diff --git a/paddle/fluid/operators/beam_search_decode_op_xpu.cc b/paddle/fluid/operators/beam_search_decode_op_xpu.cc
index aa7e6ca0476072ed75f0c4a760cb38505c15cdbd..b78cec34cb90011172839974f6b2a6ddfd3d5089 100644
--- a/paddle/fluid/operators/beam_search_decode_op_xpu.cc
+++ b/paddle/fluid/operators/beam_search_decode_op_xpu.cc
@@ -101,6 +101,8 @@ class BeamSearchDecodeXPUKernel : public framework::OpKernel<T> {
           xpu::Error_t::SUCCESS,
           platform::errors::External(
               "Execute function CopyTensorByXPU failed by [%d]", r));
+      sentenceIds_temp->set_lod(sentenceIds->lod());
+      sentenceScores_temp->set_lod(sentenceScores->lod());
     }
   }
 };
diff --git a/paddle/phi/kernels/fusion/xpu/embedding_with_eltwise_add_xpu_kernel.cc b/paddle/phi/kernels/fusion/xpu/embedding_with_eltwise_add_xpu_kernel.cc
index afde2f8f3503b24d80e87a1220fc3fd12582ce19..e373ddb60ae0796bd18b6c107bb11262938465f4 100644
--- a/paddle/phi/kernels/fusion/xpu/embedding_with_eltwise_add_xpu_kernel.cc
+++ b/paddle/phi/kernels/fusion/xpu/embedding_with_eltwise_add_xpu_kernel.cc
@@ -53,8 +53,19 @@ void EmbeddingWithEltwiseAddXpuKernel(
                                         std::vector<int>(idx_len, 0));
   std::vector<xpu::VectorParam<int>> arg_ids;
   for (int i = 0; i < emb_layer_num; i++) {
+    PADDLE_ENFORCE_EQ(
+        ids[i]->dtype() == phi::DataType::INT64 ||
+            ids[i]->dtype() == phi::DataType::INT32,
+        true,
+        errors::InvalidArgument(
+            "The data type of ids should be int64 or int32, but got %s.",
+            ids[i]->dtype()));
     for (int j = 0; j < idx_len; j++) {
-      int_idx[i][j] = static_cast<int>(ids[i]->data<int64_t>()[j]);
+      if (ids[i]->dtype() == phi::DataType::INT64) {
+        int_idx[i][j] = static_cast<int>(ids[i]->data<int64_t>()[j]);
+      } else if (ids[i]->dtype() == phi::DataType::INT32) {
+        int_idx[i][j] = ids[i]->data<int>()[j];
+      }
     }
     arg_ids.push_back(
         xpu::VectorParam<int>{int_idx[i].data(), idx_len, nullptr});
diff --git a/paddle/phi/kernels/xpu/split_kernel.cc b/paddle/phi/kernels/xpu/split_kernel.cc
index 674182620bccc5952d4ec32989d959b5c24f4173..6a9bf54876c6a3b9ac22469b9d829ae32dc89831 100644
--- a/paddle/phi/kernels/xpu/split_kernel.cc
+++ b/paddle/phi/kernels/xpu/split_kernel.cc
@@ -36,6 +36,9 @@ void SplitKernel(const Context& dev_ctx,
     out_ptrs.push_back(reinterpret_cast<XPUType*>(outs[j]->data<T>()));
     split_lists.push_back(outs[j]->dims()[axis]);
   }
+  if (x.numel() == 0) {
+    return;
+  }
   int r = xpu::split<XPUType>(dev_ctx.x_context(),
                               reinterpret_cast<const XPUType*>(x.data<T>()),
                               out_ptrs,