diff --git a/paddle/fluid/operators/fake_quantize_op.cu b/paddle/fluid/operators/fake_quantize_op.cu
index 7c65d6dba7d67b5d31720bae1f4877dd22210138..a0ff6396210c2b3a7f8bd6b9f274b875d7fd4933 100644
--- a/paddle/fluid/operators/fake_quantize_op.cu
+++ b/paddle/fluid/operators/fake_quantize_op.cu
@@ -119,7 +119,8 @@ struct FindRangeAbsMaxFunctor<platform::CUDADeviceContext, T> {
                   const framework::Tensor& last_scale,
                   const framework::Tensor& iter, const int window_size,
                   framework::Tensor* scales_arr, framework::Tensor* out_scale) {
-    auto& gpu_place = boost::get<platform::CUDAPlace>(ctx.GetPlace());
+    const auto gpu_place = boost::get<platform::CUDAPlace>(ctx.GetPlace());
+
     T* scale_arr = scales_arr->mutable_data<T>(gpu_place);
     T* out_scale_data = out_scale->mutable_data<T>(gpu_place);
 
diff --git a/paddle/scripts/paddle_build.sh b/paddle/scripts/paddle_build.sh
index 7199424b4709fbe9fc962cf98aea6223b9f3e51d..84f9d6671a80889c4ff92832f546d51ef4352007 100755
--- a/paddle/scripts/paddle_build.sh
+++ b/paddle/scripts/paddle_build.sh
@@ -115,6 +115,7 @@ function cmake_gen() {
         -DWITH_FLUID_ONLY=${WITH_FLUID_ONLY:-OFF}
         -DCMAKE_EXPORT_COMPILE_COMMANDS=ON
         -DWITH_CONTRIB=${WITH_CONTRIB:-ON}
+        -DWITH_INFERENCE=${WITH_INFERENCE:-ON}
         -DWITH_ANAKIN=${WITH_ANAKIN:-OFF}
         -DPY_VERSION=${PY_VERSION:-2.7}
     ========================================
@@ -144,6 +145,7 @@ EOF
         -DWITH_FLUID_ONLY=${WITH_FLUID_ONLY:-OFF} \
         -DCMAKE_EXPORT_COMPILE_COMMANDS=ON \
         -DWITH_CONTRIB=${WITH_CONTRIB:-ON} \
+        -DWITH_INFERENCE=${WITH_INFERENCE:-ON} \
         -DWITH_ANAKIN=${WITH_ANAKIN:-OFF} \
         -DPY_VERSION=${PY_VERSION:-2.7}
 }