merge devel to master (v3.1.2) (#5088)

Author: njzjz

.devcontainer/build_cxx.sh

@@ -13,7 +13,7 @@ cmake -D ENABLE_TENSORFLOW=ON \
 	-D ENABLE_PYTORCH=ON \
 	-D ENABLE_PADDLE=ON \
 	-D CMAKE_INSTALL_PREFIX=${SCRIPT_PATH}/../dp/ \
-	-D LAMMPS_VERSION=stable_22Jul2025_update1 \
+	-D LAMMPS_VERSION=stable_22Jul2025_update2 \
 	-D CMAKE_BUILD_TYPE=Debug \
 	-D BUILD_TESTING:BOOL=TRUE \
 	-D TENSORFLOW_ROOT=${TENSORFLOW_ROOT} \

.github/dependabot.yml

@@ -5,3 +5,8 @@ updates:
     schedule:
       interval: "weekly"
     target-branch: "devel"
+  - package-ecosystem: "pip"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+    target-branch: "devel"

.github/workflows/build_cc.yml

@@ -29,14 +29,13 @@ jobs:
         - variant: clang
           dp_variant: clang
     steps:
-    - uses: actions/checkout@v5
+    - uses: actions/checkout@v6
     - uses: actions/setup-python@v6
       with:
         python-version: '3.11'
     - uses: lukka/get-cmake@latest
     - run: python -m pip install uv
-    - run: source/install/uv_with_retry.sh pip install --system tensorflow
-    - run: source/install/uv_with_retry.sh pip install --system 'torch==2.8.*' --index-url https://download.pytorch.org/whl/cpu
+    - run: source/install/uv_with_retry.sh pip install --system --group pin_tensorflow_cpu --group pin_pytorch_cpu --torch-backend cpu
     - run: |
          wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/cuda-keyring_1.0-1_all.deb \
          && sudo dpkg -i cuda-keyring_1.0-1_all.deb \

.github/workflows/build_wheel.yml

@@ -37,7 +37,7 @@ jobs:
             cuda_version: 11.8
             dp_pkg_name: deepmd-kit-cu11
           # macos-x86-64
-          - os: macos-13
+          - os: macos-15-intel
             python: 311
             platform_id: macosx_x86_64
             dp_variant: cpu
@@ -57,7 +57,7 @@ jobs:
             platform_id: manylinux_aarch64
             dp_variant: cpu
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
         with:
           # https://github.com/pypa/setuptools_scm/issues/480
           fetch-depth: 0
@@ -73,7 +73,7 @@ jobs:
           rm -rf .git
         if: matrix.dp_pkg_name == 'deepmd-kit-cu11'
       - name: Build wheels
-        uses: pypa/cibuildwheel@v3.1
+        uses: pypa/cibuildwheel@v3.3
         env:
           CIBW_BUILD_VERBOSITY: 1
           CIBW_ARCHS: all
@@ -82,21 +82,21 @@ jobs:
           CUDA_VERSION: ${{ matrix.cuda_version }}
           DP_PKG_NAME: ${{ matrix.dp_pkg_name }}
           CIBW_BUILD_FRONTEND: 'build[uv]'
-      - uses: actions/upload-artifact@v4
+      - uses: actions/upload-artifact@v5
         with:
           name: cibw-cp${{ matrix.python }}-${{ matrix.platform_id }}-cu${{ matrix.cuda_version }}-${{ strategy.job-index }}
           path: ./wheelhouse/*.whl
   build_sdist:
     name: Build source distribution
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
         with:
           fetch-depth: 0
       - name: Build sdist
         run: pipx run uv tool run --with build[uv] --from build python -m build --installer uv --sdist
 
-      - uses: actions/upload-artifact@v4
+      - uses: actions/upload-artifact@v5
         with:
           name: cibw-sdist
           path: dist/*.tar.gz
@@ -109,7 +109,7 @@ jobs:
       id-token: write
     if: github.event_name == 'push' && startsWith(github.event.ref, 'refs/tags/v')
     steps:
-      - uses: actions/download-artifact@v5
+      - uses: actions/download-artifact@v6
         with:
           pattern: cibw-*
           path: dist
@@ -131,8 +131,8 @@ jobs:
     steps:
       - name: Delete huge unnecessary tools folder
         run: rm -rf /opt/hostedtoolcache
-      - uses: actions/checkout@v5
-      - uses: actions/download-artifact@v5
+      - uses: actions/checkout@v6
+      - uses: actions/download-artifact@v6
         with:
           path: source/install/docker/dist
           pattern: cibw-*-manylinux_x86_64-cu${{ matrix.cuda_version }}*
@@ -165,7 +165,7 @@ jobs:
     needs: [build_wheels, build_sdist]
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/download-artifact@v5
+      - uses: actions/download-artifact@v6
         with:
           path: dist/packages
           pattern: cibw-*

.github/workflows/codeql.yml

@@ -30,7 +30,7 @@ jobs:
 
     steps:
     - name: Checkout repository
-      uses: actions/checkout@v5
+      uses: actions/checkout@v6
     - uses: actions/setup-python@v6
       with:
         python-version: '3.11'
@@ -43,13 +43,13 @@ jobs:
          && sudo dpkg -i cuda-keyring_1.0-1_all.deb \
          && sudo apt-get update \
          && sudo apt-get -y install cuda-cudart-dev-12-2 cuda-nvcc-12-2
-        python -m pip install tensorflow
-        python -m pip install 'torch==2.8.*' --index-url https://download.pytorch.org/whl/cpu
+        python -m pip install uv
+        uv pip install --system --group pin_tensorflow_cpu --group pin_pytorch_cpu --torch-backend cpu
       env:
         DEBIAN_FRONTEND: noninteractive
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@v3
+      uses: github/codeql-action/init@v4
       with:
         languages: ${{ matrix.language }}
         queries: security-extended,security-and-quality
@@ -62,6 +62,6 @@ jobs:
       if: matrix.language == 'c-cpp'
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@v3
+      uses: github/codeql-action/analyze@v4
       with:
         category: "/language:${{matrix.language}}"

.github/workflows/copilot-setup-steps.yml

@@ -30,15 +30,15 @@ jobs:
     # If you do not check out your code, Copilot will do this for you.
     steps:
       - name: Checkout code
-        uses: actions/checkout@v5
+        uses: actions/checkout@v6
 
       - name: Set up Python
         uses: actions/setup-python@v6
         with:
           python-version: "3.10"
 
       - name: Install uv
-        uses: astral-sh/setup-uv@v6
+        uses: astral-sh/setup-uv@v7
         with:
           enable-cache: true
 
@@ -49,10 +49,7 @@ jobs:
         run: echo "VIRTUAL_ENV=$PWD/venv" >> $GITHUB_ENV && echo "$PWD/venv/bin" >> $GITHUB_PATH
 
       - name: Install base dependencies
-        run: uv pip install tensorflow-cpu
-
-      - name: Install PyTorch
-        run: uv pip install torch --index-url https://download.pytorch.org/whl/cpu
+        run: uv pip install --group pin_tensorflow_cpu --group pin_pytorch_cpu --torch-backend cpu
 
       - name: Build Python package
         run: uv pip install -e .[cpu,test]

.github/workflows/package_c.yml

@@ -28,7 +28,17 @@ jobs:
             tensorflow_version: ">=2.5.0,<2.15"
             filename: libdeepmd_c_cu11.tar.gz
     steps:
-      - uses: actions/checkout@v5
+      - name: Free Disk Space (Ubuntu)
+        uses: insightsengineering/disk-space-reclaimer@v1
+        with:
+          tools-cache: true
+          android: true
+          dotnet: true
+          haskell: true
+          large-packages: true
+          swap-storage: true
+          docker-images: true
+      - uses: actions/checkout@v6
         with:
           fetch-depth: 0
       - name: Package C library
@@ -40,7 +50,7 @@ jobs:
         if: matrix.filename != 'libdeepmd_c.tar.gz'
       # for download and debug
       - name: Upload artifact
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v5
         with:
           name: libdeepmd_c-${{ strategy.job-index }}-${{ matrix.filename }}
           path: ${{ matrix.filename }}
@@ -56,9 +66,9 @@ jobs:
     needs: [build_c]
     runs-on: ubuntu-22.04
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
       - name: Download artifact
-        uses: actions/download-artifact@v5
+        uses: actions/download-artifact@v6
         with:
           pattern: libdeepmd_c-*
           merge-multiple: true

.github/workflows/suppr.txt

@@ -1 +1,5 @@
 leak:libpaddle_inference
+# TensorFlow 2.20
+leak:xla::
+leak:mlir::
+leak:llvm::

.github/workflows/test_cc.yml

@@ -17,9 +17,25 @@ jobs:
     runs-on: ubuntu-22.04
     strategy:
       matrix:
-        check_memleak: [true, false]
+        include:
+          - check_memleak: true
+            enable_tensorflow: true
+            enable_pytorch: true
+            enable_paddle: false
+          - check_memleak: true
+            enable_tensorflow: false
+            enable_pytorch: false
+            enable_paddle: true
+          - check_memleak: false
+            enable_tensorflow: true
+            enable_pytorch: true
+            enable_paddle: false
+          - check_memleak: false
+            enable_tensorflow: false
+            enable_pytorch: false
+            enable_paddle: true
     steps:
-    - uses: actions/checkout@v5
+    - uses: actions/checkout@v6
     - uses: actions/setup-python@v6
       with:
         python-version: '3.11'
@@ -28,10 +44,9 @@ jobs:
     - run: python -m pip install uv
     - name: Install Python dependencies
       run: |
-        source/install/uv_with_retry.sh pip install --system tensorflow-cpu~=2.18.0 jax==0.5.0
+        source/install/uv_with_retry.sh pip install --system --group pin_tensorflow_cpu --group pin_pytorch_cpu --group pin_jax --torch-backend cpu
         export TENSORFLOW_ROOT=$(python -c 'import importlib.util,pathlib;print(pathlib.Path(importlib.util.find_spec("tensorflow").origin).parent)')
         source/install/uv_with_retry.sh pip install --system -e .[cpu,test,lmp,jax] mpi4py mpich
-        source/install/uv_with_retry.sh pip install --system 'torch==2.8.*' --index-url https://download.pytorch.org/whl/cpu
     - name: Convert models
       run: source/tests/infer/convert-models.sh
     # https://github.com/actions/runner-images/issues/9491
@@ -47,31 +62,41 @@ jobs:
         CMAKE_GENERATOR: Ninja
         CXXFLAGS: ${{ matrix.check_memleak && '-fsanitize=leak' || '' }}
         LSAN_OPTIONS: suppressions=${{ github.workspace }}/.github/workflows/suppr.txt
+        ENABLE_TENSORFLOW: ${{ matrix.enable_tensorflow && 'TRUE' || 'FALSE' }}
+        ENABLE_PYTORCH: ${{ matrix.enable_pytorch && 'TRUE' || 'FALSE' }}
+        ENABLE_PADDLE: ${{ matrix.enable_paddle && 'TRUE' || 'FALSE' }}
     # test lammps
     - run: |
         cp ${{ github.workspace }}/source/build_tests/paddle_inference_install_dir/paddle/lib/*.so ${{ github.workspace }}/dp_test/lib/
         cp ${{ github.workspace }}/source/build_tests/paddle_inference_install_dir/third_party/install/onednn/lib/* ${{ github.workspace }}/dp_test/lib/
         cp ${{ github.workspace }}/source/build_tests/paddle_inference_install_dir/third_party/install/mklml/lib/* ${{ github.workspace }}/dp_test/lib/
+      if: matrix.enable_paddle
+    - run: |
         export LD_LIBRARY_PATH=${{ github.workspace }}/dp_test/lib:$LD_LIBRARY_PATH
         pytest --cov=deepmd source/lmp/tests
       env:
         OMP_NUM_THREADS: 1
         TF_INTRA_OP_PARALLELISM_THREADS: 1
         TF_INTER_OP_PARALLELISM_THREADS: 1
         LAMMPS_PLUGIN_PATH: ${{ github.workspace }}/dp_test/lib/deepmd_lmp
+        ENABLE_TENSORFLOW: ${{ matrix.enable_tensorflow && '1' || '0' }}
+        ENABLE_PYTORCH: ${{ matrix.enable_pytorch && '1' || '0' }}
+        ENABLE_JAX: ${{ matrix.enable_tensorflow && '1' || '0' }}
+        ENABLE_PADDLE: ${{ matrix.enable_paddle && '1' || '0' }}
       if: ${{ !matrix.check_memleak }}
     # test ipi
     - run: |
         export PATH=${{ github.workspace }}/dp_test/bin:$PATH
-        cp ${{ github.workspace }}/source/build_tests/paddle_inference_install_dir/paddle/lib/*.so ${{ github.workspace }}/dp_test/lib/
-        cp ${{ github.workspace }}/source/build_tests/paddle_inference_install_dir/third_party/install/onednn/lib/* ${{ github.workspace }}/dp_test/lib/
-        cp ${{ github.workspace }}/source/build_tests/paddle_inference_install_dir/third_party/install/mklml/lib/* ${{ github.workspace }}/dp_test/lib/
         pytest --cov=deepmd source/ipi/tests
       env:
         OMP_NUM_THREADS: 1
         TF_INTRA_OP_PARALLELISM_THREADS: 1
         TF_INTER_OP_PARALLELISM_THREADS: 1
         LD_LIBRARY_PATH: ${{ github.workspace }}/dp_test/lib
+        ENABLE_TENSORFLOW: ${{ matrix.enable_tensorflow && '1' || '0' }}
+        ENABLE_PYTORCH: ${{ matrix.enable_pytorch && '1' || '0' }}
+        ENABLE_JAX: ${{ matrix.enable_tensorflow && '1' || '0' }}
+        ENABLE_PADDLE: ${{ matrix.enable_paddle && '1' || '0' }}
       if: ${{ !matrix.check_memleak }}
     - uses: codecov/codecov-action@v5
       env:

.github/workflows/test_cuda.yml

@@ -25,7 +25,7 @@ jobs:
     steps:
     - name: Make sudo and git work
       run: apt-get update && apt-get install -y sudo git
-    - uses: actions/checkout@v5
+    - uses: actions/checkout@v6
     - uses: actions/setup-python@v6
       with:
         python-version: '3.11'
@@ -43,11 +43,11 @@ jobs:
          && sudo apt-get -y install cuda-12-3 libcudnn8=8.9.5.*-1+cuda12.3
       if: false  # skip as we use nvidia image
     - run: python -m pip install -U uv
-    - run: source/install/uv_with_retry.sh pip install --system "tensorflow~=2.18.0rc2" "torch~=2.7.0" "jax[cuda12]==0.5.0"
+    - run: source/install/uv_with_retry.sh pip install --system --group pin_tensorflow_gpu --group pin_pytorch_gpu --group pin_jax "jax[cuda12]"
     - run: |
         export PYTORCH_ROOT=$(python -c 'import torch;print(torch.__path__[0])')
         export TENSORFLOW_ROOT=$(python -c 'import importlib.util,pathlib;print(pathlib.Path(importlib.util.find_spec("tensorflow").origin).parent)')
-        pip install "paddlepaddle-gpu==3.0.0" -i https://www.paddlepaddle.org.cn/packages/stable/cu126/
+        pip install --find-links "https://www.paddlepaddle.org.cn/packages/nightly/cu126/paddlepaddle-gpu/" --index-url https://pypi.org/simple "paddlepaddle-gpu==3.3.0.dev20251204"
         source/install/uv_with_retry.sh pip install --system -v -e .[gpu,test,lmp,cu12,torch,jax] mpi4py --reinstall-package deepmd-kit
       env:
         DP_VARIANT: cuda
@@ -61,6 +61,7 @@ jobs:
         # See https://jax.readthedocs.io/en/latest/gpu_memory_allocation.html
         XLA_PYTHON_CLIENT_PREALLOCATE: false
         XLA_PYTHON_CLIENT_ALLOCATOR: platform
+        FLAGS_use_stride_compute_kernel: 0
     - name: Convert models
       run: source/tests/infer/convert-models.sh
     - run: |