mirror of
https://github.com/mudler/LocalAI.git
synced 2026-09-13 14:56:11 -04:00
137dfcf15a
* ⬆️ Update antirez/ds4 Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> * fix(ds4): link upstream CUDA MMQ objects The updated ds4 CUDA object now calls into the vendored MMQ implementation. Build and link those objects into both the gRPC server and distributed worker. Assisted-by: Codex:gpt-5 [Codex] --------- Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: mudler <2420543+mudler@users.noreply.github.com> Co-authored-by: localai-org-maint-bot <306269227+localai-org-maint-bot@users.noreply.github.com>
85 lines
2.9 KiB
Makefile
85 lines
2.9 KiB
Makefile
# ds4 backend Makefile.
|
|
#
|
|
# Upstream pin lives below as DS4_VERSION?=b7e9f0091139999b6c070a57590c447c5741da5c
|
|
# (.github/bump_deps.sh) can find and update it - matches the
|
|
# llama-cpp / ik-llama-cpp / turboquant convention.
|
|
|
|
DS4_VERSION?=b7e9f0091139999b6c070a57590c447c5741da5c
|
|
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 := $(shell uname -s)
|
|
|
|
CMAKE_ARGS ?= -DCMAKE_BUILD_TYPE=Release
|
|
|
|
# Upstream splits distributed inference, tensor-parallel transport, the SSD
|
|
# expert cache, and layer placement into GPU-agnostic translation units. They
|
|
# are shared by every GPU mode, so append them unconditionally below.
|
|
ifeq ($(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 $(DS4_OBJ_TARGET)
|
|
else ifeq ($(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
|