diff --git a/deepmd/pd/model/descriptor/repflows.py b/deepmd/pd/model/descriptor/repflows.py
index 4ea72daf02..756562e333 100644
--- a/deepmd/pd/model/descriptor/repflows.py
+++ b/deepmd/pd/model/descriptor/repflows.py
@@ -69,8 +69,9 @@ def border_op(
         argument8,
     ) -> paddle.Tensor:
         raise NotImplementedError(
-            "border_op is not available since customized Paddle OP library is not built when freezing the model. "
-            "See documentation for DPA3 for details."
+            "The 'border_op' operator is unavailable because the custom Paddle OP library was not built when freezing the model.\n"
+            "To install 'border_op', run: python source/op/pd/setup.py install\n"
+            "For more information, please refer to the DPA3 documentation."
         )
 
     # Note: this hack cannot actually save a model that can be run using LAMMPS.
diff --git a/deepmd/pd/model/descriptor/repformers.py b/deepmd/pd/model/descriptor/repformers.py
index 09e9b51c83..4151833f35 100644
--- a/deepmd/pd/model/descriptor/repformers.py
+++ b/deepmd/pd/model/descriptor/repformers.py
@@ -66,8 +66,9 @@ def border_op(
         argument8,
     ) -> paddle.Tensor:
         raise NotImplementedError(
-            "border_op is not available since customized Paddle OP library is not built when freezing the model. "
-            "See documentation for DPA3 for details."
+            "The 'border_op' operator is unavailable because the custom Paddle OP library was not built when freezing the model.\n"
+            "To install 'border_op', run: python source/op/pd/setup.py install\n"
+            "For more information, please refer to the DPA3 documentation."
         )
 
     # Note: this hack cannot actually save a model that can be run using LAMMPS.
diff --git a/doc/install/easy-install.md b/doc/install/easy-install.md
index bbf8d9b1d9..9f4d6d8861 100644
--- a/doc/install/easy-install.md
+++ b/doc/install/easy-install.md
@@ -185,7 +185,10 @@ Switch to the TensorFlow {{ tensorflow_icon }} tab for more information.
 ::::{tab-item} CUDA 12.6
 
 ```bash
-pip install paddlepaddle-gpu==3.0.0 -i https://www.paddlepaddle.org.cn/packages/stable/cu126/
+# release version
+pip install paddlepaddle-gpu==3.1.1 -i https://www.paddlepaddle.org.cn/packages/stable/cu126/
+# nightly-build version
+# pip install --pre paddlepaddle-gpu -i https://www.paddlepaddle.org.cn/packages/nightly/cu126/
 pip install deepmd-kit
 ```
 
@@ -194,7 +197,10 @@ pip install deepmd-kit
 ::::{tab-item} CUDA 11.8
 
 ```bash
-pip install paddlepaddle-gpu==3.0.0 -i https://www.paddlepaddle.org.cn/packages/stable/cu118/
+# release version
+pip install paddlepaddle-gpu==3.1.1 -i https://www.paddlepaddle.org.cn/packages/stable/cu118/
+# nightly-build version
+# pip install --pre paddlepaddle-gpu -i https://www.paddlepaddle.org.cn/packages/nightly/cu118/
 pip install deepmd-kit
 ```
 
@@ -203,7 +209,10 @@ pip install deepmd-kit
 ::::{tab-item} CPU
 
 ```bash
-pip install paddlepaddle==3.0.0 -i https://www.paddlepaddle.org.cn/packages/stable/cpu/
+# release version
+pip install paddlepaddle==3.1.1 -i https://www.paddlepaddle.org.cn/packages/stable/cpu/
+# nightly-build version
+# pip install --pre paddlepaddle -i https://www.paddlepaddle.org.cn/packages/nightly/cpu/
 pip install deepmd-kit
 ```
 
diff --git a/doc/install/install-from-source.md b/doc/install/install-from-source.md
index 1dc72c51fa..a21b8913db 100644
--- a/doc/install/install-from-source.md
+++ b/doc/install/install-from-source.md
@@ -99,11 +99,22 @@ To install Paddle, run
 
 ```sh
 # cu126
-pip install paddlepaddle-gpu==3.0.0 -i https://www.paddlepaddle.org.cn/packages/stable/cu126/
+# release version
+pip install paddlepaddle-gpu==3.1.1 -i https://www.paddlepaddle.org.cn/packages/stable/cu126/
+# nightly-build version
+# pip install --pre paddlepaddle-gpu -i https://www.paddlepaddle.org.cn/packages/nightly/cu126/
+
 # cu118
-pip install paddlepaddle-gpu==3.0.0 -i https://www.paddlepaddle.org.cn/packages/stable/cu118/
+# release version
+pip install paddlepaddle-gpu==3.1.1 -i https://www.paddlepaddle.org.cn/packages/stable/cu118/
+# nightly-build version
+# pip install --pre paddlepaddle-gpu -i https://www.paddlepaddle.org.cn/packages/nightly/cu118/
+
 # cpu
-pip install paddlepaddle==3.0.0 -i https://www.paddlepaddle.org.cn/packages/stable/cpu/
+# release version
+pip install paddlepaddle==3.1.1 -i https://www.paddlepaddle.org.cn/packages/stable/cpu/
+# nightly-build version
+# pip install --pre paddlepaddle -i https://www.paddlepaddle.org.cn/packages/nightly/cpu/
 ```
 
 :::
diff --git a/doc/model/dpa3.md b/doc/model/dpa3.md
index c63b26f90a..0ff46c438f 100644
--- a/doc/model/dpa3.md
+++ b/doc/model/dpa3.md
@@ -1,4 +1,4 @@
-# Descriptor DPA3 {{ pytorch_icon }} {{ jax_icon }} {{ dpmodel_icon }}
+# Descriptor DPA3 {{ pytorch_icon }} {{ jax_icon }} {{ paddle_icon }} {{ dpmodel_icon }}
 
 :::{note}
 **Supported backends**: PyTorch {{ pytorch_icon }}, JAX {{ jax_icon }}, DP {{ dpmodel_icon }}
@@ -40,7 +40,11 @@ Virial RMSEs were averaged exclusively for systems containing virial labels (`Al
 
 Note that we set `float32` in all DPA3 models, while `float64` in other models by default.
 
-## Requirements of installation from source code {{ pytorch_icon }}
+## Requirements of installation from source code {{ pytorch_icon }} {{ paddle_icon }}
+
+::::{tab-set}
+
+:::{tab-item} PyTorch {{ pytorch_icon }}
 
 To run the DPA3 model on LAMMPS via source code installation
 (users can skip this step if using [easy installation](../install/easy-install.md)),
@@ -53,6 +57,25 @@ If one runs LAMMPS with MPI, the customized OP library for the C++ interface sho
 If one runs LAMMPS with MPI and CUDA devices, it is recommended to compile the customized OP library for the C++ interface with a [CUDA-Aware MPI](https://developer.nvidia.com/mpi-solutions-gpus) library and CUDA,
 otherwise the communication between GPU cards falls back to the slower CPU implementation.
 
+:::
+
+:::{tab-item} Paddle {{ paddle_icon }}
+
+The customized OP library for the Python interface can be installed by
+
+```sh
+cd deepmd-kit/source/op/pd
+python setup.py install
+```
+
+If one runs LAMMPS with MPI, the customized OP library for the C++ interface should be compiled against the same MPI library as the runtime MPI.
+If one runs LAMMPS with MPI and CUDA devices, it is recommended to compile the customized OP library for the C++ interface with a [CUDA-Aware MPI](https://developer.nvidia.com/mpi-solutions-gpus) library and CUDA,
+otherwise the communication between GPU cards falls back to the slower CPU implementation.
+
+:::
+
+::::
+
 ## Limitations of the JAX backend with LAMMPS {{ jax_icon }}
 
 When using the JAX backend, 2 or more MPI ranks are not supported. One must set `map` to `yes` using the [`atom_modify`](https://docs.lammps.org/atom_modify.html) command.
diff --git a/doc/train/training.md b/doc/train/training.md
index ca0b46c0ef..6ccb43bbd7 100644
--- a/doc/train/training.md
+++ b/doc/train/training.md
@@ -29,10 +29,10 @@ $ dp --pt train input.json
 :::{tab-item} Paddle {{ paddle_icon }}
 
 ```bash
-# training model in eager mode
+# training model
 $ dp --pd train input.json
 
-# [experimental] training model with CINN compiler for better performance,
+# [experimental] training models with the CINN compiler (~40%+ speedup)
 # see: https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/guides/paddle_v3_features/cinn_cn.html
 ## If the shape(s) of batch input data are dynamic during training(default).
 $ CINN=1 dp --pd train input.json