fix(llama-cpp): retain CPU variants in GPU builds (#11255)

Build the runtime CPU variant set alongside x86 GPU backends so partial offload uses the host's SIMD kernels instead of the scalar fallback. Keep arm64 GPU images on the portable binary until their builders 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>

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"