Merge remote-tracking branch 'upstream/branch-25.02' into cccl-2.7.0-rc2

.github/copy-pr-bot.yaml

@@ -2,3 +2,4 @@
 # https://docs.gha-runners.nvidia.com/apps/copy-pr-bot/
 
 enabled: true
+auto_sync_draft: false

.github/workflows/pr.yaml

@@ -61,6 +61,7 @@ jobs:
       files_yaml: |
         test_cpp:
           - '**'
+          - '!.devcontainer/**'
           - '!CONTRIBUTING.md'
           - '!README.md'
           - '!ci/cudf_pandas_scripts/**'
@@ -71,6 +72,7 @@ jobs:
           - '!python/**'
         test_cudf_pandas:
           - '**'
+          - '!.devcontainer/**'
           - '!CONTRIBUTING.md'
           - '!README.md'
           - '!docs/**'
@@ -79,6 +81,7 @@ jobs:
           - '!notebooks/**'
         test_java:
           - '**'
+          - '!.devcontainer/**'
           - '!CONTRIBUTING.md'
           - '!README.md'
           - '!ci/cudf_pandas_scripts/**'
@@ -88,12 +91,14 @@ jobs:
           - '!python/**'
         test_notebooks:
           - '**'
+          - '!.devcontainer/**'
           - '!CONTRIBUTING.md'
           - '!README.md'
           - '!ci/cudf_pandas_scripts/**'
           - '!java/**'
         test_python:
           - '**'
+          - '!.devcontainer/**'
           - '!CONTRIBUTING.md'
           - '!README.md'
           - '!ci/cudf_pandas_scripts/**'

.github/workflows/trigger-breaking-change-alert.yaml

@@ -0,0 +1,26 @@
+name: Trigger Breaking Change Notifications
+
+on:
+  pull_request_target:
+    types:
+      - closed
+      - reopened
+      - labeled
+      - unlabeled
+
+jobs:
+  trigger-notifier:
+    if: contains(github.event.pull_request.labels.*.name, 'breaking')
+    secrets: inherit
+    uses: rapidsai/shared-workflows/.github/workflows/[email protected]
+    with:
+      sender_login: ${{ github.event.sender.login }}
+      sender_avatar: ${{ github.event.sender.avatar_url }}
+      repo: ${{ github.repository }}
+      pr_number: ${{ github.event.pull_request.number }}
+      pr_title: "${{ github.event.pull_request.title }}"
+      pr_body: "${{ github.event.pull_request.body || '_Empty PR description_' }}"
+      pr_base_ref: ${{ github.event.pull_request.base.ref }}
+      pr_author: ${{ github.event.pull_request.user.login }}
+      event_action: ${{ github.event.action }}
+      pr_merged: ${{ github.event.pull_request.merged }}

.pre-commit-config.yaml

@@ -2,7 +2,7 @@
 
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.6.0
+    rev: v5.0.0
     hooks:
       - id: trailing-whitespace
         exclude: |
@@ -17,11 +17,11 @@ repos:
             ^python/cudf/cudf/tests/data/subword_tokenizer_data/.*
           )
   - repo: https://github.com/MarcoGorelli/cython-lint
-    rev: v0.16.2
+    rev: v0.16.6
     hooks:
       - id: cython-lint
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: 'v1.10.0'
+    rev: 'v1.13.0'
     hooks:
       - id: mypy
         additional_dependencies: [types-cachetools]
@@ -33,7 +33,7 @@ repos:
                "python/dask_cudf/dask_cudf"]
         pass_filenames: false
   - repo: https://github.com/nbQA-dev/nbQA
-    rev: 1.8.5
+    rev: 1.9.1
     hooks:
       - id: nbqa-isort
         # Use the cudf_kafka isort orderings in notebooks so that dask
@@ -52,7 +52,7 @@ repos:
             ^cpp/include/cudf_test/cxxopts.hpp
           )
   - repo: https://github.com/sirosen/texthooks
-    rev: 0.6.6
+    rev: 0.6.7
     hooks:
       - id: fix-smartquotes
         exclude: |
@@ -133,7 +133,7 @@ repos:
         pass_filenames: false
         verbose: true
   - repo: https://github.com/codespell-project/codespell
-    rev: v2.2.6
+    rev: v2.3.0
     hooks:
       - id: codespell
         additional_dependencies: [tomli]
@@ -144,7 +144,7 @@ repos:
             ^CHANGELOG.md$
           )
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.4.8
+    rev: v0.8.0
     hooks:
       - id: ruff
         args: ["--fix"]

conda/environments/all_cuda-118_arch-x86_64.yaml

@@ -80,7 +80,6 @@ dependencies:
 - python-confluent-kafka>=2.5.0,<2.6.0a0
 - python-xxhash
 - python>=3.10,<3.13
-- pytorch>=2.1.0
 - rapids-build-backend>=0.3.0,<0.4.0.dev0
 - rapids-dask-dependency==25.2.*,>=0.0.0a0
 - rich
@@ -97,8 +96,6 @@ dependencies:
 - sphinxcontrib-websupport
 - streamz
 - sysroot_linux-64==2.17
-- tokenizers==0.15.2
-- transformers==4.39.3
 - typing_extensions>=4.0.0
 - zlib>=1.2.13
 name: all_cuda-118_arch-x86_64

conda/environments/all_cuda-125_arch-x86_64.yaml

@@ -78,7 +78,7 @@ dependencies:
 - python-confluent-kafka>=2.5.0,<2.6.0a0
 - python-xxhash
 - python>=3.10,<3.13
-- pytorch>=2.1.0
+- pytorch>=2.4.0
 - rapids-build-backend>=0.3.0,<0.4.0.dev0
 - rapids-dask-dependency==25.2.*,>=0.0.0a0
 - rich

cpp/CMakeLists.txt

@@ -926,9 +926,16 @@ add_dependencies(cudf jitify_preprocess_run)
 # Specify the target module library dependencies
 target_link_libraries(
   cudf
-  PUBLIC CCCL::CCCL rmm::rmm $<BUILD_LOCAL_INTERFACE:BS::thread_pool> spdlog::spdlog_header_only
-  PRIVATE $<BUILD_LOCAL_INTERFACE:nvtx3::nvtx3-cpp> cuco::cuco ZLIB::ZLIB nvcomp::nvcomp
-          kvikio::kvikio $<TARGET_NAME_IF_EXISTS:CUDA::cuFile${_cufile_suffix}> nanoarrow
+  PUBLIC CCCL::CCCL rmm::rmm rmm::rmm_logger $<BUILD_LOCAL_INTERFACE:BS::thread_pool>
+         spdlog::spdlog_header_only
+  PRIVATE $<BUILD_LOCAL_INTERFACE:nvtx3::nvtx3-cpp>
+          cuco::cuco
+          ZLIB::ZLIB
+          nvcomp::nvcomp
+          kvikio::kvikio
+          $<TARGET_NAME_IF_EXISTS:CUDA::cuFile${_cufile_suffix}>
+          nanoarrow
+          rmm::rmm_logger_impl
 )
 
 # Add Conda library, and include paths if specified
@@ -1007,7 +1014,7 @@ if(CUDF_BUILD_TESTUTIL)
   )
 
   target_link_libraries(
-    cudftestutil INTERFACE Threads::Threads cudf cudftest_default_stream
+    cudftestutil INTERFACE cuco::cuco Threads::Threads cudf cudftest_default_stream
                            $<TARGET_NAME_IF_EXISTS:conda_env>
   )
 

cpp/benchmarks/CMakeLists.txt

@@ -360,8 +360,6 @@ ConfigureNVBench(
 
 # ##################################################################################################
 # * strings benchmark -------------------------------------------------------------------
-ConfigureBench(STRINGS_BENCH string/factory.cu)
-
 ConfigureNVBench(
   STRINGS_NVBENCH
   string/case.cpp
@@ -377,6 +375,7 @@ ConfigureNVBench(
   string/copy_range.cpp
   string/count.cpp
   string/extract.cpp
+  string/factory.cpp
   string/filter.cpp
   string/find.cpp
   string/find_multiple.cpp

cpp/benchmarks/string/factory.cpp

@@ -0,0 +1,60 @@
+/*
+ * Copyright (c) 2021-2024, NVIDIA CORPORATION.
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+#include <benchmarks/common/generate_input.hpp>
+
+#include <cudf/column/column_factories.hpp>
+#include <cudf/strings/detail/utilities.hpp>
+#include <cudf/strings/string_view.cuh>
+#include <cudf/strings/strings_column_view.hpp>
+#include <cudf/utilities/default_stream.hpp>
+
+#include <rmm/device_uvector.hpp>
+
+#include <nvbench/nvbench.cuh>
+
+#include <limits>
+
+static void bench_factory(nvbench::state& state)
+{
+  auto const num_rows  = static_cast<cudf::size_type>(state.get_int64("num_rows"));
+  auto const min_width = static_cast<cudf::size_type>(state.get_int64("min_width"));
+  auto const max_width = static_cast<cudf::size_type>(state.get_int64("max_width"));
+
+  data_profile const profile = data_profile_builder().distribution(
+    cudf::type_id::STRING, distribution_id::NORMAL, min_width, max_width);
+  auto const column = create_random_column(cudf::type_id::STRING, row_count{num_rows}, profile);
+  auto const sv     = cudf::strings_column_view(column->view());
+
+  auto stream    = cudf::get_default_stream();
+  auto mr        = cudf::get_current_device_resource_ref();
+  auto d_strings = cudf::strings::detail::create_string_vector_from_column(sv, stream, mr);
+
+  state.set_cuda_stream(nvbench::make_cuda_stream_view(stream.value()));
+  auto chars_size = sv.chars_size(stream);
+  state.add_global_memory_reads<nvbench::int8_t>(chars_size);
+  state.add_global_memory_writes<nvbench::int8_t>(chars_size);
+
+  state.exec(nvbench::exec_tag::sync, [&](nvbench::launch& launch) {
+    cudf::make_strings_column(d_strings, cudf::string_view{nullptr, 0});
+  });
+}
+
+NVBENCH_BENCH(bench_factory)
+  .set_name("factory")
+  .add_int64_axis("min_width", {0})
+  .add_int64_axis("max_width", {32, 64, 128, 256})
+  .add_int64_axis("num_rows", {32768, 262144, 2097152});

cpp/cmake/thirdparty/get_cucollections.cmake

@@ -16,11 +16,7 @@
 function(find_and_configure_cucollections)
   include(${rapids-cmake-dir}/cpm/cuco.cmake)
 
-  if(BUILD_SHARED_LIBS)
-    rapids_cpm_cuco(BUILD_EXPORT_SET cudf-exports)
-  else()
-    rapids_cpm_cuco(BUILD_EXPORT_SET cudf-exports INSTALL_EXPORT_SET cudf-exports)
-  endif()
+  rapids_cpm_cuco(BUILD_EXPORT_SET cudf-exports INSTALL_EXPORT_SET cudf-exports)
 endfunction()
 
 find_and_configure_cucollections()

cpp/examples/basic/CMakeLists.txt

@@ -16,6 +16,9 @@ project(
 
 include(../fetch_dependencies.cmake)
 
+include(rapids-cmake)
+rapids_cmake_build_type("Release")
+
 # Configure your project here
 add_executable(basic_example src/process_csv.cpp)
 target_link_libraries(basic_example PRIVATE cudf::cudf)

cpp/examples/billion_rows/CMakeLists.txt

@@ -16,6 +16,9 @@ project(
 
 include(../fetch_dependencies.cmake)
 
+include(rapids-cmake)
+rapids_cmake_build_type("Release")
+
 list(APPEND CUDF_CUDA_FLAGS --expt-extended-lambda --expt-relaxed-constexpr)
 
 add_library(groupby_results OBJECT groupby_results.cpp)

cpp/examples/interop/CMakeLists.txt

@@ -15,6 +15,9 @@ project(
 
 include(../fetch_dependencies.cmake)
 
+include(rapids-cmake)
+rapids_cmake_build_type("Release")
+
 # The Arrow CMake is currently broken if the build type is not set
 set(CMAKE_BUILD_TYPE Release)
 # No need to install Arrow libs when only the final example executable is shipped.