fix(turboquant): retain CPU variants in GPU builds (#11276)

Select the CPU_ALL_VARIANTS target for x86 GPU images so partial offload uses runtime-selected host kernels. Keep GPU arm64 builds on the portable fallback until their toolchains consistently provide gcc-14.

Assisted-by: Codex:gpt-5

Co-authored-by: localai-org-maint-bot <306269227+localai-org-maint-bot@users.noreply.github.com>

Author: localai-org-maint-bot

.docker/turboquant-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 turboquant-fallback
+else
+  echo turboquant-cpu-all
+fi

.docker/turboquant-compile.sh

@@ -19,20 +19,18 @@ fi
 
 cd /LocalAI/backend/cpp/turboquant
 
-if [ -z "${BUILD_TYPE:-}" ]; then
-  # Pure CPU image: one ggml CPU_ALL_VARIANTS build replaces the per-microarch binaries.
+BUILD_TARGET=$(/LocalAI/.docker/turboquant-build-target.sh "${TARGETARCH}" "${BUILD_TYPE:-}")
+if [ "$BUILD_TARGET" = "turboquant-cpu-all" ]; then
+  # BUILD_TYPE remains in the environment, so GPU builds retain their accelerator while
+  # ggml selects the best CPU library when model work is offloaded to the host.
   # arm64: the armv9.2 SME variants need gcc-14 (gcc-13 rejects +sme).
   if [ "${TARGETARCH}" = "arm64" ]; then
+    sh /LocalAI/.docker/apt-mirror.sh || true
     apt-get update -qq && apt-get install -y -qq gcc-14 g++-14
     export CC=gcc-14 CXX=g++-14
   fi
-  make turboquant-cpu-all
-else
-  # GPU build (cublas/hipblas/sycl/vulkan/...): single fallback CPU build, the accelerator
-  # does the compute. Keeps the GPU compile from also building the CPU variant matrix and
-  # avoids the gcc-14 apt step on GPU base images such as nvidia l4t.
-  make turboquant-fallback
 fi
+make "$BUILD_TARGET"
 make turboquant-grpc
 make turboquant-rpc-server
 

backend/cpp/turboquant/run.sh

@@ -12,9 +12,11 @@ grep -e "flags" /proc/cpuinfo | head -1
 
 BINARY=turboquant-fallback
 
-# x86/arm64 ship a single turboquant-cpu-all built with ggml CPU_ALL_VARIANTS: ggml's
+# CPU images and x86 GPU images ship a single turboquant-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
-# probing. ROCm ships only turboquant-fallback, so fall back to it when cpu-all is absent.
+# probing. GPU arm64 images still ship turboquant-fallback until their builder toolchains
+# support ggml's complete arm variant matrix.
 if [ -e "$CURDIR"/turboquant-cpu-all ]; then
 	BINARY=turboquant-cpu-all
 fi

scripts/build/turboquant-build-target_test.sh

@@ -0,0 +1,26 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+CURDIR=$(dirname "$(realpath "$0")")
+SELECTOR="$CURDIR/../../.docker/turboquant-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 turboquant-cpu-all
+assert_target amd64 vulkan turboquant-cpu-all
+assert_target amd64 "" turboquant-cpu-all
+assert_target arm64 cublas turboquant-fallback
+assert_target arm64 "" turboquant-cpu-all
+
+echo "PASS: turboquant build target preserves CPU variants where supported"