diff --git a/lite/backends/xpu/device.cc b/lite/backends/xpu/device.cc
index dbf88ff83302c38cdc1b266f6e5c829c5a5c1da1..badde878ad870bfc5fcd1984e39923174a11e9e2 100644
--- a/lite/backends/xpu/device.cc
+++ b/lite/backends/xpu/device.cc
@@ -36,8 +36,11 @@ std::unique_ptr<xtcl::network::xRuntimeInstance> Device::Build(
   }
   xtcl::xNetwork network =
       builder->FinalizeNetwork(xtcl::relay::TupleNode::make(all_outs));
-  auto target = xtcl::Target::Create(device_name_);
-  auto compiler = xtcl::network::xTensorCompiler(network, target);
+  auto target = xtcl::NullValue<xtcl::Target>();
+  if (!target_.empty()) {
+    target = xtcl::Target::Create(target_);
+  }
+  xtcl::network::xTensorCompiler compiler(network, target);
   compiler.SetParams(*params);  // Set the data of constant tensors
   compiler.Build();
   VLOG(3) << "[XPU] Build done";
diff --git a/lite/backends/xpu/device.h b/lite/backends/xpu/device.h
index bf9a8bf76af168a8a73f8f497b793df88f48f96b..6de18d5466da6e6b791363d2e275ea72376c78b8 100644
--- a/lite/backends/xpu/device.h
+++ b/lite/backends/xpu/device.h
@@ -15,6 +15,7 @@
 #pragma once
 
 #include <xtcl/xtcl.h>
+#include <cstdlib>
 #include <memory>
 #include <string>
 #include <utility>
@@ -30,7 +31,18 @@ class Device {
     static Device x;
     return x;
   }
-  Device() {}
+  Device() {
+    char* name = std::getenv("XPU_DEVICE_NAME");
+    if (name) {
+      name_ = std::string(name);
+    }
+    // XPU_DEVICE_TARGET for XPU model building, which supports 'llvm' and 'xpu
+    // -libs=xdnn'
+    char* target = std::getenv("XPU_DEVICE_TARGET");
+    if (target) {
+      target_ = std::string(target);
+    }
+  }
 
   // Build the XPU graph to the XPU runtime, return the XPU runtime which can be
   // used to run inference.
@@ -39,10 +51,12 @@ class Device {
       xtcl::network::xTensorCompiler::ParamNDArrayMap* params,
       std::vector<xtcl::xExpr*>* outputs);
 
+  const std::string name() const { return name_; }
+  const std::string target() const { return target_; }
+
  private:
-  // Keep reserved fields
-  int device_id_{0};
-  std::string device_name_{"llvm"};
+  std::string name_{""};
+  std::string target_{""};
 };
 
 }  // namespace xpu
diff --git a/lite/kernels/xpu/bridges/utility.cc b/lite/kernels/xpu/bridges/utility.cc
index 79fad7c8b4e0ebcae89d42c92048ed5a3cc4b825..0295ae790fe3ba59c1feefa30ad37063b18fed83 100644
--- a/lite/kernels/xpu/bridges/utility.cc
+++ b/lite/kernels/xpu/bridges/utility.cc
@@ -103,7 +103,7 @@ DLDeviceType CvtDLDeviceType(TargetType in_type) {
       out_type = kDLGPU;
       break;
     case TARGET(kXPU):
-      out_type = kDLCPU;
+      out_type = static_cast<DLDeviceType>(kDLXPU);
       break;
     default:
       LOG(FATAL) << "[XPU] Can not convert target type(" << TargetToStr(in_type)
diff --git a/lite/kernels/xpu/subgraph_compute.cc b/lite/kernels/xpu/subgraph_compute.cc
index 298f6f0e507261e42dcdc1f1b06b47e09b81b21c..15df4f80ca20a86b3f40e46e51f1683b49e9b05f 100644
--- a/lite/kernels/xpu/subgraph_compute.cc
+++ b/lite/kernels/xpu/subgraph_compute.cc
@@ -175,7 +175,7 @@ int SubgraphEngine::LaunchDeviceProgram() {
     // Update the data pointer of DLTensor to track the origin input tensors
     device_itensors_[i].data =
         const_cast<void*>(origin_itensors_[i]->raw_data());
-    device_program_->SetInputZeroCopy(device_inames_[i], &device_itensors_[i]);
+    device_program_->SetInput(device_inames_[i], &device_itensors_[i]);
   }
   // Run the XPU model
   auto GetCurrentUS = []() -> double {
diff --git a/lite/tools/build_xpu.sh b/lite/tools/build_xpu.sh
index 9f28274471f0d0a06c755e41a4a92448a96873af..fdf287501e8f4411f51e73c55b789753f2e85674 100755
--- a/lite/tools/build_xpu.sh
+++ b/lite/tools/build_xpu.sh
@@ -104,6 +104,11 @@ function main {
                 build_xpu
                 shift
                 ;;
+            full_publish)
+                TARGET_NAME=publish_inference
+                build_xpu
+                shift
+                ;;
             *)
                 # unknown option
                 print_usage