diff --git a/fastdeploy/backends/paddle/paddle_backend.cc b/fastdeploy/backends/paddle/paddle_backend.cc
index 70d8305c5..c1ecacee2 100644
--- a/fastdeploy/backends/paddle/paddle_backend.cc
+++ b/fastdeploy/backends/paddle/paddle_backend.cc
@@ -36,7 +36,7 @@ void PaddleBackend::BuildOption(const PaddleBackendOption& option) {
         FDWARNING << "Detect that tensorrt cache file has been set to " << option.trt_option.serialize_file << ", but while enable paddle2trt, please notice that the cache file will save to the directory where paddle model saved." << std::endl;
         use_static = true;
       }
-      config_.EnableTensorRtEngine(option.trt_option.max_workspace_size, 32, 3, precision, use_static);
+      config_.EnableTensorRtEngine(option.trt_option.max_workspace_size, option.trt_option.max_batch_size, 3, precision, use_static);
       SetTRTDynamicShapeToConfig(option);
 #else
       FDWARNING << "The FastDeploy is not compiled with TensorRT backend, so will fallback to GPU with Paddle Inference Backend." << std::endl;
@@ -112,8 +112,9 @@ bool PaddleBackend::InitFromPaddle(const std::string& model_file,
           FDWARNING << "Detect that tensorrt cache file has been set to " << option.trt_option.serialize_file << ", but while enable paddle2trt, please notice that the cache file will save to the directory where paddle model saved." << std::endl;
           use_static = true;
         }
-        config_.EnableTensorRtEngine(option.trt_option.max_workspace_size, 32, 3, paddle_infer::PrecisionType::kInt8, use_static, false);
+        config_.EnableTensorRtEngine(option.trt_option.max_workspace_size, option.trt_option.max_batch_size, 3, paddle_infer::PrecisionType::kInt8, use_static, false);
         SetTRTDynamicShapeToConfig(option);
+        
 #endif
       }
     }
diff --git a/fastdeploy/pybind/runtime.cc b/fastdeploy/pybind/runtime.cc
index 11cf9bf4e..759c55530 100644
--- a/fastdeploy/pybind/runtime.cc
+++ b/fastdeploy/pybind/runtime.cc
@@ -42,6 +42,7 @@ void BindRuntime(pybind11::module& m) {
       .def("set_lite_power_mode", &RuntimeOption::SetLitePowerMode)
       .def("set_trt_input_shape", &RuntimeOption::SetTrtInputShape)
       .def("set_trt_max_workspace_size", &RuntimeOption::SetTrtMaxWorkspaceSize)
+      .def("set_trt_max_batch_size", &RuntimeOption::SetTrtMaxBatchSize)
       .def("enable_paddle_to_trt", &RuntimeOption::EnablePaddleToTrt)
       .def("enable_trt_fp16", &RuntimeOption::EnableTrtFP16)
       .def("disable_trt_fp16", &RuntimeOption::DisableTrtFP16)
diff --git a/fastdeploy/runtime.cc b/fastdeploy/runtime.cc
index 94ea9de0b..4dd1bac59 100755
--- a/fastdeploy/runtime.cc
+++ b/fastdeploy/runtime.cc
@@ -371,6 +371,9 @@ void RuntimeOption::SetTrtInputShape(const std::string& input_name,
 void RuntimeOption::SetTrtMaxWorkspaceSize(size_t max_workspace_size) {
   trt_max_workspace_size = max_workspace_size;
 }
+void RuntimeOption::SetTrtMaxBatchSize(size_t max_batch_size){
+  trt_max_batch_size = max_batch_size; 
+}
 
 void RuntimeOption::EnableTrtFP16() { trt_enable_fp16 = true; }
 
diff --git a/fastdeploy/runtime.h b/fastdeploy/runtime.h
index 7ab6f1fb2..8330f412e 100644
--- a/fastdeploy/runtime.h
+++ b/fastdeploy/runtime.h
@@ -200,6 +200,9 @@ struct FASTDEPLOY_DECL RuntimeOption {
   /// Set max_workspace_size for TensorRT, default 1<<30
   void SetTrtMaxWorkspaceSize(size_t trt_max_workspace_size);
 
+  /// Set max_batch_size for TensorRT, default 32
+  void SetTrtMaxBatchSize(size_t max_batch_size);
+
   /**
    * @brief Enable FP16 inference while using TensorRT backend. Notice: not all the GPU device support FP16, on those device doesn't support FP16, FastDeploy will fallback to FP32 automaticly
    */
@@ -339,7 +342,7 @@ struct FASTDEPLOY_DECL RuntimeOption {
   std::string model_file = "";  // Path of model file
   std::string params_file = "";  // Path of parameters file, can be empty
   // format of input model
-  ModelFormat model_format = ModelFormat::AUTOREC; 
+  ModelFormat model_format = ModelFormat::AUTOREC;
 };
 
 /*! @brief Runtime object used to inference the loaded model on different devices
diff --git a/python/fastdeploy/runtime.py b/python/fastdeploy/runtime.py
index e8a6058a4..4d0311d4b 100755
--- a/python/fastdeploy/runtime.py
+++ b/python/fastdeploy/runtime.py
@@ -18,6 +18,7 @@ from . import ModelFormat
 from . import c_lib_wrap as C
 from . import rknpu2
 
+
 class Runtime:
     """FastDeploy Runtime object.
     """
@@ -207,10 +208,12 @@ class RuntimeOption:
         """
         return self._option.use_cpu()
 
-    def use_rknpu2(self,rknpu2_name=rknpu2.CpuName.RK3588,rknpu2_core=rknpu2.CoreMask.RKNN_NPU_CORE_0):
+    def use_rknpu2(self,
+                   rknpu2_name=rknpu2.CpuName.RK3588,
+                   rknpu2_core=rknpu2.CoreMask.RKNN_NPU_CORE_0):
         """Inference with CPU
         """
-        return self._option.use_rknpu2(rknpu2_name,rknpu2_core)
+        return self._option.use_rknpu2(rknpu2_name, rknpu2_core)
 
     def set_cpu_thread_num(self, thread_num=-1):
         """Set number of threads if inference with CPU
@@ -344,6 +347,11 @@ class RuntimeOption:
         """
         return self._option.set_trt_max_workspace_size(trt_max_workspace_size)
 
+    def set_trt_max_batch_size(self, trt_max_batch_size):
+        """Set max batch size while using TensorRT backend.
+        """
+        return self._option.set_trt_max_batch_size(trt_max_batch_size)
+
     def enable_paddle_trt_collect_shape(self):
         return self._option.enable_paddle_trt_collect_shape()