feat(llama-cpp): single x86 CPU build via ggml CPU_ALL_VARIANTS

Replace the per-microarch avx/avx2/avx512/fallback multi-binary build on
x86 with a single grpc-server plus the dlopen-able libggml-cpu-*.so set
that ggml's backend registry selects at runtime by probing host CPU
features. One build instead of four, broader microarch coverage (adds
alderlake AVX-VNNI, zen4 AVX512-BF16, sapphirerapids AMX), and the
shell-side /proc/cpuinfo probing in run.sh goes away.

Build/link notes:
- CPU_ALL_VARIANTS requires GGML_BACKEND_DL + BUILD_SHARED_LIBS=ON, so
  ggml/llama become shared objects. SHARED_LIBS is now a make variable
  (default OFF) so the override survives the recursive sub-make into the
  VARIANT build dir instead of being re-clobbered by the base flags.
- The cpu-all target also builds "--target ggml": the per-microarch
  backends are runtime-dlopened, not link deps, so they only compile via
  ggml's add_dependencies().
- hw_grpc_proto is pinned STATIC. Under BUILD_SHARED_LIBS=ON it would
  otherwise become a DSO referencing hidden-visibility symbols in the
  static libprotobuf.a, which fails to link ("hidden symbol ... is
  referenced by DSO"). Keeping it static links gRPC/protobuf into the
  executable while only ggml/llama stay shared, so no PIC or base-image
  change is required.
- package.sh bundles the libggml-*.so set into package/lib; ggml finds
  them by scanning the bundled ld.so directory (/proc/self/exe), which
  run.sh launches from.

Scope: x86 only. arm64/darwin keep the single fallback build. The
ik-llama-cpp / turboquant forks and the other ggml C++ backends are
unchanged; the same recipe applies but is out of scope here.

Validated with a full docker build plus a live inference smoke test:
the model loads, ggml selects the AVX512_BF16 variant on a Zen-class
host, and tokens generate correctly.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:claude-opus-4-8 [Claude Code]

backend/cpp/llama-cpp/CMakeLists.txt

@@ -50,8 +50,13 @@ add_custom_command(
         "${hw_proto}"
       DEPENDS "${hw_proto}")
 
-# hw_grpc_proto
-add_library(hw_grpc_proto
+# hw_grpc_proto: force STATIC. Under the CPU_ALL_VARIANTS build BUILD_SHARED_LIBS=ON
+# (ggml/llama become shared), which would otherwise make this glue library a DSO. As a
+# DSO it references the hidden-visibility symbols in the static libprotobuf.a, which the
+# linker cannot satisfy ("hidden symbol ... in libprotobuf.a is referenced by DSO").
+# Keeping it STATIC links protobuf/gRPC directly into the grpc-server executable while
+# only ggml/llama stay shared. No effect on the static variants (already BUILD_SHARED_LIBS=OFF).
+add_library(hw_grpc_proto STATIC
   ${hw_grpc_srcs}
   ${hw_grpc_hdrs}
   ${hw_proto_srcs}

backend/cpp/llama-cpp/Makefile

@@ -10,8 +10,16 @@ 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
+# Shared libs default to OFF: we link static gRPC and the avx/avx2/avx512/fallback
+# variants are fully static. The CPU_ALL_VARIANTS build flips SHARED_LIBS=ON (ggml/llama
+# become shared so the dynamic CPU backends work; gRPC stays static via its imported
+# targets). SHARED_LIBS is a make variable, not an appended -D, so it survives the
+# recursive sub-make into the VARIANT build dir (which re-parses this Makefile) instead
+# of being re-clobbered by a second -DBUILD_SHARED_LIBS=OFF. EXTRA_CMAKE_ARGS is the hook
+# the CPU_ALL_VARIANTS target uses to inject -DGGML_BACKEND_DL/-DGGML_CPU_ALL_VARIANTS.
+SHARED_LIBS?=OFF
+EXTRA_CMAKE_ARGS?=
+CMAKE_ARGS+=-DBUILD_SHARED_LIBS=$(SHARED_LIBS) -DLLAMA_CURL=OFF $(EXTRA_CMAKE_ARGS)
 
 CURRENT_MAKEFILE_DIR := $(dir $(abspath $(lastword $(MAKEFILE_LIST))))
 ifeq ($(NATIVE),false)
@@ -120,6 +128,30 @@ llama-cpp-fallback: llama.cpp
 	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
 
+# Single-build CPU backend using ggml's CPU_ALL_VARIANTS. Produces ONE grpc-server
+# plus a set of dlopen-able libggml-cpu-*.so (sandybridge/haswell/skylakex/...) that
+# ggml's backend registry selects from at runtime by probing host CPU features.
+# Replaces the avx/avx2/avx512/fallback multi-binary build on x86.
+#
+# CPU_ALL_VARIANTS requires GGML_BACKEND_DL, which requires BUILD_SHARED_LIBS=ON, so we
+# pass SHARED_LIBS=ON and the DL flags as make variables (NOT pre-expanded into the
+# CMAKE_ARGS env string): command-line make variables propagate through every recursive
+# sub-make, so the deepest VARIANT-dir build computes BUILD_SHARED_LIBS=ON consistently.
+# Only ggml/llama go shared - gRPC is found via its static imported targets, so the
+# grpc-server binary keeps static gRPC and only dynamically links ggml.
+#
+# TARGET adds "ggml": the per-microarch backends are runtime-dlopened, not link deps of
+# grpc-server, so they only build because each is an add_dependencies() of the ggml target.
+llama-cpp-cpu-all: llama.cpp
+	cp -rf $(CURRENT_MAKEFILE_DIR)/../llama-cpp $(CURRENT_MAKEFILE_DIR)/../llama-cpp-cpu-all-build
+	$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../llama-cpp-cpu-all-build purge
+	$(info ${GREEN}I llama-cpp build info:cpu-all-variants${RESET})
+	$(MAKE) SHARED_LIBS=ON EXTRA_CMAKE_ARGS="-DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON" TARGET="--target grpc-server --target ggml" VARIANT="llama-cpp-cpu-all-build" build-llama-cpp-grpc-server
+	cp -rfv $(CURRENT_MAKEFILE_DIR)/../llama-cpp-cpu-all-build/grpc-server llama-cpp-cpu-all
+	rm -rf ggml-shared-libs && mkdir -p ggml-shared-libs
+	find $(CURRENT_MAKEFILE_DIR)/../llama-cpp-cpu-all-build/llama.cpp/build -name '*.so*' -exec cp -av {} ggml-shared-libs/ \;
+	@echo "Collected ggml shared backends:" && ls -la ggml-shared-libs/
+
 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

backend/cpp/llama-cpp/package.sh

@@ -14,6 +14,22 @@ mkdir -p $CURDIR/package/lib
 cp -avrf $CURDIR/llama-cpp-* $CURDIR/package/
 cp -rfv $CURDIR/run.sh $CURDIR/package/
 
+# Bundle the ggml shared backends produced by the CPU_ALL_VARIANTS build (libggml-base.so,
+# libggml.so, libllama.so and the per-microarch libggml-cpu-*.so), all into package/lib.
+#
+# Two distinct resolution mechanisms both land here:
+#   - NEEDED deps (libggml-base/libggml/libllama): resolved by the dynamic linker via the
+#     LD_LIBRARY_PATH=$CURDIR/lib that run.sh exports.
+#   - The per-microarch libggml-cpu-*.so are NOT linked; ggml *discovers* them at runtime by
+#     scanning the executable's own directory (readlink /proc/self/exe). run.sh launches via
+#     the bundled $CURDIR/lib/ld.so, so /proc/self/exe -> .../lib/ld.so and ggml scans lib/.
+#     That is why the variants must sit in lib/ (next to ld.so), not just on the link path.
+# No-op on builds (arm64/darwin) that don't produce the all-variants set.
+if [ -d "$CURDIR/ggml-shared-libs" ]; then
+    echo "Bundling ggml shared backends (CPU_ALL_VARIANTS)..."
+    cp -avf $CURDIR/ggml-shared-libs/*.so* $CURDIR/package/lib/
+fi
+
 # Detect architecture and copy appropriate libraries
 if [ -f "/lib64/ld-linux-x86-64.so.2" ]; then
     # x86_64 architecture

backend/cpp/llama-cpp/run.sh

@@ -12,26 +12,11 @@ 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
+# x86 ships a single llama-cpp-cpu-all built with ggml CPU_ALL_VARIANTS: ggml's backend
+# registry dlopens the best libggml-cpu-*.so for this host, so no shell-side AVX probing.
+# arm64/darwin builds ship only llama-cpp-fallback, so fall back to it when cpu-all absent.
+if [ -e $CURDIR/llama-cpp-cpu-all ]; then
+	BINARY=llama-cpp-cpu-all
 fi
 
 if [ -n "$LLAMACPP_GRPC_SERVERS" ]; then