Merge branch 'branch-24.10' of github.com:rapidsai/cudf into libcudf-…

…wheel

.github/workflows/pandas-tests.yaml

@@ -19,7 +19,8 @@ jobs:
       secrets: inherit
       uses: rapidsai/shared-workflows/.github/workflows/[email protected]
       with:
-        matrix_filter: map(select(.ARCH == "amd64" and .PY_VER == "3.9" and (.CUDA_VER | startswith("12.5.")) ))
+        # This selects "ARCH=amd64 + the latest supported Python + CUDA".
+        matrix_filter: map(select(.ARCH == "amd64")) | group_by(.CUDA_VER|split(".")|map(tonumber)|.[0]) | map(max_by([(.PY_VER|split(".")|map(tonumber)), (.CUDA_VER|split(".")|map(tonumber))]))
         build_type: nightly
         branch: ${{ inputs.branch }}
         date: ${{ inputs.date }}

.github/workflows/pr.yaml

@@ -196,6 +196,7 @@ jobs:
     secrets: inherit
     uses: rapidsai/shared-workflows/.github/workflows/[email protected]
     with:
+      # This selects "ARCH=amd64 + the latest supported Python + CUDA".
       matrix_filter: map(select(.ARCH == "amd64")) | group_by(.CUDA_VER|split(".")|map(tonumber)|.[0]) | map(max_by([(.PY_VER|split(".")|map(tonumber)), (.CUDA_VER|split(".")|map(tonumber))]))
       build_type: pull-request
       script: ci/cudf_pandas_scripts/run_tests.sh
@@ -205,7 +206,8 @@ jobs:
     secrets: inherit
     uses: rapidsai/shared-workflows/.github/workflows/[email protected]
     with:
-      matrix_filter: map(select(.ARCH == "amd64" and .PY_VER == "3.9" and (.CUDA_VER | startswith("12.5.")) ))
+      # This selects "ARCH=amd64 + the latest supported Python + CUDA".
+      matrix_filter: map(select(.ARCH == "amd64")) | group_by(.CUDA_VER|split(".")|map(tonumber)|.[0]) | map(max_by([(.PY_VER|split(".")|map(tonumber)), (.CUDA_VER|split(".")|map(tonumber))]))
       build_type: pull-request
       script: ci/cudf_pandas_scripts/pandas-tests/run.sh pr
       # Hide test failures because they exceed the GITHUB_STEP_SUMMARY output limit.

python/dask_cudf/dask_cudf/backends.py

@@ -667,6 +667,41 @@ def from_dict(
             constructor=constructor,
         )
 
+    @staticmethod
+    def read_parquet(*args, engine=None, **kwargs):
+        import dask_expr as dx
+
+        from dask_cudf.io.parquet import CudfEngine
+
+        return _default_backend(
+            dx.read_parquet, *args, engine=CudfEngine, **kwargs
+        )
+
+    @staticmethod
+    def read_csv(
+        path,
+        *args,
+        header="infer",
+        dtype_backend=None,
+        storage_options=None,
+        **kwargs,
+    ):
+        import dask_expr as dx
+        from fsspec.utils import stringify_path
+
+        if not isinstance(path, str):
+            path = stringify_path(path)
+        return dx.new_collection(
+            dx.io.csv.ReadCSV(
+                path,
+                dtype_backend=dtype_backend,
+                storage_options=storage_options,
+                kwargs=kwargs,
+                header=header,
+                dataframe_backend="cudf",
+            )
+        )
+
     @staticmethod
     def read_json(*args, **kwargs):
         from dask_cudf.io.json import read_json as read_json_impl