fix(llama-cpp): retain CPU variants in GPU builds

.docker/llama-cpp-build-target.sh

@@ -0,0 +1,14 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+arch=${1:?target architecture is required}
+build_type=${2-}
+
+# GPU arm64 base images do not consistently provide the gcc-14 toolchain needed
+# to compile ggml's armv9.2 CPU variants. Keep their portable fallback until the
+# builder images can supply that compiler.
+if [ "$arch" = "arm64" ] && [ -n "$build_type" ]; then
+  echo llama-cpp-fallback
+else
+  echo llama-cpp-cpu-all
+fi

.docker/llama-cpp-compile.sh

@@ -18,10 +18,12 @@ if [[ -n "${CUDA_DOCKER_ARCH:-}" ]]; then
 fi
 
 cd /LocalAI/backend/cpp/llama-cpp
-if [ -z "${BUILD_TYPE:-}" ]; then
-  # Pure CPU image (BUILD_TYPE empty): one build with ggml CPU_ALL_VARIANTS replaces the
-  # per-microarch binaries (x86: avx/avx2/avx512/fallback; arm64: armv8.x/armv9.x). ggml
-  # dlopens the best libggml-cpu-*.so at runtime by probing host CPU features.
+BUILD_TARGET=$(/LocalAI/.docker/llama-cpp-build-target.sh "${TARGETARCH}" "${BUILD_TYPE:-}")
+if [ "$BUILD_TARGET" = "llama-cpp-cpu-all" ]; then
+  # One build with ggml CPU_ALL_VARIANTS replaces the per-microarch binaries (x86:
+  # avx/avx2/avx512/fallback; arm64: armv8.x/armv9.x). BUILD_TYPE remains in the
+  # environment, so GPU builds retain their accelerator backend while ggml dlopens the
+  # best CPU library when work is offloaded to the host.
   #
   # arm64: the CPU_ALL_VARIANTS table includes armv9.2 SME variants whose -march=...+sme is
   # rejected by the Ubuntu 24.04 default gcc-13. gcc-14 accepts it, so build the arm64
@@ -35,14 +37,8 @@ if [ -z "${BUILD_TYPE:-}" ]; then
     apt-get update -qq && apt-get install -y -qq gcc-14 g++-14
     export CC=gcc-14 CXX=g++-14
   fi
-  make llama-cpp-cpu-all
-else
-  # GPU build (cublas/hipblas/sycl/vulkan/...): the accelerator does the compute, so a
-  # single fallback CPU build is enough - no per-microarch CPU variants needed. (This also
-  # keeps the heavy GPU backend compile from also building the whole CPU variant matrix,
-  # and avoids the gcc-14 apt step on GPU base images such as nvidia l4t.)
-  make llama-cpp-fallback
 fi
+make "$BUILD_TARGET"
 make llama-cpp-grpc
 make llama-cpp-rpc-server
 

backend/cpp/llama-cpp/run.sh

@@ -12,10 +12,10 @@ grep -e "flags" /proc/cpuinfo | head -1
 
 BINARY=llama-cpp-fallback
 
-# CPU images (x86, arm64, darwin) ship a single llama-cpp-cpu-all built with ggml
+# CPU images and x86 GPU images ship 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. GPU images (cublas/sycl/vulkan/hipblas) ship only
-# llama-cpp-fallback (the accelerator does the compute), so fall back to it when absent.
+# host, so no shell-side AVX probing. GPU arm64 images still ship llama-cpp-fallback
+# until their builder toolchains support ggml's complete arm variant matrix.
 if [ -e "$CURDIR"/llama-cpp-cpu-all ]; then
 	BINARY=llama-cpp-cpu-all
 fi
@@ -55,4 +55,4 @@ echo "Using binary: $BINARY"
 exec "$CURDIR"/$BINARY "$@"
 
 # We should never reach this point, however just in case we do, run fallback
-exec "$CURDIR"/llama-cpp-fallback "$@"
+exec "$CURDIR"/llama-cpp-fallback "$@"

scripts/build/llama-cpp-build-target_test.sh

@@ -0,0 +1,26 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+CURDIR=$(dirname "$(realpath "$0")")
+SELECTOR="$CURDIR/../../.docker/llama-cpp-build-target.sh"
+
+assert_target() {
+  local arch=$1
+  local build_type=$2
+  local expected=$3
+  local actual
+
+  actual=$("$SELECTOR" "$arch" "$build_type")
+  if [ "$actual" != "$expected" ]; then
+    echo "FAIL: $arch/$build_type selected $actual, expected $expected"
+    exit 1
+  fi
+}
+
+assert_target amd64 cublas llama-cpp-cpu-all
+assert_target amd64 vulkan llama-cpp-cpu-all
+assert_target amd64 "" llama-cpp-cpu-all
+assert_target arm64 cublas llama-cpp-fallback
+assert_target arm64 "" llama-cpp-cpu-all
+
+echo "PASS: llama.cpp build target preserves CPU variants where supported"