feat: enable PyTorch custom ops by default (deepmodeling#5578)

## Summary
- change the `DP_ENABLE_PYTORCH` build-time default from `0` to `1` in
the build backend
- update the install-from-source docs to describe PyTorch customized C++
OPs as enabled by default
- adjust related model/compression docs so they no longer tell users to
set `DP_ENABLE_PYTORCH=1` explicitly

## Tests
- `python3 -m py_compile backend/find_pytorch.py backend/read_env.py
deepmd/pt/cxx_op.py`
- `git diff --check`
- `uv run --no-project --with dependency-groups --with packaging python`
smoke checks for default `-DENABLE_PYTORCH=ON` and explicit
`DP_ENABLE_PYTORCH=0` -> `-DENABLE_PYTORCH=OFF`

Authored by OpenClaw (model: custom-chat-jinzhezeng-group/gpt-5.5)


<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->

## Summary by CodeRabbit

* **New Features**
* PyTorch backend customized C++ OPs now enabled by default when
building from source.

* **Bug Fixes**
* Corrected error messages and installation guidance for PyTorch backend
issues.

* **Documentation**
* Updated installation and model documentation to reflect PyTorch
backend enabled by default.

<!-- end of auto-generated comment: release notes by coderabbit.ai -->

Author: njzjz-bot

backend/find_pytorch.py

@@ -49,9 +49,9 @@ def find_pytorch() -> tuple[str | None, list[str]]:
     str, optional
         PyTorch library path if found.
     list of str
-        TensorFlow requirement if not found. Empty if found.
+        PyTorch requirement if not found. Empty if found.
     """
-    if os.environ.get("DP_ENABLE_PYTORCH", "0") == "0":
+    if os.environ.get("DP_ENABLE_PYTORCH", "1") == "0":
         return None, []
     requires = []
     pt_spec = None

backend/read_env.py

@@ -104,7 +104,7 @@ def get_argument_from_env() -> tuple[str, list, list, dict, str, str]:
         cmake_args.append("-DENABLE_TENSORFLOW=OFF")
         tf_version = None
 
-    if os.environ.get("DP_ENABLE_PYTORCH", "0") == "1":
+    if os.environ.get("DP_ENABLE_PYTORCH", "1") == "1":
         pt_install_dir, _ = find_pytorch()
         pt_version = get_pt_version(pt_install_dir)
         cmake_args.extend(

deepmd/pt/cxx_op.py

@@ -83,8 +83,8 @@ def load_library(module_name: str) -> bool:
                     f"incompatible and thus an error is raised when loading {module_name}. "
                     f"You need to install PyTorch {PT_VERSION}, or rebuild deepmd-kit "
                     f"against PyTorch {pt_py_version}.\nIf you are using a wheel from "
-                    "PyPI, you may consider to install deepmd-kit execuating "
-                    "`DP_ENABLE_PYTORCH=1 pip install deepmd-kit --no-binary deepmd-kit` "
+                    "PyPI, you may consider rebuilding deepmd-kit with "
+                    "`pip install deepmd-kit --no-binary deepmd-kit` "
                     "instead."
                 ) from e
             error_message = (

doc/freeze/compress.md

@@ -125,6 +125,6 @@ See the documentation of a specific descriptor to see whether it supports model
 
 When compressing models in the PyTorch backend, the customized OP library for the Python interface must be installed when [freezing the model](../freeze/freeze.md).
 
-The customized OP library for the Python interface can be installed by setting environment variable {envvar}`DP_ENABLE_PYTORCH` to `1` during [installation](../install/install-from-source.md).
+The customized OP library for the Python interface is installed by default when building DeePMD-kit from source; see the [installation guide](../install/install-from-source.md) for details.
 
 [^1]: This section is built upon Jinzhe Zeng, Duo Zhang, Denghui Lu, Pinghui Mo, Zeyu Li, Yixiao Chen, Marián Rynik, Li'ang Huang, Ziyao Li, Shaochen Shi, Yingze Wang, Haotian Ye, Ping Tuo, Jiabin Yang, Ye Ding, Yifan Li, Davide Tisi, Qiyu Zeng, Han Bao, Yu Xia, Jiameng Huang, Koki Muraoka, Yibo Wang, Junhan Chang, Fengbo Yuan, Sigbjørn Løland Bore, Chun Cai, Yinnian Lin, Bo Wang, Jiayan Xu, Jia-Xin Zhu, Chenxing Luo, Yuzhi Zhang, Rhys E. A. Goodall, Wenshuo Liang, Anurag Kumar Singh, Sikai Yao, Jingchao Zhang, Renata Wentzcovitch, Jiequn Han, Jie Liu, Weile Jia, Darrin M. York, Weinan E, Roberto Car, Linfeng Zhang, Han Wang, [J. Chem. Phys. 159, 054801 (2023)](https://doi.org/10.1063/5.0155600) licensed under a [Creative Commons Attribution (CC BY) license](http://creativecommons.org/licenses/by/4.0/).

doc/install/install-from-source.md

@@ -151,7 +151,7 @@ Note that TensorFlow may have specific requirements for the compiler version to
 
 :::{tab-item} PyTorch {{ pytorch_icon }}
 
-You can set the environment variable `export DP_ENABLE_PYTORCH=1` to enable customized C++ OPs in the PyTorch backend.
+Customized C++ OPs in the PyTorch backend are enabled by default when building the Python interface.
 Note that PyTorch may have specific requirements for the compiler version to support the C++ standard version and [`_GLIBCXX_USE_CXX11_ABI`](https://gcc.gnu.org/onlinedocs/libstdc++/manual/using_dual_abi.html) used by PyTorch.
 :::
 
@@ -196,7 +196,7 @@ The path to the ROCM toolkit directory. If `ROCM_ROOT` is not set, it will look
 
 :::{envvar} DP_ENABLE_PYTORCH
 
-**Choices**: `0`, `1`; **Default**: `0`
+**Choices**: `0`, `1`; **Default**: `1`
 
 {{ pytorch_icon }} Enable customized C++ OPs for the PyTorch backend. PyTorch can still run without customized C++ OPs, but features will be limited.
 :::

doc/model/dpa2.md

@@ -58,7 +58,7 @@ DPA-2 is designed for multi-task pre-training with a shared descriptor and task-
 
 If one wants to run the DPA-2 model on LAMMPS, the customized OP library for the Python interface must be installed when [freezing the model](../freeze/freeze.md).
 
-The customized OP library for the Python interface can be installed by setting environment variable {envvar}`DP_ENABLE_PYTORCH` to `1` during installation.
+The customized OP library for the Python interface is installed by default when building DeePMD-kit from source.
 
 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,

doc/model/dpa3.md

@@ -130,7 +130,7 @@ To run the DPA3 model on LAMMPS via source code installation
 the custom OP library for Python interface integration must be compiled and linked
 during the [model freezing process](../freeze/freeze.md).
 
-The customized OP library for the Python interface can be installed by setting environment variable {envvar}`DP_ENABLE_PYTORCH` to `1` during installation.
+The customized OP library for the Python interface is installed by default when building DeePMD-kit from source.
 
 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,