh

test:
	@echo "ds4 backend: e2e coverage at tests/e2e-backends/ (BACKEND_BINARY mode)"

clean:
	rm -rf $(BUILD_DIR) grpc-server ds4-worker package
	if [ -d ds4 ]; then $(MAKE) -C ds4 clean; fi

purge: clean
	rm -rf ds4