[DO NOT MERGE] Testing arrow seg fault

.github/workflows/pr.yaml

@@ -180,7 +180,6 @@ jobs:
       container_image: "rapidsai/ci-conda:cuda12.5.1-ubuntu22.04-py3.11"
       run_script: "ci/build_docs.sh"
   wheel-build-libcudf:
-    needs: checks
     secrets: inherit
     uses: rapidsai/shared-workflows/.github/workflows/[email protected]
     with:
@@ -189,7 +188,7 @@ jobs:
       build_type: pull-request
       script: "ci/build_wheel_libcudf.sh"
   wheel-build-pylibcudf:
-    needs: [checks, wheel-build-libcudf]
+    needs: wheel-build-libcudf
     secrets: inherit
     uses: rapidsai/shared-workflows/.github/workflows/[email protected]
     with:
@@ -203,10 +202,9 @@ jobs:
       build_type: pull-request
       script: "ci/build_wheel_cudf.sh"
   wheel-tests-cudf:
-    needs: [wheel-build-cudf, changed-files]
+    needs: wheel-build-cudf
     secrets: inherit
     uses: rapidsai/shared-workflows/.github/workflows/[email protected]
-    if: fromJSON(needs.changed-files.outputs.changed_file_groups).test_python
     with:
       build_type: pull-request
       script: ci/test_wheel_cudf.sh

ci/test_wheel_cudf.sh

@@ -34,22 +34,6 @@ RESULTS_DIR=${RAPIDS_TESTS_DIR:-"$(mktemp -d)"}
 RAPIDS_TESTS_DIR=${RAPIDS_TESTS_DIR:-"${RESULTS_DIR}/test-results"}/
 mkdir -p "${RAPIDS_TESTS_DIR}"
 
-
-rapids-logger "pytest pylibcudf"
-pushd python/pylibcudf/pylibcudf/tests
-python -m pytest \
-  --cache-clear \
-  --numprocesses=8 \
-  --dist=worksteal \
-  .
-popd
-
 rapids-logger "pytest cudf"
-pushd python/cudf/cudf/tests
-python -m pytest \
-  --cache-clear \
-  --junitxml="${RAPIDS_TESTS_DIR}/junit-cudf.xml" \
-  --numprocesses=8 \
-  --dist=worksteal \
-  .
-popd
+export ARROW_DEFAULT_MEMORY_POOL="mimalloc"
+python -c "import cupy; import cudf"

python/cudf/cudf/__init__.py

@@ -1,5 +1,3 @@
-# Copyright (c) 2018-2024, NVIDIA CORPORATION.
-
 # If libcudf was installed as a wheel, we must request it to load the library symbols.
 # Otherwise, we assume that the library was installed in a system path that ld can find.
 try:
@@ -10,147 +8,5 @@
     libcudf.load_library()
     del libcudf
 
-# _setup_numba _must be called before numba.cuda is imported, because
-# it sets the numba config variable responsible for enabling
-# Minor Version Compatibility. Setting it after importing numba.cuda has no effect.
-from cudf.utils._numba import _setup_numba
-from cudf.utils.gpu_utils import validate_setup
-
-_setup_numba()
-validate_setup()
-
-import cupy
-from numba import config as numba_config, cuda
-
-import rmm
-from rmm.allocators.cupy import rmm_cupy_allocator
-from rmm.allocators.numba import RMMNumbaManager
-
-from cudf import api, core, datasets, testing
-from cudf._version import __git_commit__, __version__
-from cudf.api.extensions import (
-    register_dataframe_accessor,
-    register_index_accessor,
-    register_series_accessor,
-)
-from cudf.api.types import dtype
-from cudf.core.algorithms import factorize, unique
-from cudf.core.cut import cut
-from cudf.core.dataframe import DataFrame, from_dataframe, from_pandas, merge
-from cudf.core.dtypes import (
-    CategoricalDtype,
-    Decimal32Dtype,
-    Decimal64Dtype,
-    Decimal128Dtype,
-    IntervalDtype,
-    ListDtype,
-    StructDtype,
-)
-from cudf.core.groupby import Grouper, NamedAgg
-from cudf.core.index import (
-    BaseIndex,
-    CategoricalIndex,
-    DatetimeIndex,
-    Index,
-    IntervalIndex,
-    RangeIndex,
-    TimedeltaIndex,
-    interval_range,
-)
-from cudf.core.missing import NA, NaT
-from cudf.core.multiindex import MultiIndex
-from cudf.core.reshape import (
-    concat,
-    crosstab,
-    get_dummies,
-    melt,
-    pivot,
-    pivot_table,
-    unstack,
-)
-from cudf.core.scalar import Scalar
-from cudf.core.series import Series, isclose
-from cudf.core.tools.datetimes import DateOffset, date_range, to_datetime
-from cudf.core.tools.numeric import to_numeric
-from cudf.io import (
-    from_dlpack,
-    read_avro,
-    read_csv,
-    read_feather,
-    read_hdf,
-    read_json,
-    read_orc,
-    read_parquet,
-    read_text,
-)
-from cudf.options import (
-    describe_option,
-    get_option,
-    option_context,
-    set_option,
-)
-from cudf.utils.utils import clear_cache
-
-cuda.set_memory_manager(RMMNumbaManager)
-cupy.cuda.set_allocator(rmm_cupy_allocator)
-
-
-rmm.register_reinitialize_hook(clear_cache)
-
-
-__all__ = [
-    "BaseIndex",
-    "CategoricalDtype",
-    "CategoricalIndex",
-    "DataFrame",
-    "DateOffset",
-    "DatetimeIndex",
-    "Decimal32Dtype",
-    "Decimal64Dtype",
-    "Decimal128Dtype",
-    "Grouper",
-    "Index",
-    "IntervalDtype",
-    "IntervalIndex",
-    "ListDtype",
-    "MultiIndex",
-    "NA",
-    "NaT",
-    "RangeIndex",
-    "Scalar",
-    "Series",
-    "StructDtype",
-    "TimedeltaIndex",
-    "api",
-    "concat",
-    "crosstab",
-    "cut",
-    "date_range",
-    "describe_option",
-    "factorize",
-    "from_dataframe",
-    "from_dlpack",
-    "from_pandas",
-    "get_dummies",
-    "get_option",
-    "interval_range",
-    "isclose",
-    "melt",
-    "merge",
-    "option_context",
-    "pivot",
-    "pivot_table",
-    "read_avro",
-    "read_csv",
-    "read_feather",
-    "read_hdf",
-    "read_json",
-    "read_orc",
-    "read_parquet",
-    "read_text",
-    "set_option",
-    "testing",
-    "to_datetime",
-    "to_numeric",
-    "unstack",
-]
+from ptxcompiler.patch import safe_get_versions
+from cudf._lib import strings_udf