mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-05-16 20:52:08 -04:00
Code Issues Packages Projects Releases Wiki Activity
Files
c02a50f2ab7ea32e3226212a53a05c795841bef1
LocalAI/backend/cpp/llama-cpp/Makefile
Ettore Di Giacinto c02a50f2ab feat(llama-cpp): bump to d775992 and adapt to spec params refactor (#9618) 
Bumps backend/cpp/llama-cpp/Makefile LLAMA_VERSION from 665abc6 to
d775992, picking up upstream PR ggml-org/llama.cpp#22397 which splits
common_params_speculative into nested draft / ngram_simple / ngram_mod
sub-structs. Renames every grpc-server.cpp reference to match:

  speculative.mparams_dft.path  -> speculative.draft.mparams.path
  speculative.{n_max,n_min}     -> speculative.draft.{n_max,n_min}
  speculative.{p_min,p_split}   -> speculative.draft.{p_min,p_split}
  speculative.{n_gpu_layers,n_ctx} -> speculative.draft.{n_gpu_layers,n_ctx}
  speculative.ngram_size_n      -> speculative.ngram_simple.size_n
  speculative.ngram_size_m      -> speculative.ngram_simple.size_m
  speculative.ngram_min_hits    -> speculative.ngram_simple.min_hits

The "speculative.n_max" JSON key sent to the upstream server stays
unchanged — server-task.cpp still reads it and routes the value into
draft.n_max internally.

The turboquant fork (TheTom/llama-cpp-turboquant @ 11a241d) branched
before #22397 and still exposes the flat layout. Since turboquant
reuses the shared backend/cpp/llama-cpp/grpc-server.cpp, extend
patch-grpc-server.sh with an idempotent sed block that reverts the
ten field references back to the legacy flat names on the build copy
only — the original under backend/cpp/llama-cpp/ stays compiling
against vanilla upstream. Drop the block once the fork rebases.

ik-llama-cpp has its own grpc-server.cpp with no speculative refs
(0/2661 lines), so it is unaffected.

Validated locally with `make docker-build-llama-cpp` (avx, avx2,
avx512, fallback, grpc + rpc-server all built; image exported).


Assisted-by: Claude:claude-opus-4-7 [Bash Read Edit]

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2026-04-30 08:44:43 +02:00

168 lines
7.0 KiB
Makefile
Raw Blame History

LLAMA_VERSION?=d77599234ea6e498775aeadbce665eece5bd98cd
LLAMA_REPO?=https://github.com/ggerganov/llama.cpp
CMAKE_ARGS?=
BUILD_TYPE?=
NATIVE?=false
ONEAPI_VARS?=/opt/intel/oneapi/setvars.sh
TARGET?=--target grpc-server
JOBS?=$(shell nproc 2>/dev/null || sysctl -n hw.ncpu 2>/dev/null || echo 1)
ARCH?=$(shell uname -m)
# Disable Shared libs as we are linking on static gRPC and we can't mix shared and static
CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF -DLLAMA_CURL=OFF
CURRENT_MAKEFILE_DIR := $(dir $(abspath $(lastword $(MAKEFILE_LIST))))
ifeq ($(NATIVE),false)
CMAKE_ARGS+=-DGGML_NATIVE=OFF -DLLAMA_OPENSSL=OFF
endif
# If build type is cublas, then we set -DGGML_CUDA=ON to CMAKE_ARGS automatically
ifeq ($(BUILD_TYPE),cublas)
CMAKE_ARGS+=-DGGML_CUDA=ON
# If build type is openblas then we set -DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS
# to CMAKE_ARGS automatically
else ifeq ($(BUILD_TYPE),openblas)
CMAKE_ARGS+=-DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS
# If build type is clblas (openCL) we set -DGGML_CLBLAST=ON -DCLBlast_DIR=/some/path
else ifeq ($(BUILD_TYPE),clblas)
CMAKE_ARGS+=-DGGML_CLBLAST=ON -DCLBlast_DIR=/some/path
# If it's hipblas we do have also to set CC=/opt/rocm/llvm/bin/clang CXX=/opt/rocm/llvm/bin/clang++
else ifeq ($(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,gfx1151,gfx1200,gfx1201
CMAKE_ARGS+=-DGGML_HIP=ON -DAMDGPU_TARGETS=$(AMDGPU_TARGETS)
else ifeq ($(BUILD_TYPE),vulkan)
CMAKE_ARGS+=-DGGML_VULKAN=1
else ifeq ($(OS),Darwin)
ifeq ($(BUILD_TYPE),)
BUILD_TYPE=metal
endif
ifneq ($(BUILD_TYPE),metal)
CMAKE_ARGS+=-DGGML_METAL=OFF
else
CMAKE_ARGS+=-DGGML_METAL=ON
CMAKE_ARGS+=-DGGML_METAL_EMBED_LIBRARY=ON
CMAKE_ARGS+=-DGGML_METAL_USE_BF16=ON
CMAKE_ARGS+=-DGGML_OPENMP=OFF
endif
TARGET+=--target ggml-metal
endif
ifeq ($(BUILD_TYPE),sycl_f16)
CMAKE_ARGS+=-DGGML_SYCL=ON \
-DCMAKE_C_COMPILER=icx \
-DCMAKE_CXX_COMPILER=icpx \
-DCMAKE_CXX_FLAGS="-fsycl" \
-DGGML_SYCL_F16=ON
endif
ifeq ($(BUILD_TYPE),sycl_f32)
CMAKE_ARGS+=-DGGML_SYCL=ON \
-DCMAKE_C_COMPILER=icx \
-DCMAKE_CXX_COMPILER=icpx \
-DCMAKE_CXX_FLAGS="-fsycl"
endif
INSTALLED_PACKAGES=$(CURDIR)/../grpc/installed_packages
INSTALLED_LIB_CMAKE=$(INSTALLED_PACKAGES)/lib/cmake
ADDED_CMAKE_ARGS=-Dabsl_DIR=${INSTALLED_LIB_CMAKE}/absl \
-DProtobuf_DIR=${INSTALLED_LIB_CMAKE}/protobuf \
-Dutf8_range_DIR=${INSTALLED_LIB_CMAKE}/utf8_range \
-DgRPC_DIR=${INSTALLED_LIB_CMAKE}/grpc \
-DCMAKE_CXX_STANDARD_INCLUDE_DIRECTORIES=${INSTALLED_PACKAGES}/include
build-llama-cpp-grpc-server:
# Conditionally build grpc for the llama backend to use if needed
ifdef BUILD_GRPC_FOR_BACKEND_LLAMA
$(MAKE) -C ../../grpc build
_PROTOBUF_PROTOC=${INSTALLED_PACKAGES}/bin/proto \
_GRPC_CPP_PLUGIN_EXECUTABLE=${INSTALLED_PACKAGES}/bin/grpc_cpp_plugin \
PATH="${INSTALLED_PACKAGES}/bin:${PATH}" \
CMAKE_ARGS="${CMAKE_ARGS} ${ADDED_CMAKE_ARGS}" \
LLAMA_VERSION=$(LLAMA_VERSION) \
$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../$(VARIANT) grpc-server
else
echo "BUILD_GRPC_FOR_BACKEND_LLAMA is not defined."
LLAMA_VERSION=$(LLAMA_VERSION) $(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../$(VARIANT) grpc-server
endif
llama-cpp-avx2: llama.cpp
cp -rf $(CURRENT_MAKEFILE_DIR)/../llama-cpp $(CURRENT_MAKEFILE_DIR)/../llama-cpp-avx2-build
$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../llama-cpp-avx2-build purge
$(info ${GREEN}I llama-cpp build info:avx2${RESET})
CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=on -DGGML_AVX512=off -DGGML_FMA=on -DGGML_F16C=on" $(MAKE) VARIANT="llama-cpp-avx2-build" build-llama-cpp-grpc-server
cp -rfv $(CURRENT_MAKEFILE_DIR)/../llama-cpp-avx2-build/grpc-server llama-cpp-avx2
llama-cpp-avx512: llama.cpp
cp -rf $(CURRENT_MAKEFILE_DIR)/../llama-cpp $(CURRENT_MAKEFILE_DIR)/../llama-cpp-avx512-build
$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../llama-cpp-avx512-build purge
$(info ${GREEN}I llama-cpp build info:avx512${RESET})
CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=off -DGGML_AVX512=on -DGGML_FMA=on -DGGML_F16C=on" $(MAKE) VARIANT="llama-cpp-avx512-build" build-llama-cpp-grpc-server
cp -rfv $(CURRENT_MAKEFILE_DIR)/../llama-cpp-avx512-build/grpc-server llama-cpp-avx512
llama-cpp-avx: llama.cpp
cp -rf $(CURRENT_MAKEFILE_DIR)/../llama-cpp $(CURRENT_MAKEFILE_DIR)/../llama-cpp-avx-build
$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../llama-cpp-avx-build purge
$(info ${GREEN}I llama-cpp build info:avx${RESET})
CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) VARIANT="llama-cpp-avx-build" build-llama-cpp-grpc-server
cp -rfv $(CURRENT_MAKEFILE_DIR)/../llama-cpp-avx-build/grpc-server llama-cpp-avx
llama-cpp-fallback: llama.cpp
cp -rf $(CURRENT_MAKEFILE_DIR)/../llama-cpp $(CURRENT_MAKEFILE_DIR)/../llama-cpp-fallback-build
$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../llama-cpp-fallback-build purge
$(info ${GREEN}I llama-cpp build info:fallback${RESET})
CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) VARIANT="llama-cpp-fallback-build" build-llama-cpp-grpc-server
cp -rfv $(CURRENT_MAKEFILE_DIR)/../llama-cpp-fallback-build/grpc-server llama-cpp-fallback
llama-cpp-grpc: llama.cpp
cp -rf $(CURRENT_MAKEFILE_DIR)/../llama-cpp $(CURRENT_MAKEFILE_DIR)/../llama-cpp-grpc-build
$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../llama-cpp-grpc-build purge
$(info ${GREEN}I llama-cpp build info:grpc${RESET})
CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_RPC=ON -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" TARGET="--target grpc-server --target rpc-server" $(MAKE) VARIANT="llama-cpp-grpc-build" build-llama-cpp-grpc-server
cp -rfv $(CURRENT_MAKEFILE_DIR)/../llama-cpp-grpc-build/grpc-server llama-cpp-grpc
llama-cpp-rpc-server: llama-cpp-grpc
cp -rf $(CURRENT_MAKEFILE_DIR)/../llama-cpp-grpc-build/llama.cpp/build/bin/rpc-server llama-cpp-rpc-server
llama.cpp:
mkdir -p llama.cpp
cd llama.cpp && \
git init && \
git remote add origin $(LLAMA_REPO) && \
git fetch --all --tags && \
git checkout -b build $(LLAMA_VERSION) && \
git submodule update --init --recursive --depth 1 --single-branch
llama.cpp/tools/grpc-server: llama.cpp
mkdir -p llama.cpp/tools/grpc-server
bash prepare.sh
rebuild:
bash prepare.sh
rm -rf grpc-server
$(MAKE) grpc-server
package:
bash package.sh
purge:
rm -rf llama.cpp/build
rm -rf llama.cpp/tools/grpc-server
rm -rf grpc-server
clean: purge
rm -rf llama.cpp
grpc-server: llama.cpp llama.cpp/tools/grpc-server
@echo "Building grpc-server with $(BUILD_TYPE) build type and $(CMAKE_ARGS)"
ifneq (,$(findstring sycl,$(BUILD_TYPE)))
+bash -c "source $(ONEAPI_VARS); \
cd llama.cpp && mkdir -p build && cd build && cmake .. $(CMAKE_ARGS) && cmake --build . --config Release -j $(JOBS) $(TARGET)"
else
+cd llama.cpp && mkdir -p build && cd build && cmake .. $(CMAKE_ARGS) && cmake --build . --config Release -j $(JOBS) $(TARGET)
endif
cp llama.cpp/build/bin/grpc-server .
Reference in New Issue View Git Blame Copy Permalink