fix unitest config

Author: HydrogenSulfate

.github/workflows/test_cuda.yml

@@ -47,7 +47,7 @@ jobs:
     - 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==3.2.2" -i https://www.paddlepaddle.org.cn/packages/stable/cu126/
+        pip install --pre paddlepaddle-gpu -i https://www.paddlepaddle.org.cn/packages/nightly/cu126/
         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: |

.github/workflows/test_python.yml

@@ -35,7 +35,7 @@ jobs:
         source/install/uv_with_retry.sh pip install --system -e .[test,jax] mpi4py "jax==0.5.0;python_version>='3.10'"
         source/install/uv_with_retry.sh pip install --system -U setuptools
         source/install/uv_with_retry.sh pip install --system horovod --no-build-isolation
-        source/install/uv_with_retry.sh pip install --system --pre "paddlepaddle==3.2.2" -i https://www.paddlepaddle.org.cn/packages/stable/cpu/
+        source/install/uv_with_retry.sh pip install --system --pre "paddlepaddle" -i https://www.paddlepaddle.org.cn/packages/stable/cpu/
       env:
         # Please note that uv has some issues with finding
         # existing TensorFlow package. Currently, it uses
@@ -63,6 +63,7 @@ jobs:
     - run: pytest --cov=deepmd source/tests  --splits 6 --group ${{ matrix.group }} --store-durations --clean-durations --durations-path=.test_durations --splitting-algorithm least_duration
       env:
         NUM_WORKERS: 0
+        FLAGS_use_stride_compute_kernel: 0
     - name: Test TF2 eager mode
       run: pytest --cov=deepmd --cov-append source/tests/consistent/io/test_io.py source/jax2tf_tests
       env:

source/tests/pd/conftest.py

@@ -6,4 +6,5 @@
 @pytest.fixture(scope="package", autouse=True)
 def clear_cuda_memory(request):
     yield
-    paddle.device.empty_cache()
+    if paddle.device.get_device() != "cpu":
+        paddle.device.empty_cache()