From 3f52776a1cd762729347cf9991f8e3ee3eb9c201 Mon Sep 17 00:00:00 2001
From: Ettore Di Giacinto <mudler@localai.io>
Date: Wed, 23 Jul 2025 21:18:47 +0200
Subject: [PATCH] WIP

---
 backend/Dockerfile.llama-cpp         | 27 ++++++++++-----------
 backend/cpp/llama-cpp/CMakeLists.txt |  2 ++
 backend/cpp/llama-cpp/Makefile       | 35 ++++++----------------------
 backend/cpp/llama-cpp/run.sh         | 32 ++-----------------------
 4 files changed, 23 insertions(+), 73 deletions(-)

diff --git a/backend/Dockerfile.llama-cpp b/backend/Dockerfile.llama-cpp
index 6d679eb0c9cf..9aab76355119 100644
--- a/backend/Dockerfile.llama-cpp
+++ b/backend/Dockerfile.llama-cpp
@@ -11,6 +11,7 @@ ARG GRPC_MAKEFLAGS="-j4 -Otarget"
 ARG GRPC_VERSION=v1.65.0
 ARG CMAKE_FROM_SOURCE=false
 ARG CMAKE_VERSION=3.26.4
+ARG PROTOBUF_VERSION=v21.12
 
 ENV MAKEFLAGS=${GRPC_MAKEFLAGS}
 
@@ -49,6 +50,14 @@ RUN git clone --recurse-submodules --jobs 4 -b ${GRPC_VERSION} --depth 1 --shall
     make install && \
     rm -rf /build
 
+RUN git clone --recurse-submodules --branch ${PROTOBUF_VERSION} https://github.com/protocolbuffers/protobuf.git && \
+    mkdir -p /build/protobuf/build && \
+    cd /build/protobuf/build && \
+    cmake -Dprotobuf_BUILD_SHARED_LIBS=ON -Dprotobuf_BUILD_TESTS=OFF .. && \
+    make && \
+    make install && \
+    rm -rf /build
+
 FROM ${BASE_IMAGE} AS builder
 ARG BACKEND=rerankers
 ARG BUILD_TYPE
@@ -180,21 +189,9 @@ COPY --from=grpc /opt/grpc /usr/local
 
 COPY . /LocalAI
 
-## Otherwise just run the normal build
-RUN <<EOT bash
-if [ "${TARGETARCH}" = "arm64" ] || [ "${BUILD_TYPE}" = "hipblas" ]; then \
-        cd /LocalAI/backend/cpp/llama-cpp && make llama-cpp-fallback && \
-        make llama-cpp-grpc && make llama-cpp-rpc-server; \
-    else \
-        cd /LocalAI/backend/cpp/llama-cpp && make llama-cpp-avx && \
-        make llama-cpp-avx2 && \
-        make llama-cpp-avx512 && \
-        make llama-cpp-fallback && \
-        make llama-cpp-grpc && \
-        make llama-cpp-rpc-server; \
-    fi  
-EOT
-
+RUN make -C /LocalAI/backend/cpp/llama-cpp llama-cpp
+RUN make -C /LocalAI/backend/cpp/llama-cpp llama-cpp-grpc
+RUN make -C /LocalAI/backend/cpp/llama-cpp llama-cpp-rpc-server
 
 # Copy libraries using a script to handle architecture differences
 RUN make -C /LocalAI/backend/cpp/llama-cpp package
diff --git a/backend/cpp/llama-cpp/CMakeLists.txt b/backend/cpp/llama-cpp/CMakeLists.txt
index c839800b86af..bdbeda6d00e7 100644
--- a/backend/cpp/llama-cpp/CMakeLists.txt
+++ b/backend/cpp/llama-cpp/CMakeLists.txt
@@ -17,6 +17,8 @@ if (${CMAKE_SYSTEM_NAME} MATCHES "Darwin")
     include_directories("${HOMEBREW_DEFAULT_PREFIX}/include")
 endif()
 
+set(Protobuf_USE_STATIC_LIBS OFF)
+set(gRPC_USE_STATIC_LIBS OFF)
 find_package(absl CONFIG REQUIRED)
 find_package(Protobuf CONFIG REQUIRED)
 find_package(gRPC CONFIG REQUIRED)
diff --git a/backend/cpp/llama-cpp/Makefile b/backend/cpp/llama-cpp/Makefile
index 6adb4e6ed0fe..bd0729d73c4f 100644
--- a/backend/cpp/llama-cpp/Makefile
+++ b/backend/cpp/llama-cpp/Makefile
@@ -9,7 +9,7 @@ ONEAPI_VARS?=/opt/intel/oneapi/setvars.sh
 TARGET?=--target grpc-server
 
 # 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
+CMAKE_ARGS+=-DBUILD_SHARED_LIBS=ON -DLLAMA_CURL=OFF -DGGML_CPU_ALL_VARIANTS=ON -DGGML_BACKEND_DL=ON
 
 CURRENT_MAKEFILE_DIR := $(dir $(abspath $(lastword $(MAKEFILE_LIST))))
 ifeq ($(NATIVE),false)
@@ -89,33 +89,12 @@ else
 	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" $(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" $(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: llama.cpp
+	cp -rf $(CURRENT_MAKEFILE_DIR)/../llama-cpp $(CURRENT_MAKEFILE_DIR)/../llama-cpp-build
+	$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../llama-cpp-build purge
+	$(info ${GREEN}I llama-cpp build info:${RESET})
+	CMAKE_ARGS="$(CMAKE_ARGS)" $(MAKE) VARIANT="llama-cpp-build" build-llama-cpp-grpc-server
+	cp -rfv $(CURRENT_MAKEFILE_DIR)/../llama-cpp-build/grpc-server llama-cpp
 
 llama-cpp-grpc: llama.cpp
 	cp -rf $(CURRENT_MAKEFILE_DIR)/../llama-cpp $(CURRENT_MAKEFILE_DIR)/../llama-cpp-grpc-build
diff --git a/backend/cpp/llama-cpp/run.sh b/backend/cpp/llama-cpp/run.sh
index dde3161fa513..22f314264c9c 100755
--- a/backend/cpp/llama-cpp/run.sh
+++ b/backend/cpp/llama-cpp/run.sh
@@ -6,34 +6,9 @@ CURDIR=$(dirname "$(realpath $0)")
 
 cd /
 
-echo "CPU info:"
-grep -e "model\sname" /proc/cpuinfo | head -1
-grep -e "flags" /proc/cpuinfo | head -1
-
-BINARY=llama-cpp-fallback
-
-if grep -q -e "\savx\s" /proc/cpuinfo ; then
-	echo "CPU:    AVX    found OK"
-	if [ -e $CURDIR/llama-cpp-avx ]; then
-		BINARY=llama-cpp-avx
-	fi
-fi
-
-if grep -q -e "\savx2\s" /proc/cpuinfo ; then
-	echo "CPU:    AVX2   found OK"
-	if [ -e $CURDIR/llama-cpp-avx2 ]; then
-		BINARY=llama-cpp-avx2
-	fi
-fi
-
-# Check avx 512
-if grep -q -e "\savx512f\s" /proc/cpuinfo ; then
-	echo "CPU:    AVX512F found OK"
-	if [ -e $CURDIR/llama-cpp-avx512 ]; then
-		BINARY=llama-cpp-avx512
-	fi
-fi
+BINARY=llama-cpp
 
+## P2P/GRPC mode
 if [ -n "$LLAMACPP_GRPC_SERVERS" ]; then
 	if [ -e $CURDIR/llama-cpp-grpc ]; then
 		BINARY=llama-cpp-grpc
@@ -56,6 +31,3 @@ fi
 
 echo "Using binary: $BINARY"
 exec $CURDIR/$BINARY "$@"
-
-# In case we fail execing, just run fallback
-exec $CURDIR/llama-cpp-fallback "$@"
\ No newline at end of file