diff --git a/cpp/include/cudf/aggregation/host_udf.hpp b/cpp/include/cudf/aggregation/host_udf.hpp
index 313dd1ff8500..051cae14e4ae 100644
--- a/cpp/include/cudf/aggregation/host_udf.hpp
+++ b/cpp/include/cudf/aggregation/host_udf.hpp
@@ -13,7 +13,7 @@
 
 #include <rmm/resource_ref.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <functional>
 #include <optional>
diff --git a/cpp/include/cudf/column/column.hpp b/cpp/include/cudf/column/column.hpp
index d02d821d83cd..a2617e12416c 100644
--- a/cpp/include/cudf/column/column.hpp
+++ b/cpp/include/cudf/column/column.hpp
@@ -13,7 +13,7 @@
 #include <rmm/device_buffer.hpp>
 #include <rmm/device_uvector.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 #include <type_traits>
diff --git a/cpp/include/cudf/column/column_device_view.cuh b/cpp/include/cudf/column/column_device_view.cuh
index a7add0c42c26..a3b1901244c9 100644
--- a/cpp/include/cudf/column/column_device_view.cuh
+++ b/cpp/include/cudf/column/column_device_view.cuh
@@ -19,7 +19,7 @@
 
 #include <cuda/iterator>
 #include <cuda/std/utility>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/iterator/transform_iterator.h>
 
 #include <functional>
diff --git a/cpp/include/cudf/column/column_factories.hpp b/cpp/include/cudf/column/column_factories.hpp
index b8b4b3fa5781..748764cca890 100644
--- a/cpp/include/cudf/column/column_factories.hpp
+++ b/cpp/include/cudf/column/column_factories.hpp
@@ -14,7 +14,7 @@
 #include <rmm/cuda_stream_view.hpp>
 
 #include <cuda/std/utility>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 /**
  * @file
diff --git a/cpp/include/cudf/column/column_stream.hpp b/cpp/include/cudf/column/column_stream.hpp
index db1835adc8dd..17555994d553 100644
--- a/cpp/include/cudf/column/column_stream.hpp
+++ b/cpp/include/cudf/column/column_stream.hpp
@@ -6,7 +6,7 @@
 
 #include <cudf/column/column.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 
diff --git a/cpp/include/cudf/concatenate.hpp b/cpp/include/cudf/concatenate.hpp
index 8f6459d74247..e9beada299a6 100644
--- a/cpp/include/cudf/concatenate.hpp
+++ b/cpp/include/cudf/concatenate.hpp
@@ -11,7 +11,7 @@
 #include <cudf/utilities/memory_resource.hpp>
 #include <cudf/utilities/span.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 #include <span>
diff --git a/cpp/include/cudf/detail/algorithms/copy_if.cuh b/cpp/include/cudf/detail/algorithms/copy_if.cuh
index 038385f67c27..15455e42637e 100644
--- a/cpp/include/cudf/detail/algorithms/copy_if.cuh
+++ b/cpp/include/cudf/detail/algorithms/copy_if.cuh
@@ -1,5 +1,5 @@
 /*
- * SPDX-FileCopyrightText: Copyright (c) 2022-2026, NVIDIA CORPORATION.
+ * SPDX-FileCopyrightText: Copyright (c) 2022-2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
  * SPDX-License-Identifier: Apache-2.0
  */
 #pragma once
@@ -15,7 +15,7 @@
 #include <cub/device/device_select.cuh>
 #include <cuda/iterator>
 #include <cuda/std/functional>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/copy.h>
 
 namespace cudf::detail {
diff --git a/cpp/include/cudf/detail/algorithms/reduce.cuh b/cpp/include/cudf/detail/algorithms/reduce.cuh
index 3f81875bf629..c50062ba10cc 100644
--- a/cpp/include/cudf/detail/algorithms/reduce.cuh
+++ b/cpp/include/cudf/detail/algorithms/reduce.cuh
@@ -1,5 +1,5 @@
 /*
- * SPDX-FileCopyrightText: Copyright (c) 2022-2026, NVIDIA CORPORATION.
+ * SPDX-FileCopyrightText: Copyright (c) 2022-2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
  * SPDX-License-Identifier: Apache-2.0
  */
 #pragma once
@@ -15,7 +15,7 @@
 #include <cub/device/device_reduce.cuh>
 #include <cuda/iterator>
 #include <cuda/std/functional>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf::detail {
 
diff --git a/cpp/include/cudf/detail/binaryop.hpp b/cpp/include/cudf/detail/binaryop.hpp
index 1bc3bc40f917..a83bd008919e 100644
--- a/cpp/include/cudf/detail/binaryop.hpp
+++ b/cpp/include/cudf/detail/binaryop.hpp
@@ -8,7 +8,7 @@
 #include <cudf/utilities/default_stream.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 //! Inner interfaces and implementations
diff --git a/cpp/include/cudf/detail/concatenate.hpp b/cpp/include/cudf/detail/concatenate.hpp
index b67f556b911d..4463b126f958 100644
--- a/cpp/include/cudf/detail/concatenate.hpp
+++ b/cpp/include/cudf/detail/concatenate.hpp
@@ -11,7 +11,7 @@
 #include <cudf/utilities/memory_resource.hpp>
 #include <cudf/utilities/span.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <span>
 #include <vector>
diff --git a/cpp/include/cudf/detail/concatenate_masks.hpp b/cpp/include/cudf/detail/concatenate_masks.hpp
index 449791bee14c..74c75f5dee55 100644
--- a/cpp/include/cudf/detail/concatenate_masks.hpp
+++ b/cpp/include/cudf/detail/concatenate_masks.hpp
@@ -11,7 +11,7 @@
 
 #include <rmm/device_buffer.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <span>
 
diff --git a/cpp/include/cudf/detail/contiguous_split.hpp b/cpp/include/cudf/detail/contiguous_split.hpp
index 73de92bce2e9..fa6be805fe26 100644
--- a/cpp/include/cudf/detail/contiguous_split.hpp
+++ b/cpp/include/cudf/detail/contiguous_split.hpp
@@ -10,7 +10,7 @@
 #include <cudf/utilities/default_stream.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <cstdint>
 #include <optional>
diff --git a/cpp/include/cudf/detail/copy.hpp b/cpp/include/cudf/detail/copy.hpp
index 0afd97f4b44e..f18ff013fb9c 100644
--- a/cpp/include/cudf/detail/copy.hpp
+++ b/cpp/include/cudf/detail/copy.hpp
@@ -13,7 +13,7 @@
 #include <cudf/utilities/span.hpp>
 #include <cudf/utilities/traits.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <initializer_list>
 #include <span>
diff --git a/cpp/include/cudf/detail/copy_range.cuh b/cpp/include/cudf/detail/copy_range.cuh
index dcb934dd645e..4a438503f724 100644
--- a/cpp/include/cudf/detail/copy_range.cuh
+++ b/cpp/include/cudf/detail/copy_range.cuh
@@ -19,7 +19,7 @@
 #include <cudf/utilities/type_dispatcher.hpp>
 
 #include <cub/cub.cuh>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <cuda_runtime.h>
 
 #include <memory>
diff --git a/cpp/include/cudf/detail/fill.hpp b/cpp/include/cudf/detail/fill.hpp
index 4931b2f69363..80a6fc48a344 100644
--- a/cpp/include/cudf/detail/fill.hpp
+++ b/cpp/include/cudf/detail/fill.hpp
@@ -10,7 +10,7 @@
 #include <cudf/utilities/default_stream.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 
diff --git a/cpp/include/cudf/detail/gather.hpp b/cpp/include/cudf/detail/gather.hpp
index 9190b08e57f2..a5fdf224228f 100644
--- a/cpp/include/cudf/detail/gather.hpp
+++ b/cpp/include/cudf/detail/gather.hpp
@@ -13,7 +13,7 @@
 #include <cudf/utilities/memory_resource.hpp>
 #include <cudf/utilities/span.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 
diff --git a/cpp/include/cudf/detail/groupby.hpp b/cpp/include/cudf/detail/groupby.hpp
index 85c9e395379f..e6ab30c2b102 100644
--- a/cpp/include/cudf/detail/groupby.hpp
+++ b/cpp/include/cudf/detail/groupby.hpp
@@ -9,7 +9,7 @@
 #include <cudf/utilities/memory_resource.hpp>
 #include <cudf/utilities/span.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 #include <utility>
diff --git a/cpp/include/cudf/detail/groupby/sort_helper.hpp b/cpp/include/cudf/detail/groupby/sort_helper.hpp
index 71b9a6a00da2..c0ea19eb3d70 100644
--- a/cpp/include/cudf/detail/groupby/sort_helper.hpp
+++ b/cpp/include/cudf/detail/groupby/sort_helper.hpp
@@ -13,7 +13,7 @@
 
 #include <rmm/device_uvector.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace groupby::detail::sort {
diff --git a/cpp/include/cudf/detail/is_element_valid.hpp b/cpp/include/cudf/detail/is_element_valid.hpp
index df5630575cad..538211c4906c 100644
--- a/cpp/include/cudf/detail/is_element_valid.hpp
+++ b/cpp/include/cudf/detail/is_element_valid.hpp
@@ -8,7 +8,7 @@
 #include <cudf/column/column_view.hpp>
 #include <cudf/utilities/export.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace CUDF_EXPORT cudf {
 namespace detail {
diff --git a/cpp/include/cudf/detail/join/distinct_hash_join.cuh b/cpp/include/cudf/detail/join/distinct_hash_join.cuh
index bcaacdc8457a..f054de00fb2a 100644
--- a/cpp/include/cudf/detail/join/distinct_hash_join.cuh
+++ b/cpp/include/cudf/detail/join/distinct_hash_join.cuh
@@ -12,7 +12,7 @@
 #include <rmm/mr/polymorphic_allocator.hpp>
 
 #include <cuco/static_set.cuh>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <cstddef>
 #include <memory>
diff --git a/cpp/include/cudf/detail/join/filtered_join.cuh b/cpp/include/cudf/detail/join/filtered_join.cuh
index 0f886217a076..b6d9949e187b 100644
--- a/cpp/include/cudf/detail/join/filtered_join.cuh
+++ b/cpp/include/cudf/detail/join/filtered_join.cuh
@@ -20,7 +20,7 @@
 #include <cuco/pair.cuh>
 #include <cuco/probing_scheme.cuh>
 #include <cuco/types.cuh>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <cstddef>
 #include <cstdint>
diff --git a/cpp/include/cudf/detail/join/hash_join.hpp b/cpp/include/cudf/detail/join/hash_join.hpp
index fc32d86c0e5d..0218faf19599 100644
--- a/cpp/include/cudf/detail/join/hash_join.hpp
+++ b/cpp/include/cudf/detail/join/hash_join.hpp
@@ -16,7 +16,7 @@
 #include <rmm/device_buffer.hpp>
 #include <rmm/device_uvector.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <cstddef>
 #include <memory>
diff --git a/cpp/include/cudf/detail/join/join.hpp b/cpp/include/cudf/detail/join/join.hpp
index 227ac6024bc2..83b17930e90c 100644
--- a/cpp/include/cudf/detail/join/join.hpp
+++ b/cpp/include/cudf/detail/join/join.hpp
@@ -13,7 +13,7 @@
 #include <rmm/device_uvector.hpp>
 #include <rmm/resource_ref.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <cstddef>
 #include <memory>
diff --git a/cpp/include/cudf/detail/null_mask.cuh b/cpp/include/cudf/detail/null_mask.cuh
index 6d33cc35cb01..a80a99db8cda 100644
--- a/cpp/include/cudf/detail/null_mask.cuh
+++ b/cpp/include/cudf/detail/null_mask.cuh
@@ -24,7 +24,7 @@
 #include <cuda/functional>
 #include <cuda/iterator>
 #include <cuda/std/tuple>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/for_each.h>
 #include <thrust/iterator/transform_iterator.h>
 #include <thrust/transform.h>
diff --git a/cpp/include/cudf/detail/null_mask.hpp b/cpp/include/cudf/detail/null_mask.hpp
index 4b7558aea780..cf4f8130af25 100644
--- a/cpp/include/cudf/detail/null_mask.hpp
+++ b/cpp/include/cudf/detail/null_mask.hpp
@@ -10,7 +10,7 @@
 #include <cudf/utilities/memory_resource.hpp>
 #include <cudf/utilities/span.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <span>
 #include <vector>
diff --git a/cpp/include/cudf/detail/repeat.hpp b/cpp/include/cudf/detail/repeat.hpp
index 9ef70c4f951e..f124557940e7 100644
--- a/cpp/include/cudf/detail/repeat.hpp
+++ b/cpp/include/cudf/detail/repeat.hpp
@@ -9,7 +9,7 @@
 #include <cudf/utilities/default_stream.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 
diff --git a/cpp/include/cudf/detail/rolling.hpp b/cpp/include/cudf/detail/rolling.hpp
index a962361d64f0..fa5d8a3bf7cb 100644
--- a/cpp/include/cudf/detail/rolling.hpp
+++ b/cpp/include/cudf/detail/rolling.hpp
@@ -11,7 +11,7 @@
 #include <cudf/utilities/default_stream.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 
diff --git a/cpp/include/cudf/detail/scan.hpp b/cpp/include/cudf/detail/scan.hpp
index 182446e0aa6b..f50209f3d41a 100644
--- a/cpp/include/cudf/detail/scan.hpp
+++ b/cpp/include/cudf/detail/scan.hpp
@@ -8,7 +8,7 @@
 #include <cudf/detail/aggregation/aggregation.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace detail {
diff --git a/cpp/include/cudf/detail/scatter.cuh b/cpp/include/cudf/detail/scatter.cuh
index a836d7eb33eb..a967c51963f0 100644
--- a/cpp/include/cudf/detail/scatter.cuh
+++ b/cpp/include/cudf/detail/scatter.cuh
@@ -26,7 +26,7 @@
 #include <rmm/exec_policy.hpp>
 
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/count.h>
 #include <thrust/iterator/transform_iterator.h>
 #include <thrust/scatter.h>
diff --git a/cpp/include/cudf/detail/scatter.hpp b/cpp/include/cudf/detail/scatter.hpp
index 7045aea44c3a..2ac62adbf8c4 100644
--- a/cpp/include/cudf/detail/scatter.hpp
+++ b/cpp/include/cudf/detail/scatter.hpp
@@ -12,7 +12,7 @@
 #include <cudf/utilities/memory_resource.hpp>
 #include <cudf/utilities/span.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 
diff --git a/cpp/include/cudf/detail/search.hpp b/cpp/include/cudf/detail/search.hpp
index 8e9e80195a9e..a741bda40b9d 100644
--- a/cpp/include/cudf/detail/search.hpp
+++ b/cpp/include/cudf/detail/search.hpp
@@ -13,7 +13,7 @@
 
 #include <rmm/device_uvector.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace detail {
diff --git a/cpp/include/cudf/detail/sequence.hpp b/cpp/include/cudf/detail/sequence.hpp
index d67d5a83f4b9..ab3ac4ac59dd 100644
--- a/cpp/include/cudf/detail/sequence.hpp
+++ b/cpp/include/cudf/detail/sequence.hpp
@@ -10,7 +10,7 @@
 #include <cudf/utilities/default_stream.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace detail {
diff --git a/cpp/include/cudf/detail/sorting.hpp b/cpp/include/cudf/detail/sorting.hpp
index 9c5e8dc4af07..bf48a7d29dac 100644
--- a/cpp/include/cudf/detail/sorting.hpp
+++ b/cpp/include/cudf/detail/sorting.hpp
@@ -10,7 +10,7 @@
 #include <cudf/utilities/default_stream.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 #include <vector>
diff --git a/cpp/include/cudf/detail/transform.hpp b/cpp/include/cudf/detail/transform.hpp
index f6fd1ca386c7..11406c69a345 100644
--- a/cpp/include/cudf/detail/transform.hpp
+++ b/cpp/include/cudf/detail/transform.hpp
@@ -11,7 +11,7 @@
 #include <cudf/utilities/export.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace detail {
diff --git a/cpp/include/cudf/detail/unary.hpp b/cpp/include/cudf/detail/unary.hpp
index fd86d4d897e3..cc1286963d19 100644
--- a/cpp/include/cudf/detail/unary.hpp
+++ b/cpp/include/cudf/detail/unary.hpp
@@ -10,7 +10,7 @@
 #include <cudf/utilities/default_stream.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace detail {
diff --git a/cpp/include/cudf/dictionary/detail/concatenate.hpp b/cpp/include/cudf/dictionary/detail/concatenate.hpp
index 1238e3f6b1bc..8bc1ba109f32 100644
--- a/cpp/include/cudf/dictionary/detail/concatenate.hpp
+++ b/cpp/include/cudf/dictionary/detail/concatenate.hpp
@@ -10,7 +10,7 @@
 #include <cudf/utilities/memory_resource.hpp>
 #include <cudf/utilities/span.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace dictionary::detail {
diff --git a/cpp/include/cudf/dictionary/detail/encode.hpp b/cpp/include/cudf/dictionary/detail/encode.hpp
index e728acc1e389..6a212831661c 100644
--- a/cpp/include/cudf/dictionary/detail/encode.hpp
+++ b/cpp/include/cudf/dictionary/detail/encode.hpp
@@ -10,7 +10,7 @@
 #include <cudf/utilities/default_stream.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace dictionary::detail {
diff --git a/cpp/include/cudf/dictionary/detail/merge.hpp b/cpp/include/cudf/dictionary/detail/merge.hpp
index de4f15a3a431..b69009e9c5cd 100644
--- a/cpp/include/cudf/dictionary/detail/merge.hpp
+++ b/cpp/include/cudf/dictionary/detail/merge.hpp
@@ -9,7 +9,7 @@
 #include <cudf/dictionary/dictionary_column_view.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace dictionary::detail {
diff --git a/cpp/include/cudf/dictionary/detail/replace.hpp b/cpp/include/cudf/dictionary/detail/replace.hpp
index 3cd91b0ce77b..7b6bcd7a238d 100644
--- a/cpp/include/cudf/dictionary/detail/replace.hpp
+++ b/cpp/include/cudf/dictionary/detail/replace.hpp
@@ -10,7 +10,7 @@
 #include <cudf/utilities/default_stream.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace dictionary::detail {
diff --git a/cpp/include/cudf/dictionary/detail/search.hpp b/cpp/include/cudf/dictionary/detail/search.hpp
index 17483793ba44..4e5902dd0f88 100644
--- a/cpp/include/cudf/dictionary/detail/search.hpp
+++ b/cpp/include/cudf/dictionary/detail/search.hpp
@@ -9,7 +9,7 @@
 #include <cudf/utilities/default_stream.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace dictionary {
diff --git a/cpp/include/cudf/dictionary/detail/update_keys.hpp b/cpp/include/cudf/dictionary/detail/update_keys.hpp
index 0fb608acfa02..aa6accf03c1f 100644
--- a/cpp/include/cudf/dictionary/detail/update_keys.hpp
+++ b/cpp/include/cudf/dictionary/detail/update_keys.hpp
@@ -11,7 +11,7 @@
 #include <cudf/utilities/memory_resource.hpp>
 #include <cudf/utilities/span.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <span>
 
diff --git a/cpp/include/cudf/dictionary/dictionary_factories.hpp b/cpp/include/cudf/dictionary/dictionary_factories.hpp
index abfc29ba3e9f..bd336c866d8c 100644
--- a/cpp/include/cudf/dictionary/dictionary_factories.hpp
+++ b/cpp/include/cudf/dictionary/dictionary_factories.hpp
@@ -9,7 +9,7 @@
 #include <cudf/utilities/default_stream.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 /**
  * @file
diff --git a/cpp/include/cudf/groupby.hpp b/cpp/include/cudf/groupby.hpp
index a5d3a49893c8..a3e21b58093f 100644
--- a/cpp/include/cudf/groupby.hpp
+++ b/cpp/include/cudf/groupby.hpp
@@ -14,7 +14,7 @@
 #include <cudf/utilities/memory_resource.hpp>
 #include <cudf/utilities/span.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 #include <span>
diff --git a/cpp/include/cudf/join/conditional_join.hpp b/cpp/include/cudf/join/conditional_join.hpp
index a9d9a19ade5f..b0af5db3d007 100644
--- a/cpp/include/cudf/join/conditional_join.hpp
+++ b/cpp/include/cudf/join/conditional_join.hpp
@@ -15,7 +15,7 @@
 
 #include <rmm/device_uvector.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <optional>
 #include <utility>
diff --git a/cpp/include/cudf/join/direct_join.hpp b/cpp/include/cudf/join/direct_join.hpp
index f82d368d9542..40b145a3fd1e 100644
--- a/cpp/include/cudf/join/direct_join.hpp
+++ b/cpp/include/cudf/join/direct_join.hpp
@@ -13,7 +13,7 @@
 
 #include <rmm/device_uvector.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 #include <utility>
diff --git a/cpp/include/cudf/join/distinct_hash_join.hpp b/cpp/include/cudf/join/distinct_hash_join.hpp
index c88f8de40742..b89ae2c3dd1b 100644
--- a/cpp/include/cudf/join/distinct_hash_join.hpp
+++ b/cpp/include/cudf/join/distinct_hash_join.hpp
@@ -14,7 +14,7 @@
 
 #include <rmm/device_uvector.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <utility>
 
diff --git a/cpp/include/cudf/join/filtered_join.hpp b/cpp/include/cudf/join/filtered_join.hpp
index 3c1738afd579..8f41ffe86d0f 100644
--- a/cpp/include/cudf/join/filtered_join.hpp
+++ b/cpp/include/cudf/join/filtered_join.hpp
@@ -13,7 +13,7 @@
 
 #include <rmm/device_uvector.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 /**
  * @file
diff --git a/cpp/include/cudf/join/hash_join.hpp b/cpp/include/cudf/join/hash_join.hpp
index e527a856039f..22d88367402f 100644
--- a/cpp/include/cudf/join/hash_join.hpp
+++ b/cpp/include/cudf/join/hash_join.hpp
@@ -16,7 +16,7 @@
 
 #include <rmm/device_uvector.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <optional>
 #include <utility>
diff --git a/cpp/include/cudf/join/join.hpp b/cpp/include/cudf/join/join.hpp
index adc2358ca6fb..9b13ccdaf85b 100644
--- a/cpp/include/cudf/join/join.hpp
+++ b/cpp/include/cudf/join/join.hpp
@@ -15,7 +15,7 @@
 #include <rmm/device_uvector.hpp>
 
 #include <cuda/std/limits>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <cstddef>
 #include <cstdint>
diff --git a/cpp/include/cudf/join/key_remapping.hpp b/cpp/include/cudf/join/key_remapping.hpp
index 5eef4139571a..8b1dd8919505 100644
--- a/cpp/include/cudf/join/key_remapping.hpp
+++ b/cpp/include/cudf/join/key_remapping.hpp
@@ -12,7 +12,7 @@
 #include <cudf/utilities/export.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 
diff --git a/cpp/include/cudf/join/mark_join.hpp b/cpp/include/cudf/join/mark_join.hpp
index e1d88219e1c8..8ef75c2b73b9 100644
--- a/cpp/include/cudf/join/mark_join.hpp
+++ b/cpp/include/cudf/join/mark_join.hpp
@@ -14,7 +14,7 @@
 
 #include <rmm/device_uvector.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 
diff --git a/cpp/include/cudf/join/mixed_join.hpp b/cpp/include/cudf/join/mixed_join.hpp
index 52d5f4d45818..308bd2df2f29 100644
--- a/cpp/include/cudf/join/mixed_join.hpp
+++ b/cpp/include/cudf/join/mixed_join.hpp
@@ -15,7 +15,7 @@
 
 #include <rmm/device_uvector.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <optional>
 #include <utility>
diff --git a/cpp/include/cudf/join/sort_merge_join.hpp b/cpp/include/cudf/join/sort_merge_join.hpp
index 346369180e54..907b19a245be 100644
--- a/cpp/include/cudf/join/sort_merge_join.hpp
+++ b/cpp/include/cudf/join/sort_merge_join.hpp
@@ -13,7 +13,7 @@
 
 #include <rmm/device_uvector.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 
diff --git a/cpp/include/cudf/null_mask.hpp b/cpp/include/cudf/null_mask.hpp
index c60aeb1bfedc..bab9a034eafa 100644
--- a/cpp/include/cudf/null_mask.hpp
+++ b/cpp/include/cudf/null_mask.hpp
@@ -12,7 +12,7 @@
 
 #include <rmm/device_buffer.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <span>
 #include <vector>
diff --git a/cpp/include/cudf/partitioning.hpp b/cpp/include/cudf/partitioning.hpp
index 4b3a9b81dfaf..df8c35122b28 100644
--- a/cpp/include/cudf/partitioning.hpp
+++ b/cpp/include/cudf/partitioning.hpp
@@ -10,7 +10,7 @@
 #include <cudf/utilities/export.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 #include <vector>
diff --git a/cpp/include/cudf/reduction/approx_distinct_count.hpp b/cpp/include/cudf/reduction/approx_distinct_count.hpp
index 026dbc1784f8..0e9dddcba2e9 100644
--- a/cpp/include/cudf/reduction/approx_distinct_count.hpp
+++ b/cpp/include/cudf/reduction/approx_distinct_count.hpp
@@ -12,7 +12,7 @@
 #include <cudf/utilities/memory_resource.hpp>
 
 #include <cuda/std/span>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <cstddef>
 #include <cstdint>
diff --git a/cpp/include/cudf/reduction/detail/approx_distinct_count.cuh b/cpp/include/cudf/reduction/detail/approx_distinct_count.cuh
index fc1f9d79a426..4983f4da7099 100644
--- a/cpp/include/cudf/reduction/detail/approx_distinct_count.cuh
+++ b/cpp/include/cudf/reduction/detail/approx_distinct_count.cuh
@@ -16,7 +16,7 @@
 #include <cuco/hyperloglog_ref.cuh>
 #include <cuda/functional>
 #include <cuda/std/span>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <cstddef>
 #include <cstdint>
diff --git a/cpp/include/cudf/reduction/detail/distinct_count.hpp b/cpp/include/cudf/reduction/detail/distinct_count.hpp
index 4e1ba98ae24d..3b7d42463a50 100644
--- a/cpp/include/cudf/reduction/detail/distinct_count.hpp
+++ b/cpp/include/cudf/reduction/detail/distinct_count.hpp
@@ -10,7 +10,7 @@
 #include <cudf/table/table_view.hpp>
 #include <cudf/types.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace detail {
diff --git a/cpp/include/cudf/reduction/detail/histogram.hpp b/cpp/include/cudf/reduction/detail/histogram.hpp
index cbf499913913..0f656d492117 100644
--- a/cpp/include/cudf/reduction/detail/histogram.hpp
+++ b/cpp/include/cudf/reduction/detail/histogram.hpp
@@ -13,7 +13,7 @@
 
 #include <rmm/device_uvector.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 #include <optional>
diff --git a/cpp/include/cudf/reduction/detail/reduction.cuh b/cpp/include/cudf/reduction/detail/reduction.cuh
index 39175ff3ed05..e1957ff4375f 100644
--- a/cpp/include/cudf/reduction/detail/reduction.cuh
+++ b/cpp/include/cudf/reduction/detail/reduction.cuh
@@ -18,7 +18,7 @@
 
 #include <cub/device/device_reduce.cuh>
 #include <cuda/std/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/for_each.h>
 
 #include <optional>
diff --git a/cpp/include/cudf/reduction/detail/reduction_functions.hpp b/cpp/include/cudf/reduction/detail/reduction_functions.hpp
index 23b906ca4882..50a02d889174 100644
--- a/cpp/include/cudf/reduction/detail/reduction_functions.hpp
+++ b/cpp/include/cudf/reduction/detail/reduction_functions.hpp
@@ -12,7 +12,7 @@
 #include <cudf/utilities/default_stream.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <optional>
 
diff --git a/cpp/include/cudf/reduction/detail/segmented_reduction.cuh b/cpp/include/cudf/reduction/detail/segmented_reduction.cuh
index 4b56011542bc..45d39db4cfce 100644
--- a/cpp/include/cudf/reduction/detail/segmented_reduction.cuh
+++ b/cpp/include/cudf/reduction/detail/segmented_reduction.cuh
@@ -15,7 +15,7 @@
 
 #include <cub/device/device_segmented_reduce.cuh>
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/transform.h>
 
 namespace cudf {
diff --git a/cpp/include/cudf/reduction/detail/segmented_reduction_functions.hpp b/cpp/include/cudf/reduction/detail/segmented_reduction_functions.hpp
index 483f9c3578b2..fcc7dccc293b 100644
--- a/cpp/include/cudf/reduction/detail/segmented_reduction_functions.hpp
+++ b/cpp/include/cudf/reduction/detail/segmented_reduction_functions.hpp
@@ -10,7 +10,7 @@
 #include <cudf/scalar/scalar.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <optional>
 
diff --git a/cpp/include/cudf/reduction/detail/unique_count.hpp b/cpp/include/cudf/reduction/detail/unique_count.hpp
index 47bbb3f151f9..1995ccd1fbf3 100644
--- a/cpp/include/cudf/reduction/detail/unique_count.hpp
+++ b/cpp/include/cudf/reduction/detail/unique_count.hpp
@@ -10,7 +10,7 @@
 #include <cudf/table/table_view.hpp>
 #include <cudf/types.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace detail {
diff --git a/cpp/include/cudf/reduction/distinct_count.hpp b/cpp/include/cudf/reduction/distinct_count.hpp
index 88014857f13e..1ca03f73d3db 100644
--- a/cpp/include/cudf/reduction/distinct_count.hpp
+++ b/cpp/include/cudf/reduction/distinct_count.hpp
@@ -11,7 +11,7 @@
 #include <cudf/utilities/default_stream.hpp>
 #include <cudf/utilities/export.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 /**
  * @file
diff --git a/cpp/include/cudf/reduction/unique_count.hpp b/cpp/include/cudf/reduction/unique_count.hpp
index 241e85956c9b..d4a21c10711c 100644
--- a/cpp/include/cudf/reduction/unique_count.hpp
+++ b/cpp/include/cudf/reduction/unique_count.hpp
@@ -11,7 +11,7 @@
 #include <cudf/utilities/default_stream.hpp>
 #include <cudf/utilities/export.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 /**
  * @file
diff --git a/cpp/include/cudf/scalar/scalar.hpp b/cpp/include/cudf/scalar/scalar.hpp
index 41cf9d879302..b12212c7039f 100644
--- a/cpp/include/cudf/scalar/scalar.hpp
+++ b/cpp/include/cudf/scalar/scalar.hpp
@@ -15,7 +15,7 @@
 #include <rmm/device_buffer.hpp>
 #include <rmm/device_scalar.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <span>
 #include <string_view>
diff --git a/cpp/include/cudf/scalar/scalar_factories.hpp b/cpp/include/cudf/scalar/scalar_factories.hpp
index 5a146c6dd879..633ee505cb73 100644
--- a/cpp/include/cudf/scalar/scalar_factories.hpp
+++ b/cpp/include/cudf/scalar/scalar_factories.hpp
@@ -10,7 +10,7 @@
 
 #include <rmm/cuda_stream_view.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <span>
 
diff --git a/cpp/include/cudf_test/column_utilities.hpp b/cpp/include/cudf_test/column_utilities.hpp
index e26f64f19586..1cbee8bdc645 100644
--- a/cpp/include/cudf_test/column_utilities.hpp
+++ b/cpp/include/cudf_test/column_utilities.hpp
@@ -18,7 +18,7 @@
 #include <cudf/utilities/export.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/host_vector.h>
 #include <thrust/iterator/transform_iterator.h>
 
diff --git a/cpp/include/cudf_test/memory_resource_utilities.hpp b/cpp/include/cudf_test/memory_resource_utilities.hpp
index 1ad81d7ef1eb..411b6a5c598a 100644
--- a/cpp/include/cudf_test/memory_resource_utilities.hpp
+++ b/cpp/include/cudf_test/memory_resource_utilities.hpp
@@ -16,7 +16,7 @@
 #include <rmm/resource_ref.hpp>
 
 #include <cuda/memory_resource>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <concepts>
 #include <cstddef>
diff --git a/cpp/include/cudf_test/stream_checking_resource_adaptor.hpp b/cpp/include/cudf_test/stream_checking_resource_adaptor.hpp
index 5849fb3e3041..d7115df0c666 100644
--- a/cpp/include/cudf_test/stream_checking_resource_adaptor.hpp
+++ b/cpp/include/cudf_test/stream_checking_resource_adaptor.hpp
@@ -1,5 +1,5 @@
 /*
- * SPDX-FileCopyrightText: Copyright (c) 2022-2026, NVIDIA CORPORATION.
+ * SPDX-FileCopyrightText: Copyright (c) 2022-2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
  * SPDX-License-Identifier: Apache-2.0
  */
 #pragma once
@@ -13,7 +13,7 @@
 #include <rmm/resource_ref.hpp>
 
 #include <cuda/memory_resource>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <cstddef>
 #include <iostream>
diff --git a/cpp/src/binaryop/binaryop.cpp b/cpp/src/binaryop/binaryop.cpp
index 899bcf9d1f97..c4d39655eb78 100644
--- a/cpp/src/binaryop/binaryop.cpp
+++ b/cpp/src/binaryop/binaryop.cpp
@@ -40,7 +40,7 @@
 #include <cudf/utilities/type_dispatcher.hpp>
 
 #include <cuda/std/optional>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <string>
 
diff --git a/cpp/src/binaryop/compiled/binary_ops.cu b/cpp/src/binaryop/compiled/binary_ops.cu
index e3d06fe998c8..0e639d90e95d 100644
--- a/cpp/src/binaryop/compiled/binary_ops.cu
+++ b/cpp/src/binaryop/compiled/binary_ops.cu
@@ -21,7 +21,7 @@
 
 #include <cuda/functional>
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/transform.h>
 
 namespace cudf {
diff --git a/cpp/src/binaryop/compiled/binary_ops.cuh b/cpp/src/binaryop/compiled/binary_ops.cuh
index 37d6ae31b3d4..556d336f5d68 100644
--- a/cpp/src/binaryop/compiled/binary_ops.cuh
+++ b/cpp/src/binaryop/compiled/binary_ops.cuh
@@ -18,7 +18,7 @@
 
 #include <cuda/iterator>
 #include <cuda/std/type_traits>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace binops {
diff --git a/cpp/src/binaryop/compiled/binary_ops.hpp b/cpp/src/binaryop/compiled/binary_ops.hpp
index 76b24620d1a6..d2e0d8865f47 100644
--- a/cpp/src/binaryop/compiled/binary_ops.hpp
+++ b/cpp/src/binaryop/compiled/binary_ops.hpp
@@ -10,7 +10,7 @@
 #include <cudf/utilities/default_stream.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <optional>
 
diff --git a/cpp/src/binaryop/compiled/struct_binary_ops.cuh b/cpp/src/binaryop/compiled/struct_binary_ops.cuh
index f8e752b8e6eb..07e313968755 100644
--- a/cpp/src/binaryop/compiled/struct_binary_ops.cuh
+++ b/cpp/src/binaryop/compiled/struct_binary_ops.cuh
@@ -18,7 +18,7 @@
 #include <rmm/exec_policy.hpp>
 
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/transform.h>
 
 namespace cudf::binops::compiled::detail {
diff --git a/cpp/src/bitmask/is_element_valid.cpp b/cpp/src/bitmask/is_element_valid.cpp
index 23848634f227..055576ff0131 100644
--- a/cpp/src/bitmask/is_element_valid.cpp
+++ b/cpp/src/bitmask/is_element_valid.cpp
@@ -8,7 +8,7 @@
 #include <cudf/utilities/bit.hpp>
 #include <cudf/utilities/error.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace detail {
diff --git a/cpp/src/bitmask/null_mask.cu b/cpp/src/bitmask/null_mask.cu
index 74d099156cdb..525a8d168c53 100644
--- a/cpp/src/bitmask/null_mask.cu
+++ b/cpp/src/bitmask/null_mask.cu
@@ -25,7 +25,7 @@
 #include <cub/cub.cuh>
 #include <cuda/atomic>
 #include <cuda/numeric>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/execution_policy.h>
 #include <thrust/tabulate.h>
 
diff --git a/cpp/src/column/column.cu b/cpp/src/column/column.cu
index 085fe0d9562c..37c223fba0b8 100644
--- a/cpp/src/column/column.cu
+++ b/cpp/src/column/column.cu
@@ -26,7 +26,7 @@
 
 #include <rmm/device_buffer.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/iterator/transform_iterator.h>
 
 #include <algorithm>
diff --git a/cpp/src/column/column_device_view.cu b/cpp/src/column/column_device_view.cu
index a46c0e442459..80e1247d3f89 100644
--- a/cpp/src/column/column_device_view.cu
+++ b/cpp/src/column/column_device_view.cu
@@ -9,7 +9,7 @@
 #include <cudf/types.hpp>
 #include <cudf/utilities/error.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <functional>
 #include <numeric>
diff --git a/cpp/src/copying/concatenate.cu b/cpp/src/copying/concatenate.cu
index 4ebd84072da3..52721b4f787b 100644
--- a/cpp/src/copying/concatenate.cu
+++ b/cpp/src/copying/concatenate.cu
@@ -31,7 +31,7 @@
 
 #include <cuda/iterator>
 #include <cuda/std/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/binary_search.h>
 #include <thrust/copy.h>
 #include <thrust/execution_policy.h>
diff --git a/cpp/src/copying/contiguous_split.cu b/cpp/src/copying/contiguous_split.cu
index 010e8d326aad..8fe81ff0a719 100644
--- a/cpp/src/copying/contiguous_split.cu
+++ b/cpp/src/copying/contiguous_split.cu
@@ -27,7 +27,7 @@
 #include <cuda/iterator>
 #include <cuda/std/functional>
 #include <cuda/std/utility>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/binary_search.h>
 #include <thrust/execution_policy.h>
 #include <thrust/for_each.h>
diff --git a/cpp/src/copying/copy.cpp b/cpp/src/copying/copy.cpp
index 1ec3bb93ca0b..9763ec2da222 100644
--- a/cpp/src/copying/copy.cpp
+++ b/cpp/src/copying/copy.cpp
@@ -12,7 +12,7 @@
 #include <cudf/table/table.hpp>
 #include <cudf/utilities/traits.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <algorithm>
 
diff --git a/cpp/src/copying/copy.cu b/cpp/src/copying/copy.cu
index 38d8c12bb4ad..391b6c59130a 100644
--- a/cpp/src/copying/copy.cu
+++ b/cpp/src/copying/copy.cu
@@ -23,7 +23,7 @@
 
 #include <cuda/iterator>
 #include <cuda/std/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <stdexcept>
 
diff --git a/cpp/src/copying/copy_range.cu b/cpp/src/copying/copy_range.cu
index a84ae741960b..0dd75c59b164 100644
--- a/cpp/src/copying/copy_range.cu
+++ b/cpp/src/copying/copy_range.cu
@@ -25,7 +25,7 @@
 #include <cudf/utilities/type_checks.hpp>
 
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 #include <stdexcept>
diff --git a/cpp/src/copying/gather.cu b/cpp/src/copying/gather.cu
index a43e662478a0..0e84a51261d8 100644
--- a/cpp/src/copying/gather.cu
+++ b/cpp/src/copying/gather.cu
@@ -15,7 +15,7 @@
 #include <cudf/utilities/memory_resource.hpp>
 
 #include <cuda/functional>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/iterator/transform_iterator.h>
 
 #include <stdexcept>
diff --git a/cpp/src/copying/get_element.cu b/cpp/src/copying/get_element.cu
index 3ff512d15465..4d9f2867dd76 100644
--- a/cpp/src/copying/get_element.cu
+++ b/cpp/src/copying/get_element.cu
@@ -19,7 +19,7 @@
 #include <cudf/utilities/default_stream.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <stdexcept>
 
diff --git a/cpp/src/copying/pack.cpp b/cpp/src/copying/pack.cpp
index 9cb3dc29ca30..dc199645a04f 100644
--- a/cpp/src/copying/pack.cpp
+++ b/cpp/src/copying/pack.cpp
@@ -7,7 +7,7 @@
 #include <cudf/detail/contiguous_split.hpp>
 #include <cudf/detail/nvtx/ranges.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <algorithm>
 #include <cstddef>
diff --git a/cpp/src/copying/reverse.cu b/cpp/src/copying/reverse.cu
index e0dae162d928..21870553f916 100644
--- a/cpp/src/copying/reverse.cu
+++ b/cpp/src/copying/reverse.cu
@@ -16,7 +16,7 @@
 #include <rmm/exec_policy.hpp>
 
 #include <cuda/functional>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/scan.h>
 
 namespace cudf {
diff --git a/cpp/src/copying/sample.cu b/cpp/src/copying/sample.cu
index 31e1ccba0000..45bfef011752 100644
--- a/cpp/src/copying/sample.cu
+++ b/cpp/src/copying/sample.cu
@@ -17,7 +17,7 @@
 
 #include <cuda/functional>
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/random.h>
 #include <thrust/random/uniform_int_distribution.h>
 #include <thrust/shuffle.h>
diff --git a/cpp/src/copying/scatter.cu b/cpp/src/copying/scatter.cu
index c8b10f15740c..bb2df3867e96 100644
--- a/cpp/src/copying/scatter.cu
+++ b/cpp/src/copying/scatter.cu
@@ -28,7 +28,7 @@
 
 #include <cuda/functional>
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/count.h>
 #include <thrust/iterator/transform_iterator.h>
 #include <thrust/scatter.h>
diff --git a/cpp/src/copying/segmented_shift.cu b/cpp/src/copying/segmented_shift.cu
index 0b6d52f8f2d0..e3453395d688 100644
--- a/cpp/src/copying/segmented_shift.cu
+++ b/cpp/src/copying/segmented_shift.cu
@@ -13,7 +13,7 @@
 #include <cudf/utilities/memory_resource.hpp>
 #include <cudf/utilities/traits.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/binary_search.h>
 #include <thrust/execution_policy.h>
 #include <thrust/iterator/transform_iterator.h>
diff --git a/cpp/src/copying/shift.cu b/cpp/src/copying/shift.cu
index 2a8834078505..7e7504248340 100644
--- a/cpp/src/copying/shift.cu
+++ b/cpp/src/copying/shift.cu
@@ -22,7 +22,7 @@
 #include <rmm/exec_policy.hpp>
 
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/copy.h>
 #include <thrust/transform.h>
 
diff --git a/cpp/src/copying/slice.cu b/cpp/src/copying/slice.cu
index a08d751ea33d..ffdfa31468a9 100644
--- a/cpp/src/copying/slice.cu
+++ b/cpp/src/copying/slice.cu
@@ -13,7 +13,7 @@
 #include <cudf/utilities/default_stream.hpp>
 #include <cudf/utilities/error.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/iterator/transform_iterator.h>
 
 #include <algorithm>
diff --git a/cpp/src/copying/split.cpp b/cpp/src/copying/split.cpp
index a75574f543d1..0914ebc90f1a 100644
--- a/cpp/src/copying/split.cpp
+++ b/cpp/src/copying/split.cpp
@@ -7,7 +7,7 @@
 #include <cudf/detail/nvtx/ranges.hpp>
 #include <cudf/utilities/error.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <algorithm>
 #include <stdexcept>
diff --git a/cpp/src/dictionary/decode.cu b/cpp/src/dictionary/decode.cu
index 0338a939ed7d..1f54b62843ff 100644
--- a/cpp/src/dictionary/decode.cu
+++ b/cpp/src/dictionary/decode.cu
@@ -14,7 +14,7 @@
 #include <cudf/utilities/default_stream.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace dictionary {
diff --git a/cpp/src/dictionary/detail/concatenate.cu b/cpp/src/dictionary/detail/concatenate.cu
index e3e428c14ace..1159c63852a9 100644
--- a/cpp/src/dictionary/detail/concatenate.cu
+++ b/cpp/src/dictionary/detail/concatenate.cu
@@ -29,7 +29,7 @@
 #include <cuda/functional>
 #include <cuda/iterator>
 #include <cuda/std/utility>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/binary_search.h>
 #include <thrust/execution_policy.h>
 #include <thrust/gather.h>
diff --git a/cpp/src/dictionary/detail/merge.cu b/cpp/src/dictionary/detail/merge.cu
index d946c68bcdf8..24af7b510329 100644
--- a/cpp/src/dictionary/detail/merge.cu
+++ b/cpp/src/dictionary/detail/merge.cu
@@ -15,7 +15,7 @@
 
 #include <rmm/exec_policy.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/transform.h>
 
 namespace cudf {
diff --git a/cpp/src/dictionary/dictionary_factories.cu b/cpp/src/dictionary/dictionary_factories.cu
index 05df8d36b3fd..af733284b20a 100644
--- a/cpp/src/dictionary/dictionary_factories.cu
+++ b/cpp/src/dictionary/dictionary_factories.cu
@@ -12,7 +12,7 @@
 #include <cudf/utilities/memory_resource.hpp>
 #include <cudf/utilities/type_dispatcher.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace {
diff --git a/cpp/src/dictionary/encode.cu b/cpp/src/dictionary/encode.cu
index 7f43eb337370..b3dd4ce3c5af 100644
--- a/cpp/src/dictionary/encode.cu
+++ b/cpp/src/dictionary/encode.cu
@@ -31,7 +31,7 @@
 #include <cuco/static_set.cuh>
 #include <cuda/iterator>
 #include <cuda/std/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/binary_search.h>
 #include <thrust/sort.h>
 #include <thrust/transform.h>
diff --git a/cpp/src/dictionary/match_keys.cu b/cpp/src/dictionary/match_keys.cu
index 269cb403998c..f86559ed7181 100644
--- a/cpp/src/dictionary/match_keys.cu
+++ b/cpp/src/dictionary/match_keys.cu
@@ -25,7 +25,7 @@
 #include <cuco/static_set.cuh>
 #include <cuda/iterator>
 #include <cuda/std/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <algorithm>
 #include <iterator>
diff --git a/cpp/src/dictionary/remove_keys.cu b/cpp/src/dictionary/remove_keys.cu
index 7ae4826b6a3d..654f2726be74 100644
--- a/cpp/src/dictionary/remove_keys.cu
+++ b/cpp/src/dictionary/remove_keys.cu
@@ -23,7 +23,7 @@
 #include <rmm/exec_policy.hpp>
 
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/fill.h>
 #include <thrust/scatter.h>
 #include <thrust/sequence.h>
diff --git a/cpp/src/dictionary/replace.cu b/cpp/src/dictionary/replace.cu
index 24d007647087..f4697b167909 100644
--- a/cpp/src/dictionary/replace.cu
+++ b/cpp/src/dictionary/replace.cu
@@ -17,7 +17,7 @@
 #include <cudf/utilities/memory_resource.hpp>
 #include <cudf/utilities/type_checks.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace dictionary {
diff --git a/cpp/src/dictionary/search.cu b/cpp/src/dictionary/search.cu
index d0e868572907..3d90c811d443 100644
--- a/cpp/src/dictionary/search.cu
+++ b/cpp/src/dictionary/search.cu
@@ -16,7 +16,7 @@
 #include <cudf/utilities/type_dispatcher.hpp>
 
 #include <cub/device/device_find.cuh>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace dictionary {
diff --git a/cpp/src/dictionary/set_keys.cu b/cpp/src/dictionary/set_keys.cu
index 04475f2bbcdb..a4aec50705e7 100644
--- a/cpp/src/dictionary/set_keys.cu
+++ b/cpp/src/dictionary/set_keys.cu
@@ -26,7 +26,7 @@
 
 #include <cuda/iterator>
 #include <cuda/std/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/binary_search.h>
 #include <thrust/execution_policy.h>
 #include <thrust/transform.h>
diff --git a/cpp/src/filling/calendrical_month_sequence.cu b/cpp/src/filling/calendrical_month_sequence.cu
index b020b4817701..30dd9a36aac3 100644
--- a/cpp/src/filling/calendrical_month_sequence.cu
+++ b/cpp/src/filling/calendrical_month_sequence.cu
@@ -14,7 +14,7 @@
 
 #include <rmm/exec_policy.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace detail {
diff --git a/cpp/src/filling/fill.cu b/cpp/src/filling/fill.cu
index fb80d3e67113..5da1423438a9 100644
--- a/cpp/src/filling/fill.cu
+++ b/cpp/src/filling/fill.cu
@@ -26,7 +26,7 @@
 #include <cudf/utilities/type_checks.hpp>
 
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 
diff --git a/cpp/src/filling/repeat.cu b/cpp/src/filling/repeat.cu
index 8d328ae581f9..8e53c90dc9ab 100644
--- a/cpp/src/filling/repeat.cu
+++ b/cpp/src/filling/repeat.cu
@@ -24,7 +24,7 @@
 
 #include <cuda/functional>
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/binary_search.h>
 #include <thrust/reduce.h>
 #include <thrust/scan.h>
diff --git a/cpp/src/filling/sequence.cu b/cpp/src/filling/sequence.cu
index 67f66b908470..0af4d908bb48 100644
--- a/cpp/src/filling/sequence.cu
+++ b/cpp/src/filling/sequence.cu
@@ -19,7 +19,7 @@
 
 #include <rmm/exec_policy.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/sequence.h>
 #include <thrust/tabulate.h>
 
diff --git a/cpp/src/groupby/common/m2_var_std.cu b/cpp/src/groupby/common/m2_var_std.cu
index 596be8c49004..50b2bccfbc50 100644
--- a/cpp/src/groupby/common/m2_var_std.cu
+++ b/cpp/src/groupby/common/m2_var_std.cu
@@ -17,7 +17,7 @@
 #include <cuda/iterator>
 #include <cuda/std/cmath>
 #include <cuda/std/functional>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/tabulate.h>
 
 namespace cudf::groupby::detail {
diff --git a/cpp/src/groupby/common/m2_var_std.hpp b/cpp/src/groupby/common/m2_var_std.hpp
index 704c2a23d057..645791b94471 100644
--- a/cpp/src/groupby/common/m2_var_std.hpp
+++ b/cpp/src/groupby/common/m2_var_std.hpp
@@ -10,7 +10,7 @@
 
 #include <rmm/resource_ref.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf::groupby::detail {
 
diff --git a/cpp/src/groupby/common/utils.hpp b/cpp/src/groupby/common/utils.hpp
index 1709ff535527..a88258a9376c 100644
--- a/cpp/src/groupby/common/utils.hpp
+++ b/cpp/src/groupby/common/utils.hpp
@@ -15,7 +15,7 @@
 
 #include <rmm/device_buffer.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 #include <span>
diff --git a/cpp/src/groupby/groupby.cu b/cpp/src/groupby/groupby.cu
index 6daf81a403ba..da265ee8909f 100644
--- a/cpp/src/groupby/groupby.cu
+++ b/cpp/src/groupby/groupby.cu
@@ -28,7 +28,7 @@
 #include <cudf/utilities/type_checks.hpp>
 
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 #include <utility>
diff --git a/cpp/src/groupby/hash/compute_global_memory_aggs.cuh b/cpp/src/groupby/hash/compute_global_memory_aggs.cuh
index 9a74369d35b7..1fdce3089bac 100644
--- a/cpp/src/groupby/hash/compute_global_memory_aggs.cuh
+++ b/cpp/src/groupby/hash/compute_global_memory_aggs.cuh
@@ -15,7 +15,7 @@
 #include <rmm/exec_policy.hpp>
 
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/for_each.h>
 #include <thrust/transform.h>
 
diff --git a/cpp/src/groupby/hash/compute_global_memory_aggs.hpp b/cpp/src/groupby/hash/compute_global_memory_aggs.hpp
index 01a163d886c1..c3b3367ed79f 100644
--- a/cpp/src/groupby/hash/compute_global_memory_aggs.hpp
+++ b/cpp/src/groupby/hash/compute_global_memory_aggs.hpp
@@ -11,7 +11,7 @@
 
 #include <rmm/resource_ref.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <cstdint>
 #include <memory>
diff --git a/cpp/src/groupby/hash/compute_groupby.cu b/cpp/src/groupby/hash/compute_groupby.cu
index 32c575a407d8..c06aaa6aa2f8 100644
--- a/cpp/src/groupby/hash/compute_groupby.cu
+++ b/cpp/src/groupby/hash/compute_groupby.cu
@@ -23,7 +23,7 @@
 #include <cuco/static_set.cuh>
 #include <cuda/iterator>
 #include <cuda/std/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/tabulate.h>
 
 namespace cudf::groupby::detail::hash {
diff --git a/cpp/src/groupby/hash/compute_groupby.hpp b/cpp/src/groupby/hash/compute_groupby.hpp
index c2e3e657e349..923536b8e7fb 100644
--- a/cpp/src/groupby/hash/compute_groupby.hpp
+++ b/cpp/src/groupby/hash/compute_groupby.hpp
@@ -12,7 +12,7 @@
 
 #include <rmm/resource_ref.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 
diff --git a/cpp/src/groupby/hash/compute_mapping_indices.cuh b/cpp/src/groupby/hash/compute_mapping_indices.cuh
index f3d929e9a7c0..dff18f512834 100644
--- a/cpp/src/groupby/hash/compute_mapping_indices.cuh
+++ b/cpp/src/groupby/hash/compute_mapping_indices.cuh
@@ -15,7 +15,7 @@
 #include <cooperative_groups.h>
 #include <cuco/static_set_ref.cuh>
 #include <cuda/std/atomic>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <algorithm>
 
diff --git a/cpp/src/groupby/hash/compute_mapping_indices.hpp b/cpp/src/groupby/hash/compute_mapping_indices.hpp
index fcda23b92fcb..be098275dcc7 100644
--- a/cpp/src/groupby/hash/compute_mapping_indices.hpp
+++ b/cpp/src/groupby/hash/compute_mapping_indices.hpp
@@ -7,7 +7,7 @@
 #include <cudf/types.hpp>
 
 #include <cuda/std/atomic>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf::groupby::detail::hash {
 
diff --git a/cpp/src/groupby/hash/compute_shared_memory_aggs.cu b/cpp/src/groupby/hash/compute_shared_memory_aggs.cu
index 54b8f3a02807..b97de8e9b378 100644
--- a/cpp/src/groupby/hash/compute_shared_memory_aggs.cu
+++ b/cpp/src/groupby/hash/compute_shared_memory_aggs.cu
@@ -26,7 +26,7 @@
 #include <cuda/std/cstddef>
 #include <cuda/std/type_traits>
 #include <cuda/std/utility>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <cstddef>
 #include <cstdint>
diff --git a/cpp/src/groupby/hash/compute_shared_memory_aggs.hpp b/cpp/src/groupby/hash/compute_shared_memory_aggs.hpp
index b3ffaefe605d..9a9645008c33 100644
--- a/cpp/src/groupby/hash/compute_shared_memory_aggs.hpp
+++ b/cpp/src/groupby/hash/compute_shared_memory_aggs.hpp
@@ -8,7 +8,7 @@
 #include <cudf/table/table_device_view.cuh>
 #include <cudf/types.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <cstdint>
 
diff --git a/cpp/src/groupby/hash/compute_single_pass_aggs.cuh b/cpp/src/groupby/hash/compute_single_pass_aggs.cuh
index 431043ace3b8..fd248138fabf 100644
--- a/cpp/src/groupby/hash/compute_single_pass_aggs.cuh
+++ b/cpp/src/groupby/hash/compute_single_pass_aggs.cuh
@@ -23,7 +23,7 @@
 
 #include <cuco/static_set.cuh>
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/for_each.h>
 
 namespace cudf::groupby::detail::hash {
diff --git a/cpp/src/groupby/hash/compute_single_pass_aggs.hpp b/cpp/src/groupby/hash/compute_single_pass_aggs.hpp
index 51ff564e90d2..122750ff5de0 100644
--- a/cpp/src/groupby/hash/compute_single_pass_aggs.hpp
+++ b/cpp/src/groupby/hash/compute_single_pass_aggs.hpp
@@ -11,7 +11,7 @@
 
 #include <rmm/device_uvector.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf::groupby::detail::hash {
 
diff --git a/cpp/src/groupby/hash/groupby.cu b/cpp/src/groupby/hash/groupby.cu
index 207b8a7b7225..8b9a778cba91 100644
--- a/cpp/src/groupby/hash/groupby.cu
+++ b/cpp/src/groupby/hash/groupby.cu
@@ -21,7 +21,7 @@
 #include <cudf/utilities/traits.cuh>
 #include <cudf/utilities/traits.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 #include <utility>
diff --git a/cpp/src/groupby/hash/hash_compound_agg_finalizer.cu b/cpp/src/groupby/hash/hash_compound_agg_finalizer.cu
index 3ed04e31068b..48970b03d067 100644
--- a/cpp/src/groupby/hash/hash_compound_agg_finalizer.cu
+++ b/cpp/src/groupby/hash/hash_compound_agg_finalizer.cu
@@ -17,7 +17,7 @@
 #include <cudf/dictionary/dictionary_column_view.hpp>
 #include <cudf/types.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf::groupby::detail::hash {
 
diff --git a/cpp/src/groupby/hash/output_utils.cu b/cpp/src/groupby/hash/output_utils.cu
index 613961b51bf2..0f8e0d9265de 100644
--- a/cpp/src/groupby/hash/output_utils.cu
+++ b/cpp/src/groupby/hash/output_utils.cu
@@ -22,7 +22,7 @@
 
 #include <cuco/static_set.cuh>
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/scatter.h>
 #include <thrust/transform.h>
 
diff --git a/cpp/src/groupby/hash/output_utils.hpp b/cpp/src/groupby/hash/output_utils.hpp
index e4607e181ba1..97f0dcf98e27 100644
--- a/cpp/src/groupby/hash/output_utils.hpp
+++ b/cpp/src/groupby/hash/output_utils.hpp
@@ -14,7 +14,7 @@
 
 #include <rmm/device_uvector.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <cstdint>
 #include <memory>
diff --git a/cpp/src/groupby/sort/aggregate.cpp b/cpp/src/groupby/sort/aggregate.cpp
index a10c73206eff..77e0d1c160cd 100644
--- a/cpp/src/groupby/sort/aggregate.cpp
+++ b/cpp/src/groupby/sort/aggregate.cpp
@@ -26,7 +26,7 @@
 #include <cudf/types.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 #include <unordered_map>
diff --git a/cpp/src/groupby/sort/functors.hpp b/cpp/src/groupby/sort/functors.hpp
index 6d1d79815bde..cc1925a2d037 100644
--- a/cpp/src/groupby/sort/functors.hpp
+++ b/cpp/src/groupby/sort/functors.hpp
@@ -11,7 +11,7 @@
 #include <cudf/types.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 
diff --git a/cpp/src/groupby/sort/group_argmax.cu b/cpp/src/groupby/sort/group_argmax.cu
index 9d8b3f43a7ff..e2e570748b43 100644
--- a/cpp/src/groupby/sort/group_argmax.cu
+++ b/cpp/src/groupby/sort/group_argmax.cu
@@ -9,7 +9,7 @@
 #include <cudf/utilities/memory_resource.hpp>
 #include <cudf/utilities/span.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/gather.h>
 
 namespace cudf {
diff --git a/cpp/src/groupby/sort/group_argmin.cu b/cpp/src/groupby/sort/group_argmin.cu
index 171f78043a56..4d264c95c8b2 100644
--- a/cpp/src/groupby/sort/group_argmin.cu
+++ b/cpp/src/groupby/sort/group_argmin.cu
@@ -11,7 +11,7 @@
 
 #include <rmm/device_uvector.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/gather.h>
 
 namespace cudf {
diff --git a/cpp/src/groupby/sort/group_bitwise.cu b/cpp/src/groupby/sort/group_bitwise.cu
index 860328a31599..95604e569517 100644
--- a/cpp/src/groupby/sort/group_bitwise.cu
+++ b/cpp/src/groupby/sort/group_bitwise.cu
@@ -18,7 +18,7 @@
 
 #include <cuda/iterator>
 #include <cuda/std/functional>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf::groupby::detail {
 
diff --git a/cpp/src/groupby/sort/group_collect.cu b/cpp/src/groupby/sort/group_collect.cu
index d4dc1dce7d36..1f2a96b24705 100644
--- a/cpp/src/groupby/sort/group_collect.cu
+++ b/cpp/src/groupby/sort/group_collect.cu
@@ -13,7 +13,7 @@
 #include <cudf/utilities/span.hpp>
 
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/copy.h>
 #include <thrust/count.h>
 #include <thrust/execution_policy.h>
diff --git a/cpp/src/groupby/sort/group_correlation.cu b/cpp/src/groupby/sort/group_correlation.cu
index 1799c1179fcf..332382e9576f 100644
--- a/cpp/src/groupby/sort/group_correlation.cu
+++ b/cpp/src/groupby/sort/group_correlation.cu
@@ -20,7 +20,7 @@
 
 #include <cuda/iterator>
 #include <cuda/std/tuple>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/transform.h>
 
 #include <type_traits>
diff --git a/cpp/src/groupby/sort/group_count.cu b/cpp/src/groupby/sort/group_count.cu
index f9e7a11f52c0..c697c76d774b 100644
--- a/cpp/src/groupby/sort/group_count.cu
+++ b/cpp/src/groupby/sort/group_count.cu
@@ -15,7 +15,7 @@
 
 #include <cuda/functional>
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/adjacent_difference.h>
 #include <thrust/iterator/transform_iterator.h>
 
diff --git a/cpp/src/groupby/sort/group_count_scan.cu b/cpp/src/groupby/sort/group_count_scan.cu
index be4eab3c7ef5..ae56da9d8c61 100644
--- a/cpp/src/groupby/sort/group_count_scan.cu
+++ b/cpp/src/groupby/sort/group_count_scan.cu
@@ -15,7 +15,7 @@
 #include <rmm/exec_policy.hpp>
 
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/scan.h>
 
 namespace cudf {
diff --git a/cpp/src/groupby/sort/group_m2.cu b/cpp/src/groupby/sort/group_m2.cu
index b4743be597d9..acd3a34245b2 100644
--- a/cpp/src/groupby/sort/group_m2.cu
+++ b/cpp/src/groupby/sort/group_m2.cu
@@ -19,7 +19,7 @@
 #include <rmm/exec_policy.hpp>
 
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/transform.h>
 
 namespace cudf {
diff --git a/cpp/src/groupby/sort/group_max.cu b/cpp/src/groupby/sort/group_max.cu
index 6a2b3edfec95..c2b0dceee04a 100644
--- a/cpp/src/groupby/sort/group_max.cu
+++ b/cpp/src/groupby/sort/group_max.cu
@@ -7,7 +7,7 @@
 
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace groupby {
diff --git a/cpp/src/groupby/sort/group_max_scan.cu b/cpp/src/groupby/sort/group_max_scan.cu
index 8f58f4f514c8..664248411c83 100644
--- a/cpp/src/groupby/sort/group_max_scan.cu
+++ b/cpp/src/groupby/sort/group_max_scan.cu
@@ -7,7 +7,7 @@
 
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace groupby {
diff --git a/cpp/src/groupby/sort/group_merge_lists.cu b/cpp/src/groupby/sort/group_merge_lists.cu
index 8fc75c9f2fe3..17f94458f7cd 100644
--- a/cpp/src/groupby/sort/group_merge_lists.cu
+++ b/cpp/src/groupby/sort/group_merge_lists.cu
@@ -10,7 +10,7 @@
 
 #include <rmm/exec_policy.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/gather.h>
 
 namespace cudf {
diff --git a/cpp/src/groupby/sort/group_merge_m2.cu b/cpp/src/groupby/sort/group_merge_m2.cu
index aba53e492080..c01dd53fe011 100644
--- a/cpp/src/groupby/sort/group_merge_m2.cu
+++ b/cpp/src/groupby/sort/group_merge_m2.cu
@@ -12,7 +12,7 @@
 
 #include <cuda/iterator>
 #include <cuda/std/tuple>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/transform.h>
 
 namespace cudf {
diff --git a/cpp/src/groupby/sort/group_min.cu b/cpp/src/groupby/sort/group_min.cu
index fd423967018a..6b1b53245516 100644
--- a/cpp/src/groupby/sort/group_min.cu
+++ b/cpp/src/groupby/sort/group_min.cu
@@ -7,7 +7,7 @@
 
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace groupby {
diff --git a/cpp/src/groupby/sort/group_min_scan.cu b/cpp/src/groupby/sort/group_min_scan.cu
index e7cffe59014a..2ef20dcec0fa 100644
--- a/cpp/src/groupby/sort/group_min_scan.cu
+++ b/cpp/src/groupby/sort/group_min_scan.cu
@@ -7,7 +7,7 @@
 
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace groupby {
diff --git a/cpp/src/groupby/sort/group_nth_element.cu b/cpp/src/groupby/sort/group_nth_element.cu
index 0fbe013f91a4..ee992e9f29b8 100644
--- a/cpp/src/groupby/sort/group_nth_element.cu
+++ b/cpp/src/groupby/sort/group_nth_element.cu
@@ -19,7 +19,7 @@
 
 #include <cuda/functional>
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/iterator/transform_iterator.h>
 #include <thrust/scan.h>
 #include <thrust/scatter.h>
diff --git a/cpp/src/groupby/sort/group_nunique.cu b/cpp/src/groupby/sort/group_nunique.cu
index 160755cb3018..e3a54734c6d9 100644
--- a/cpp/src/groupby/sort/group_nunique.cu
+++ b/cpp/src/groupby/sort/group_nunique.cu
@@ -14,7 +14,7 @@
 #include <rmm/exec_policy.hpp>
 
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/iterator/transform_iterator.h>
 
 namespace cudf {
diff --git a/cpp/src/groupby/sort/group_product.cu b/cpp/src/groupby/sort/group_product.cu
index ebee7f4e49e0..c6813f374111 100644
--- a/cpp/src/groupby/sort/group_product.cu
+++ b/cpp/src/groupby/sort/group_product.cu
@@ -9,7 +9,7 @@
 #include <cudf/utilities/memory_resource.hpp>
 #include <cudf/utilities/span.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace groupby {
diff --git a/cpp/src/groupby/sort/group_product_scan.cu b/cpp/src/groupby/sort/group_product_scan.cu
index a2e28d543939..d7ca44cec9c1 100644
--- a/cpp/src/groupby/sort/group_product_scan.cu
+++ b/cpp/src/groupby/sort/group_product_scan.cu
@@ -7,7 +7,7 @@
 
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace groupby {
diff --git a/cpp/src/groupby/sort/group_quantiles.cu b/cpp/src/groupby/sort/group_quantiles.cu
index f0044dec93b7..24b82535c3bb 100644
--- a/cpp/src/groupby/sort/group_quantiles.cu
+++ b/cpp/src/groupby/sort/group_quantiles.cu
@@ -21,7 +21,7 @@
 #include <rmm/exec_policy.hpp>
 
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/execution_policy.h>
 #include <thrust/for_each.h>
 #include <thrust/transform.h>
diff --git a/cpp/src/groupby/sort/group_rank_scan.cu b/cpp/src/groupby/sort/group_rank_scan.cu
index f4661a0baa1c..6762942ae4f3 100644
--- a/cpp/src/groupby/sort/group_rank_scan.cu
+++ b/cpp/src/groupby/sort/group_rank_scan.cu
@@ -22,7 +22,7 @@
 #include <cuda/std/iterator>
 #include <cuda/std/limits>
 #include <cuda/std/utility>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/scan.h>
 #include <thrust/transform.h>
 
diff --git a/cpp/src/groupby/sort/group_reductions.hpp b/cpp/src/groupby/sort/group_reductions.hpp
index 94c7312b65b0..f41c66c92a52 100644
--- a/cpp/src/groupby/sort/group_reductions.hpp
+++ b/cpp/src/groupby/sort/group_reductions.hpp
@@ -10,7 +10,7 @@
 #include <cudf/utilities/memory_resource.hpp>
 #include <cudf/utilities/span.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 
diff --git a/cpp/src/groupby/sort/group_scan.hpp b/cpp/src/groupby/sort/group_scan.hpp
index 53000b9c8aac..e6b96c19f3fc 100644
--- a/cpp/src/groupby/sort/group_scan.hpp
+++ b/cpp/src/groupby/sort/group_scan.hpp
@@ -10,7 +10,7 @@
 #include <cudf/utilities/memory_resource.hpp>
 #include <cudf/utilities/span.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 
diff --git a/cpp/src/groupby/sort/group_scan_util.cuh b/cpp/src/groupby/sort/group_scan_util.cuh
index ab92b7b6fbde..961e124ae9f4 100644
--- a/cpp/src/groupby/sort/group_scan_util.cuh
+++ b/cpp/src/groupby/sort/group_scan_util.cuh
@@ -27,7 +27,7 @@
 
 #include <cuda/iterator>
 #include <cuda/std/functional>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/iterator/transform_iterator.h>
 #include <thrust/scan.h>
 
diff --git a/cpp/src/groupby/sort/group_single_pass_reduction_util.cuh b/cpp/src/groupby/sort/group_single_pass_reduction_util.cuh
index fd297a2d78e3..c350ee718804 100644
--- a/cpp/src/groupby/sort/group_single_pass_reduction_util.cuh
+++ b/cpp/src/groupby/sort/group_single_pass_reduction_util.cuh
@@ -23,7 +23,7 @@
 
 #include <cuda/iterator>
 #include <cuda/std/functional>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/reduce.h>
 
 namespace cudf {
diff --git a/cpp/src/groupby/sort/group_std.cu b/cpp/src/groupby/sort/group_std.cu
index a055cfb33581..e75069b97481 100644
--- a/cpp/src/groupby/sort/group_std.cu
+++ b/cpp/src/groupby/sort/group_std.cu
@@ -21,7 +21,7 @@
 #include <rmm/exec_policy.hpp>
 
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/for_each.h>
 #include <thrust/iterator/transform_iterator.h>
 #include <thrust/transform.h>
diff --git a/cpp/src/groupby/sort/group_sum.cu b/cpp/src/groupby/sort/group_sum.cu
index 9787cbf1b24a..830bb65ae516 100644
--- a/cpp/src/groupby/sort/group_sum.cu
+++ b/cpp/src/groupby/sort/group_sum.cu
@@ -9,7 +9,7 @@
 #include <cudf/utilities/memory_resource.hpp>
 #include <cudf/utilities/span.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace groupby {
diff --git a/cpp/src/groupby/sort/group_sum_overflow.cu b/cpp/src/groupby/sort/group_sum_overflow.cu
index cc7e2c94d5c2..9e1e22b40b0a 100644
--- a/cpp/src/groupby/sort/group_sum_overflow.cu
+++ b/cpp/src/groupby/sort/group_sum_overflow.cu
@@ -23,7 +23,7 @@
 #include <cuda/iterator>
 #include <cuda/std/functional>
 #include <cuda/std/tuple>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/reduce.h>
 
 #include <memory>
diff --git a/cpp/src/groupby/sort/group_sum_scan.cu b/cpp/src/groupby/sort/group_sum_scan.cu
index 14870bdd07a0..b8b25fb1bdc4 100644
--- a/cpp/src/groupby/sort/group_sum_scan.cu
+++ b/cpp/src/groupby/sort/group_sum_scan.cu
@@ -7,7 +7,7 @@
 
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace groupby {
diff --git a/cpp/src/groupby/sort/group_topk.cu b/cpp/src/groupby/sort/group_topk.cu
index f89144d7411c..b088b2c7fb2e 100644
--- a/cpp/src/groupby/sort/group_topk.cu
+++ b/cpp/src/groupby/sort/group_topk.cu
@@ -9,7 +9,7 @@
 #include <cudf/types.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 
diff --git a/cpp/src/groupby/sort/scan.cpp b/cpp/src/groupby/sort/scan.cpp
index 340365fa7a28..772cf18e28ab 100644
--- a/cpp/src/groupby/sort/scan.cpp
+++ b/cpp/src/groupby/sort/scan.cpp
@@ -24,7 +24,7 @@
 #include <cudf/utilities/error.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 
diff --git a/cpp/src/groupby/sort/sort_helper.cu b/cpp/src/groupby/sort/sort_helper.cu
index f5aeeffdb026..e664702dc6d7 100644
--- a/cpp/src/groupby/sort/sort_helper.cu
+++ b/cpp/src/groupby/sort/sort_helper.cu
@@ -23,7 +23,7 @@
 #include <rmm/device_uvector.hpp>
 #include <rmm/exec_policy.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/transform.h>
 
 #include <algorithm>
diff --git a/cpp/src/groupby/sort/sort_helper_group_offsets.cuh b/cpp/src/groupby/sort/sort_helper_group_offsets.cuh
index 4310d9114cb5..dd2e32d54165 100644
--- a/cpp/src/groupby/sort/sort_helper_group_offsets.cuh
+++ b/cpp/src/groupby/sort/sort_helper_group_offsets.cuh
@@ -20,7 +20,7 @@
 #include <cuda/functional>
 #include <cuda/iterator>
 #include <cuda/std/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/transform.h>
 
 namespace cudf::groupby::detail::sort {
diff --git a/cpp/src/groupby/streaming_groupby.cpp b/cpp/src/groupby/streaming_groupby.cpp
index a3667395f000..cba537e29fcf 100644
--- a/cpp/src/groupby/streaming_groupby.cpp
+++ b/cpp/src/groupby/streaming_groupby.cpp
@@ -10,7 +10,7 @@
 #include <cudf/table/table_view.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 #include <utility>
diff --git a/cpp/src/groupby/streaming_groupby/aggregate.cu b/cpp/src/groupby/streaming_groupby/aggregate.cu
index 702be6d794e0..96699895d603 100644
--- a/cpp/src/groupby/streaming_groupby/aggregate.cu
+++ b/cpp/src/groupby/streaming_groupby/aggregate.cu
@@ -13,7 +13,7 @@
 #include <rmm/exec_policy.hpp>
 
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/for_each.h>
 
 #include <limits>
diff --git a/cpp/src/groupby/streaming_groupby/common.cuh b/cpp/src/groupby/streaming_groupby/common.cuh
index 251ce33f0b70..259a655e86ac 100644
--- a/cpp/src/groupby/streaming_groupby/common.cuh
+++ b/cpp/src/groupby/streaming_groupby/common.cuh
@@ -24,7 +24,7 @@
 #include <cuco/static_set.cuh>
 #include <cuda/std/functional>
 #include <cuda/std/utility>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 #include <vector>
diff --git a/cpp/src/groupby/streaming_groupby/impl.cu b/cpp/src/groupby/streaming_groupby/impl.cu
index 49e2207955f7..f7d13d97714c 100644
--- a/cpp/src/groupby/streaming_groupby/impl.cu
+++ b/cpp/src/groupby/streaming_groupby/impl.cu
@@ -25,7 +25,7 @@
 
 #include <rmm/device_uvector.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <algorithm>
 #include <memory>
diff --git a/cpp/src/groupby/streaming_groupby/insert.cuh b/cpp/src/groupby/streaming_groupby/insert.cuh
index d5e7de800453..90be7c533ae9 100644
--- a/cpp/src/groupby/streaming_groupby/insert.cuh
+++ b/cpp/src/groupby/streaming_groupby/insert.cuh
@@ -17,7 +17,7 @@
 #include <rmm/exec_policy.hpp>
 
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/for_each.h>
 #include <thrust/transform.h>
 
diff --git a/cpp/src/groupby/streaming_groupby/insert_first.cuh b/cpp/src/groupby/streaming_groupby/insert_first.cuh
index a9e8e9f3af49..25c6ac2a45d2 100644
--- a/cpp/src/groupby/streaming_groupby/insert_first.cuh
+++ b/cpp/src/groupby/streaming_groupby/insert_first.cuh
@@ -15,7 +15,7 @@
 #include <rmm/exec_policy.hpp>
 
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/copy.h>
 
 #include <cstddef>
diff --git a/cpp/src/groupby/streaming_groupby/insert_subsequent.cuh b/cpp/src/groupby/streaming_groupby/insert_subsequent.cuh
index eae56e4549ef..9b2a741b3de2 100644
--- a/cpp/src/groupby/streaming_groupby/insert_subsequent.cuh
+++ b/cpp/src/groupby/streaming_groupby/insert_subsequent.cuh
@@ -12,7 +12,7 @@
 #include <rmm/exec_policy.hpp>
 
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/copy.h>
 
 namespace cudf::groupby {
diff --git a/cpp/src/groupby/streaming_groupby/merge.cu b/cpp/src/groupby/streaming_groupby/merge.cu
index 67c05fc176ce..a4fcab2576ac 100644
--- a/cpp/src/groupby/streaming_groupby/merge.cu
+++ b/cpp/src/groupby/streaming_groupby/merge.cu
@@ -15,7 +15,7 @@
 #include <rmm/exec_policy.hpp>
 
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/for_each.h>
 
 #include <string>
diff --git a/cpp/src/join/conditional_join.cu b/cpp/src/join/conditional_join.cu
index 0019ae67bde1..96795e03d511 100644
--- a/cpp/src/join/conditional_join.cu
+++ b/cpp/src/join/conditional_join.cu
@@ -20,7 +20,7 @@
 #include <cudf/utilities/error.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <optional>
 #include <vector>
diff --git a/cpp/src/join/conditional_join.hpp b/cpp/src/join/conditional_join.hpp
index 7d66e340ade0..821ff5cf7258 100644
--- a/cpp/src/join/conditional_join.hpp
+++ b/cpp/src/join/conditional_join.hpp
@@ -11,7 +11,7 @@
 #include <cudf/table/table_view.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <optional>
 
diff --git a/cpp/src/join/cross_join.cu b/cpp/src/join/cross_join.cu
index c0b85a533fc3..bcf63f3b06b4 100644
--- a/cpp/src/join/cross_join.cu
+++ b/cpp/src/join/cross_join.cu
@@ -17,7 +17,7 @@
 #include <cudf/utilities/error.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <cstdint>
 #include <limits>
diff --git a/cpp/src/join/direct_join.cu b/cpp/src/join/direct_join.cu
index 5750e6f5fdd7..2673ee2771a6 100644
--- a/cpp/src/join/direct_join.cu
+++ b/cpp/src/join/direct_join.cu
@@ -18,7 +18,7 @@
 #include <cub/device/device_transform.cuh>
 #include <cuda/iterator>
 #include <cuda/std/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <cstdint>
 #include <memory>
diff --git a/cpp/src/join/distinct_hash_join.cu b/cpp/src/join/distinct_hash_join.cu
index ba2647af0506..b7d735cfb78d 100644
--- a/cpp/src/join/distinct_hash_join.cu
+++ b/cpp/src/join/distinct_hash_join.cu
@@ -28,7 +28,7 @@
 #include <cuda/functional>
 #include <cuda/iterator>
 #include <cuda/std/tuple>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/fill.h>
 #include <thrust/sequence.h>
 
diff --git a/cpp/src/join/filter_join_indices/filter_join_indices.cu b/cpp/src/join/filter_join_indices/filter_join_indices.cu
index f500425f8098..adf46223367d 100644
--- a/cpp/src/join/filter_join_indices/filter_join_indices.cu
+++ b/cpp/src/join/filter_join_indices/filter_join_indices.cu
@@ -38,7 +38,7 @@
 #include <cuda/iterator>
 #include <cuda/std/functional>
 #include <cuda/std/tuple>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/reduce.h>
 #include <thrust/transform.h>
 
diff --git a/cpp/src/join/filter_join_indices/filter_join_indices_jit.cu b/cpp/src/join/filter_join_indices/filter_join_indices_jit.cu
index 7268e3696fb4..bd58b71a59b4 100644
--- a/cpp/src/join/filter_join_indices/filter_join_indices_jit.cu
+++ b/cpp/src/join/filter_join_indices/filter_join_indices_jit.cu
@@ -30,7 +30,7 @@
 #include <cuco/static_set.cuh>
 #include <cuda/iterator>
 #include <cuda/std/tuple>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <jit/cache.hpp>
 #include <jit/helpers.hpp>
diff --git a/cpp/src/join/filter_join_indices/filter_join_indices_jit_kernel.cuh b/cpp/src/join/filter_join_indices/filter_join_indices_jit_kernel.cuh
index 1bfeab3e05d1..fc2f3799ea7e 100644
--- a/cpp/src/join/filter_join_indices/filter_join_indices_jit_kernel.cuh
+++ b/cpp/src/join/filter_join_indices/filter_join_indices_jit_kernel.cuh
@@ -12,7 +12,7 @@
 
 #include <rmm/device_uvector.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 #include <string>
diff --git a/cpp/src/join/filter_join_indices/filter_join_indices_kernel.cuh b/cpp/src/join/filter_join_indices/filter_join_indices_kernel.cuh
index 299ec4f3738e..134749854e8e 100644
--- a/cpp/src/join/filter_join_indices/filter_join_indices_kernel.cuh
+++ b/cpp/src/join/filter_join_indices/filter_join_indices_kernel.cuh
@@ -15,7 +15,7 @@
 #include <cudf/types.hpp>
 #include <cudf/utilities/span.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf::detail {
 
diff --git a/cpp/src/join/filter_join_indices/filter_join_indices_kernel.hpp b/cpp/src/join/filter_join_indices/filter_join_indices_kernel.hpp
index 31662c8b22e6..6d83874a0dda 100644
--- a/cpp/src/join/filter_join_indices/filter_join_indices_kernel.hpp
+++ b/cpp/src/join/filter_join_indices/filter_join_indices_kernel.hpp
@@ -10,7 +10,7 @@
 #include <cudf/types.hpp>
 #include <cudf/utilities/span.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <cstddef>
 
diff --git a/cpp/src/join/filter_join_indices/filter_join_indices_output_size_kernel.cuh b/cpp/src/join/filter_join_indices/filter_join_indices_output_size_kernel.cuh
index 70399f8287b7..4bb281d077ab 100644
--- a/cpp/src/join/filter_join_indices/filter_join_indices_output_size_kernel.cuh
+++ b/cpp/src/join/filter_join_indices/filter_join_indices_output_size_kernel.cuh
@@ -17,7 +17,7 @@
 #include <cudf/utilities/span.hpp>
 
 #include <cuda/atomic>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf::detail {
 
diff --git a/cpp/src/join/filter_join_indices/filter_join_indices_output_size_kernel.hpp b/cpp/src/join/filter_join_indices/filter_join_indices_output_size_kernel.hpp
index 2d24fd8fdbf7..cc75cc3f816c 100644
--- a/cpp/src/join/filter_join_indices/filter_join_indices_output_size_kernel.hpp
+++ b/cpp/src/join/filter_join_indices/filter_join_indices_output_size_kernel.hpp
@@ -13,7 +13,7 @@
 #include <cudf/types.hpp>
 #include <cudf/utilities/span.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <cstddef>
 
diff --git a/cpp/src/join/filtered_join/filtered_join.cu b/cpp/src/join/filtered_join/filtered_join.cu
index 046f78a07478..25f7172ffa2d 100644
--- a/cpp/src/join/filtered_join/filtered_join.cu
+++ b/cpp/src/join/filtered_join/filtered_join.cu
@@ -25,7 +25,7 @@
 
 #include <cuco/extent.cuh>
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/copy.h>
 #include <thrust/sequence.h>
 
diff --git a/cpp/src/join/filtered_join/filtered_join_common.cuh b/cpp/src/join/filtered_join/filtered_join_common.cuh
index f2bac5350d87..555fbb08d6fa 100644
--- a/cpp/src/join/filtered_join/filtered_join_common.cuh
+++ b/cpp/src/join/filtered_join/filtered_join_common.cuh
@@ -17,7 +17,7 @@
 
 #include <cuco/detail/open_addressing/kernels.cuh>
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <cuda_runtime_api.h>
 
 #include <cstdint>
diff --git a/cpp/src/join/filtered_join/filtered_join_flat.cu b/cpp/src/join/filtered_join/filtered_join_flat.cu
index 2550d5f47d2e..70b15158f242 100644
--- a/cpp/src/join/filtered_join/filtered_join_flat.cu
+++ b/cpp/src/join/filtered_join/filtered_join_flat.cu
@@ -18,7 +18,7 @@
 #include <cuco/operator.hpp>
 #include <cuco/static_set_ref.cuh>
 #include <cuco/utility/cuda_thread_scope.cuh>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 
diff --git a/cpp/src/join/filtered_join/filtered_join_nested.cu b/cpp/src/join/filtered_join/filtered_join_nested.cu
index a119f15d11c6..55fb7de21d66 100644
--- a/cpp/src/join/filtered_join/filtered_join_nested.cu
+++ b/cpp/src/join/filtered_join/filtered_join_nested.cu
@@ -16,7 +16,7 @@
 #include <cuco/operator.hpp>
 #include <cuco/static_set_ref.cuh>
 #include <cuco/utility/cuda_thread_scope.cuh>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf::detail {
 
diff --git a/cpp/src/join/filtered_join/filtered_join_nested_query.cu b/cpp/src/join/filtered_join/filtered_join_nested_query.cu
index ce3d1f888af0..0b5b716e67a3 100644
--- a/cpp/src/join/filtered_join/filtered_join_nested_query.cu
+++ b/cpp/src/join/filtered_join/filtered_join_nested_query.cu
@@ -19,7 +19,7 @@
 #include <cuco/operator.hpp>
 #include <cuco/static_set_ref.cuh>
 #include <cuco/utility/cuda_thread_scope.cuh>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 
diff --git a/cpp/src/join/filtered_join/filtered_join_primitive.cu b/cpp/src/join/filtered_join/filtered_join_primitive.cu
index 22c4113ca67d..3425d2855990 100644
--- a/cpp/src/join/filtered_join/filtered_join_primitive.cu
+++ b/cpp/src/join/filtered_join/filtered_join_primitive.cu
@@ -18,7 +18,7 @@
 #include <cuco/operator.hpp>
 #include <cuco/static_set_ref.cuh>
 #include <cuco/utility/cuda_thread_scope.cuh>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 
diff --git a/cpp/src/join/hash_join/common.cuh b/cpp/src/join/hash_join/common.cuh
index 517573412e65..4a9c5621ae96 100644
--- a/cpp/src/join/hash_join/common.cuh
+++ b/cpp/src/join/hash_join/common.cuh
@@ -14,7 +14,7 @@
 #include <rmm/device_uvector.hpp>
 #include <rmm/resource_ref.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 
diff --git a/cpp/src/join/hash_join/finalize_partitioned_full_join.cpp b/cpp/src/join/hash_join/finalize_partitioned_full_join.cpp
index 385f3bff56c1..8ef9326ff957 100644
--- a/cpp/src/join/hash_join/finalize_partitioned_full_join.cpp
+++ b/cpp/src/join/hash_join/finalize_partitioned_full_join.cpp
@@ -14,7 +14,7 @@
 
 #include <rmm/device_uvector.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 
diff --git a/cpp/src/join/hash_join/partitioned_count_kernels.cuh b/cpp/src/join/hash_join/partitioned_count_kernels.cuh
index e07965ab919a..3cb978711596 100644
--- a/cpp/src/join/hash_join/partitioned_count_kernels.cuh
+++ b/cpp/src/join/hash_join/partitioned_count_kernels.cuh
@@ -11,7 +11,7 @@
 
 #include <cooperative_groups.h>
 #include <cooperative_groups/reduce.h>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf::detail {
 
diff --git a/cpp/src/join/hash_join/partitioned_count_kernels.hpp b/cpp/src/join/hash_join/partitioned_count_kernels.hpp
index 14e6db4bc294..47543b8cc63a 100644
--- a/cpp/src/join/hash_join/partitioned_count_kernels.hpp
+++ b/cpp/src/join/hash_join/partitioned_count_kernels.hpp
@@ -7,7 +7,7 @@
 
 #include "kernels_common.cuh"
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf::detail {
 
diff --git a/cpp/src/join/hash_join/partitioned_retrieve_kernels.cuh b/cpp/src/join/hash_join/partitioned_retrieve_kernels.cuh
index 72518018fb2f..3931a92e4764 100644
--- a/cpp/src/join/hash_join/partitioned_retrieve_kernels.cuh
+++ b/cpp/src/join/hash_join/partitioned_retrieve_kernels.cuh
@@ -20,7 +20,7 @@
 #include <cuda/atomic>
 #include <cuda/std/bit>
 #include <cuda/std/cstdint>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/reduce.h>
 
 namespace cudf::detail {
diff --git a/cpp/src/join/hash_join/partitioned_retrieve_kernels.hpp b/cpp/src/join/hash_join/partitioned_retrieve_kernels.hpp
index aa7f89fc066f..ea36e7b80d9b 100644
--- a/cpp/src/join/hash_join/partitioned_retrieve_kernels.hpp
+++ b/cpp/src/join/hash_join/partitioned_retrieve_kernels.hpp
@@ -11,7 +11,7 @@
 
 #include <rmm/device_uvector.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 #include <utility>
diff --git a/cpp/src/join/join.cu b/cpp/src/join/join.cu
index 6b5191a6e0d0..d3a0cb194cbe 100644
--- a/cpp/src/join/join.cu
+++ b/cpp/src/join/join.cu
@@ -18,7 +18,7 @@
 #include <rmm/device_uvector.hpp>
 #include <rmm/resource_ref.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 
diff --git a/cpp/src/join/join_common_utils.cuh b/cpp/src/join/join_common_utils.cuh
index 9f78f17e3553..32bfd94324bd 100644
--- a/cpp/src/join/join_common_utils.cuh
+++ b/cpp/src/join/join_common_utils.cuh
@@ -12,7 +12,7 @@
 #include <cudf/detail/row_operator/hashing.cuh>
 #include <cudf/detail/utilities/cuda.cuh>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 
diff --git a/cpp/src/join/join_common_utils.hpp b/cpp/src/join/join_common_utils.hpp
index c1069dff7062..eb3c6a5e89af 100644
--- a/cpp/src/join/join_common_utils.hpp
+++ b/cpp/src/join/join_common_utils.hpp
@@ -12,7 +12,7 @@
 #include <rmm/device_uvector.hpp>
 #include <rmm/resource_ref.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 #include <utility>
diff --git a/cpp/src/join/join_utils.cu b/cpp/src/join/join_utils.cu
index 8c47f3659b48..6e4e20b1d7d5 100644
--- a/cpp/src/join/join_utils.cu
+++ b/cpp/src/join/join_utils.cu
@@ -22,7 +22,7 @@
 #include <cuda/std/functional>
 #include <cuda/std/iterator>
 #include <cuda/std/tuple>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/scatter.h>
 #include <thrust/sequence.h>
 #include <thrust/uninitialized_fill.h>
diff --git a/cpp/src/join/key_remapping.cu b/cpp/src/join/key_remapping.cu
index f07fe8344242..8191ea164e08 100644
--- a/cpp/src/join/key_remapping.cu
+++ b/cpp/src/join/key_remapping.cu
@@ -32,7 +32,7 @@
 #include <cuda/functional>
 #include <cuda/iterator>
 #include <cuda/std/atomic>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/fill.h>
 #include <thrust/for_each.h>
 #include <thrust/reduce.h>
diff --git a/cpp/src/join/mark_join.cuh b/cpp/src/join/mark_join.cuh
index 6a3179f3b493..9c83e7bfa855 100644
--- a/cpp/src/join/mark_join.cuh
+++ b/cpp/src/join/mark_join.cuh
@@ -25,7 +25,7 @@
 #include <cuco/probing_scheme.cuh>
 #include <cuco/types.cuh>
 #include <cuda/std/limits>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 
diff --git a/cpp/src/join/mixed_join.cu b/cpp/src/join/mixed_join.cu
index 62eaf975d821..f9a8c42b5bf4 100644
--- a/cpp/src/join/mixed_join.cu
+++ b/cpp/src/join/mixed_join.cu
@@ -20,7 +20,7 @@
 #include <rmm/device_uvector.hpp>
 #include <rmm/exec_policy.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/uninitialized_fill.h>
 
 #include <memory>
diff --git a/cpp/src/join/mixed_join_kernels_semi.cuh b/cpp/src/join/mixed_join_kernels_semi.cuh
index 293552e18324..276f60a47d2a 100644
--- a/cpp/src/join/mixed_join_kernels_semi.cuh
+++ b/cpp/src/join/mixed_join_kernels_semi.cuh
@@ -13,7 +13,7 @@
 #include <cudf/types.hpp>
 #include <cudf/utilities/span.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace detail {
diff --git a/cpp/src/join/mixed_join_semi.cu b/cpp/src/join/mixed_join_semi.cu
index 52eb1f6b871d..956bd53423b6 100644
--- a/cpp/src/join/mixed_join_semi.cu
+++ b/cpp/src/join/mixed_join_semi.cu
@@ -27,7 +27,7 @@
 
 #include <cuda/iterator>
 #include <cuda/std/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/fill.h>
 
 #include <optional>
diff --git a/cpp/src/join/sort_merge_join.cu b/cpp/src/join/sort_merge_join.cu
index f8018e67e9ee..1c0ed633dfe8 100644
--- a/cpp/src/join/sort_merge_join.cu
+++ b/cpp/src/join/sort_merge_join.cu
@@ -39,7 +39,7 @@
 #include <cuda/std/execution>
 #include <cuda/std/iterator>
 #include <cuda/std/tuple>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/binary_search.h>
 #include <thrust/for_each.h>
 #include <thrust/sort.h>
diff --git a/cpp/src/join/sort_merge_join.hpp b/cpp/src/join/sort_merge_join.hpp
index 71b8daef8e74..2924548386c9 100644
--- a/cpp/src/join/sort_merge_join.hpp
+++ b/cpp/src/join/sort_merge_join.hpp
@@ -16,7 +16,7 @@
 #include <rmm/device_buffer.hpp>
 #include <rmm/device_uvector.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 #include <optional>
diff --git a/cpp/src/partitioning/partitioning.cu b/cpp/src/partitioning/partitioning.cu
index 3becafb1b4a3..3afab1d7c5db 100644
--- a/cpp/src/partitioning/partitioning.cu
+++ b/cpp/src/partitioning/partitioning.cu
@@ -28,7 +28,7 @@
 #include <cuda/atomic>
 #include <cuda/devices>
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/scan.h>
 #include <thrust/transform.h>
 
diff --git a/cpp/src/partitioning/round_robin.cu b/cpp/src/partitioning/round_robin.cu
index 92559da84276..6233acabd211 100644
--- a/cpp/src/partitioning/round_robin.cu
+++ b/cpp/src/partitioning/round_robin.cu
@@ -24,7 +24,7 @@
 
 #include <cuda/functional>
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/execution_policy.h>
 #include <thrust/for_each.h>
 #include <thrust/iterator/transform_iterator.h>
diff --git a/cpp/src/quantiles/tdigest/tdigest_aggregation.cu b/cpp/src/quantiles/tdigest/tdigest_aggregation.cu
index ffa3a3d7a28a..3aeaa3459aff 100644
--- a/cpp/src/quantiles/tdigest/tdigest_aggregation.cu
+++ b/cpp/src/quantiles/tdigest/tdigest_aggregation.cu
@@ -33,7 +33,7 @@
 #include <cuda/iterator>
 #include <cuda/std/span>
 #include <cuda/std/tuple>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/binary_search.h>
 #include <thrust/copy.h>
 #include <thrust/execution_policy.h>
diff --git a/cpp/src/reductions/approx_distinct_count.cu b/cpp/src/reductions/approx_distinct_count.cu
index 61f0bf140db0..07acf1d205f6 100644
--- a/cpp/src/reductions/approx_distinct_count.cu
+++ b/cpp/src/reductions/approx_distinct_count.cu
@@ -20,7 +20,7 @@
 #include <cuda/functional>
 #include <cuda/iterator>
 #include <cuda/std/type_traits>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <cmath>
 #include <utility>
diff --git a/cpp/src/reductions/count.cpp b/cpp/src/reductions/count.cpp
index fbc3a29a800d..61542c5d0f0e 100644
--- a/cpp/src/reductions/count.cpp
+++ b/cpp/src/reductions/count.cpp
@@ -9,7 +9,7 @@
 #include <cudf/utilities/memory_resource.hpp>
 #include <cudf/utilities/type_dispatcher.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace reduction {
diff --git a/cpp/src/reductions/distinct_count.cu b/cpp/src/reductions/distinct_count.cu
index a125b27a1e62..0a19155f7e2c 100644
--- a/cpp/src/reductions/distinct_count.cu
+++ b/cpp/src/reductions/distinct_count.cu
@@ -23,7 +23,7 @@
 
 #include <cuco/static_set.cuh>
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/count.h>
 #include <thrust/execution_policy.h>
 #include <thrust/logical.h>
diff --git a/cpp/src/reductions/extrema_utils.cuh b/cpp/src/reductions/extrema_utils.cuh
index 5768b4bff0aa..ca3f945ea463 100644
--- a/cpp/src/reductions/extrema_utils.cuh
+++ b/cpp/src/reductions/extrema_utils.cuh
@@ -17,7 +17,7 @@
 #include <rmm/exec_policy.hpp>
 
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/extrema.h>
 
 namespace cudf::reduction::simple::detail {
diff --git a/cpp/src/reductions/max.cu b/cpp/src/reductions/max.cu
index 94aaa08c3dbb..6f35245a1300 100644
--- a/cpp/src/reductions/max.cu
+++ b/cpp/src/reductions/max.cu
@@ -9,7 +9,7 @@
 #include <cudf/reduction/detail/reduction_functions.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace reduction {
diff --git a/cpp/src/reductions/mean.cu b/cpp/src/reductions/mean.cu
index 5e3e80d390be..e44b7742318d 100644
--- a/cpp/src/reductions/mean.cu
+++ b/cpp/src/reductions/mean.cu
@@ -9,7 +9,7 @@
 #include <cudf/reduction/detail/reduction_functions.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace reduction {
diff --git a/cpp/src/reductions/minmax.cu b/cpp/src/reductions/minmax.cu
index c30f0339e8f8..c52af997d679 100644
--- a/cpp/src/reductions/minmax.cu
+++ b/cpp/src/reductions/minmax.cu
@@ -21,7 +21,7 @@
 #include <cuda/std/functional>
 #include <cuda/std/iterator>
 #include <cuda/std/utility>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/transform_reduce.h>
 
 #include <type_traits>
diff --git a/cpp/src/reductions/nth_element.cu b/cpp/src/reductions/nth_element.cu
index e11ae7c422f9..ea1a48ad356f 100644
--- a/cpp/src/reductions/nth_element.cu
+++ b/cpp/src/reductions/nth_element.cu
@@ -14,7 +14,7 @@
 #include <rmm/exec_policy.hpp>
 
 #include <cuda/functional>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/binary_search.h>
 #include <thrust/iterator/transform_iterator.h>
 #include <thrust/scan.h>
diff --git a/cpp/src/reductions/nunique.cpp b/cpp/src/reductions/nunique.cpp
index 6f07679c9c98..7615c12ba1d6 100644
--- a/cpp/src/reductions/nunique.cpp
+++ b/cpp/src/reductions/nunique.cpp
@@ -9,7 +9,7 @@
 #include <cudf/utilities/memory_resource.hpp>
 #include <cudf/utilities/type_dispatcher.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace reduction {
diff --git a/cpp/src/reductions/product.cu b/cpp/src/reductions/product.cu
index bd11bbf77a28..abf33f581410 100644
--- a/cpp/src/reductions/product.cu
+++ b/cpp/src/reductions/product.cu
@@ -9,7 +9,7 @@
 #include <cudf/reduction/detail/reduction_functions.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace reduction {
diff --git a/cpp/src/reductions/quantile.cu b/cpp/src/reductions/quantile.cu
index 3c555253270e..b749bd0c8f26 100644
--- a/cpp/src/reductions/quantile.cu
+++ b/cpp/src/reductions/quantile.cu
@@ -11,7 +11,7 @@
 #include <cudf/reduction/detail/reduction_functions.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace reduction {
diff --git a/cpp/src/reductions/reductions.cpp b/cpp/src/reductions/reductions.cpp
index 427dcb16bcba..bae67c8b0b65 100644
--- a/cpp/src/reductions/reductions.cpp
+++ b/cpp/src/reductions/reductions.cpp
@@ -19,7 +19,7 @@
 #include <cudf/utilities/error.hpp>
 #include <cudf/utilities/type_checks.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <utility>
 
diff --git a/cpp/src/reductions/scan/ewm.cu b/cpp/src/reductions/scan/ewm.cu
index 7362e9dab0e4..40a06efeccd5 100644
--- a/cpp/src/reductions/scan/ewm.cu
+++ b/cpp/src/reductions/scan/ewm.cu
@@ -17,7 +17,7 @@
 #include <cuda/functional>
 #include <cuda/iterator>
 #include <cuda/std/utility>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/scan.h>
 #include <thrust/transform_scan.h>
 
diff --git a/cpp/src/reductions/scan/rank_scan.cu b/cpp/src/reductions/scan/rank_scan.cu
index 10f5e536064b..9fbd854dbb3f 100644
--- a/cpp/src/reductions/scan/rank_scan.cu
+++ b/cpp/src/reductions/scan/rank_scan.cu
@@ -15,7 +15,7 @@
 #include <rmm/exec_policy.hpp>
 
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/scan.h>
 #include <thrust/transform.h>
 
diff --git a/cpp/src/reductions/scan/scan.cuh b/cpp/src/reductions/scan/scan.cuh
index 0de4a69dd1c8..24837c6c0884 100644
--- a/cpp/src/reductions/scan/scan.cuh
+++ b/cpp/src/reductions/scan/scan.cuh
@@ -12,7 +12,7 @@
 #include <cudf/utilities/memory_resource.hpp>
 #include <cudf/utilities/type_dispatcher.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <utility>
 
diff --git a/cpp/src/reductions/scan/scan_exclusive.cu b/cpp/src/reductions/scan/scan_exclusive.cu
index 55fbabff78c4..17000ec41c1a 100644
--- a/cpp/src/reductions/scan/scan_exclusive.cu
+++ b/cpp/src/reductions/scan/scan_exclusive.cu
@@ -17,7 +17,7 @@
 #include <rmm/exec_policy.hpp>
 
 #include <cuda/functional>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/scan.h>
 
 namespace cudf {
diff --git a/cpp/src/reductions/scan/scan_inclusive.cu b/cpp/src/reductions/scan/scan_inclusive.cu
index 60893adf6ce5..fd5b8c01b684 100644
--- a/cpp/src/reductions/scan/scan_inclusive.cu
+++ b/cpp/src/reductions/scan/scan_inclusive.cu
@@ -23,7 +23,7 @@
 
 #include <cuda/functional>
 #include <cuda/std/functional>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/find.h>
 #include <thrust/scan.h>
 
diff --git a/cpp/src/reductions/segmented/counts.hpp b/cpp/src/reductions/segmented/counts.hpp
index 1760ac59b6f9..e3a8edaf96d3 100644
--- a/cpp/src/reductions/segmented/counts.hpp
+++ b/cpp/src/reductions/segmented/counts.hpp
@@ -11,7 +11,7 @@
 
 #include <rmm/device_uvector.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 class column_device_view;
diff --git a/cpp/src/reductions/segmented/mean.cu b/cpp/src/reductions/segmented/mean.cu
index b09122086018..a90152a4d551 100644
--- a/cpp/src/reductions/segmented/mean.cu
+++ b/cpp/src/reductions/segmented/mean.cu
@@ -8,7 +8,7 @@
 #include <cudf/reduction/detail/segmented_reduction_functions.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace reduction {
diff --git a/cpp/src/reductions/segmented/nunique.cu b/cpp/src/reductions/segmented/nunique.cu
index 7c7c8ffdaa55..8680dc1a91af 100644
--- a/cpp/src/reductions/segmented/nunique.cu
+++ b/cpp/src/reductions/segmented/nunique.cu
@@ -16,7 +16,7 @@
 #include <cudf/utilities/memory_resource.hpp>
 
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/transform.h>
 
 namespace cudf {
diff --git a/cpp/src/reductions/segmented/reductions.cpp b/cpp/src/reductions/segmented/reductions.cpp
index 3ebbf13e981b..73450ed36315 100644
--- a/cpp/src/reductions/segmented/reductions.cpp
+++ b/cpp/src/reductions/segmented/reductions.cpp
@@ -13,7 +13,7 @@
 #include <cudf/utilities/error.hpp>
 #include <cudf/utilities/type_checks.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace reduction {
diff --git a/cpp/src/reductions/segmented/simple.cuh b/cpp/src/reductions/segmented/simple.cuh
index f450aae1f334..6ced8884ba94 100644
--- a/cpp/src/reductions/segmented/simple.cuh
+++ b/cpp/src/reductions/segmented/simple.cuh
@@ -24,7 +24,7 @@
 
 #include <cuda/functional>
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/iterator/transform_iterator.h>
 #include <thrust/reduce.h>
 
diff --git a/cpp/src/reductions/segmented/std.cu b/cpp/src/reductions/segmented/std.cu
index 821c769dfc8b..f7f112e097c2 100644
--- a/cpp/src/reductions/segmented/std.cu
+++ b/cpp/src/reductions/segmented/std.cu
@@ -8,7 +8,7 @@
 #include <cudf/reduction/detail/segmented_reduction_functions.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace reduction {
diff --git a/cpp/src/reductions/segmented/sum_of_squares.cu b/cpp/src/reductions/segmented/sum_of_squares.cu
index e3ad0a220987..0dcc356431f2 100644
--- a/cpp/src/reductions/segmented/sum_of_squares.cu
+++ b/cpp/src/reductions/segmented/sum_of_squares.cu
@@ -8,7 +8,7 @@
 #include <cudf/reduction/detail/segmented_reduction_functions.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace reduction {
diff --git a/cpp/src/reductions/segmented/update_validity.hpp b/cpp/src/reductions/segmented/update_validity.hpp
index 531f88222b26..da25977375cb 100644
--- a/cpp/src/reductions/segmented/update_validity.hpp
+++ b/cpp/src/reductions/segmented/update_validity.hpp
@@ -11,7 +11,7 @@
 #include <cudf/utilities/memory_resource.hpp>
 #include <cudf/utilities/span.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <optional>
 
diff --git a/cpp/src/reductions/segmented/var.cu b/cpp/src/reductions/segmented/var.cu
index f3b5dbdc3e73..74d3f41e1e03 100644
--- a/cpp/src/reductions/segmented/var.cu
+++ b/cpp/src/reductions/segmented/var.cu
@@ -8,7 +8,7 @@
 #include <cudf/reduction/detail/segmented_reduction_functions.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace reduction {
diff --git a/cpp/src/reductions/simple.cuh b/cpp/src/reductions/simple.cuh
index e0d1aac3e56c..c3dbb461b3df 100644
--- a/cpp/src/reductions/simple.cuh
+++ b/cpp/src/reductions/simple.cuh
@@ -21,7 +21,7 @@
 #include <cudf/utilities/type_dispatcher.hpp>
 
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/iterator/transform_iterator.h>
 #include <thrust/reduce.h>
 
diff --git a/cpp/src/reductions/std.cu b/cpp/src/reductions/std.cu
index 12c1f1fce543..a99158e12168 100644
--- a/cpp/src/reductions/std.cu
+++ b/cpp/src/reductions/std.cu
@@ -9,7 +9,7 @@
 #include <cudf/reduction/detail/reduction_functions.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace reduction {
diff --git a/cpp/src/reductions/sum.cu b/cpp/src/reductions/sum.cu
index 16048a445e45..914548dccfa3 100644
--- a/cpp/src/reductions/sum.cu
+++ b/cpp/src/reductions/sum.cu
@@ -9,7 +9,7 @@
 #include <cudf/reduction/detail/reduction_functions.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace reduction {
diff --git a/cpp/src/reductions/sum_of_squares.cu b/cpp/src/reductions/sum_of_squares.cu
index 7770533e2c80..a5034a4f4e51 100644
--- a/cpp/src/reductions/sum_of_squares.cu
+++ b/cpp/src/reductions/sum_of_squares.cu
@@ -9,7 +9,7 @@
 #include <cudf/reduction/detail/reduction_functions.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace reduction {
diff --git a/cpp/src/reductions/sum_overflow.cu b/cpp/src/reductions/sum_overflow.cu
index 2808f3eb8776..8f8746d2ec03 100644
--- a/cpp/src/reductions/sum_overflow.cu
+++ b/cpp/src/reductions/sum_overflow.cu
@@ -22,7 +22,7 @@
 
 #include <cuda/iterator>
 #include <cuda/numeric>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/transform_reduce.h>
 
 namespace cudf::reduction::detail {
diff --git a/cpp/src/reductions/unique_count.cu b/cpp/src/reductions/unique_count.cu
index 8630a36ef38b..080b9beaa7ba 100644
--- a/cpp/src/reductions/unique_count.cu
+++ b/cpp/src/reductions/unique_count.cu
@@ -13,7 +13,7 @@
 #include <rmm/exec_policy.hpp>
 
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/count.h>
 #include <thrust/execution_policy.h>
 #include <thrust/transform.h>
diff --git a/cpp/src/reductions/unique_count_column.cu b/cpp/src/reductions/unique_count_column.cu
index 27d271bbb54d..aa06fea39322 100644
--- a/cpp/src/reductions/unique_count_column.cu
+++ b/cpp/src/reductions/unique_count_column.cu
@@ -18,7 +18,7 @@
 #include <cuda/iterator>
 #include <cuda/std/cmath>
 #include <cuda/std/type_traits>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/count.h>
 #include <thrust/execution_policy.h>
 
diff --git a/cpp/src/reductions/var.cu b/cpp/src/reductions/var.cu
index ee7bf983de82..924af0137959 100644
--- a/cpp/src/reductions/var.cu
+++ b/cpp/src/reductions/var.cu
@@ -9,7 +9,7 @@
 #include <cudf/reduction/detail/reduction_functions.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace reduction {
diff --git a/cpp/src/rolling/detail/optimized_unbounded_window.hpp b/cpp/src/rolling/detail/optimized_unbounded_window.hpp
index 1d5b7932bda9..4c64ece33492 100644
--- a/cpp/src/rolling/detail/optimized_unbounded_window.hpp
+++ b/cpp/src/rolling/detail/optimized_unbounded_window.hpp
@@ -11,7 +11,7 @@
 
 #include <rmm/resource_ref.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 
diff --git a/cpp/src/rolling/detail/range_rolling.hpp b/cpp/src/rolling/detail/range_rolling.hpp
index 2b36c87012dd..637883c0ed4c 100644
--- a/cpp/src/rolling/detail/range_rolling.hpp
+++ b/cpp/src/rolling/detail/range_rolling.hpp
@@ -15,7 +15,7 @@
 
 #include <rmm/resource_ref.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 #include <optional>
diff --git a/cpp/src/rolling/detail/range_utils.cuh b/cpp/src/rolling/detail/range_utils.cuh
index e05183c1deff..d802f77a3000 100644
--- a/cpp/src/rolling/detail/range_utils.cuh
+++ b/cpp/src/rolling/detail/range_utils.cuh
@@ -33,7 +33,7 @@
 #include <cuda/std/limits>
 #include <cuda/std/type_traits>
 #include <cuda/std/utility>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/binary_search.h>
 #include <thrust/execution_policy.h>
 
diff --git a/cpp/src/rolling/detail/rolling.cuh b/cpp/src/rolling/detail/rolling.cuh
index 50d08f6451ea..2a82ed5656c7 100644
--- a/cpp/src/rolling/detail/rolling.cuh
+++ b/cpp/src/rolling/detail/rolling.cuh
@@ -35,7 +35,7 @@
 
 #include <rmm/exec_policy.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 
diff --git a/cpp/src/rolling/detail/rolling.hpp b/cpp/src/rolling/detail/rolling.hpp
index 74247456c10b..11e980174f29 100644
--- a/cpp/src/rolling/detail/rolling.hpp
+++ b/cpp/src/rolling/detail/rolling.hpp
@@ -14,7 +14,7 @@
 
 #include <rmm/resource_ref.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 
diff --git a/cpp/src/rolling/detail/rolling_collect_list.cuh b/cpp/src/rolling/detail/rolling_collect_list.cuh
index 224f10107ac7..66c9b0ff9f4e 100644
--- a/cpp/src/rolling/detail/rolling_collect_list.cuh
+++ b/cpp/src/rolling/detail/rolling_collect_list.cuh
@@ -16,7 +16,7 @@
 
 #include <cuda/functional>
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/extrema.h>
 #include <thrust/iterator/transform_iterator.h>
 #include <thrust/transform.h>
diff --git a/cpp/src/rolling/detail/rolling_operators.cuh b/cpp/src/rolling/detail/rolling_operators.cuh
index 3fc455e16dea..b3f1a59934de 100644
--- a/cpp/src/rolling/detail/rolling_operators.cuh
+++ b/cpp/src/rolling/detail/rolling_operators.cuh
@@ -26,7 +26,7 @@
 
 #include <cuda/iterator>
 #include <cuda/std/limits>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/count.h>
 #include <thrust/execution_policy.h>
 #include <thrust/reduce.h>
diff --git a/cpp/src/rolling/detail/rolling_udf.cuh b/cpp/src/rolling/detail/rolling_udf.cuh
index 0a71259affc1..66b1bcc09ace 100644
--- a/cpp/src/rolling/detail/rolling_udf.cuh
+++ b/cpp/src/rolling/detail/rolling_udf.cuh
@@ -19,7 +19,7 @@
 #include <cudf/types.hpp>
 #include <cudf/utilities/error.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 
diff --git a/cpp/src/rolling/grouped_rolling.cu b/cpp/src/rolling/grouped_rolling.cu
index f22b729f6073..30b3cd44ccfb 100644
--- a/cpp/src/rolling/grouped_rolling.cu
+++ b/cpp/src/rolling/grouped_rolling.cu
@@ -23,7 +23,7 @@
 
 #include <cuda/functional>
 #include <cuda/std/functional>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <concepts>
 #include <span>
diff --git a/cpp/src/rolling/range_rolling.cu b/cpp/src/rolling/range_rolling.cu
index bce0c5dbca4c..0887a22b5720 100644
--- a/cpp/src/rolling/range_rolling.cu
+++ b/cpp/src/rolling/range_rolling.cu
@@ -24,7 +24,7 @@
 
 #include <cub/device/device_segmented_reduce.cuh>
 #include <cuda/functional>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <cstddef>
 #include <memory>
diff --git a/cpp/src/rolling/range_rolling_bounded_closed.cu b/cpp/src/rolling/range_rolling_bounded_closed.cu
index ee4d64ef15c7..cc0c215b5c28 100644
--- a/cpp/src/rolling/range_rolling_bounded_closed.cu
+++ b/cpp/src/rolling/range_rolling_bounded_closed.cu
@@ -16,7 +16,7 @@
 
 #include <rmm/resource_ref.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 #include <optional>
diff --git a/cpp/src/rolling/range_rolling_bounded_open.cu b/cpp/src/rolling/range_rolling_bounded_open.cu
index ccb2f3431aeb..a780defb31ec 100644
--- a/cpp/src/rolling/range_rolling_bounded_open.cu
+++ b/cpp/src/rolling/range_rolling_bounded_open.cu
@@ -16,7 +16,7 @@
 
 #include <rmm/resource_ref.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 #include <optional>
diff --git a/cpp/src/rolling/range_rolling_current_row.cu b/cpp/src/rolling/range_rolling_current_row.cu
index 64f9af8073ba..7a841bfb396d 100644
--- a/cpp/src/rolling/range_rolling_current_row.cu
+++ b/cpp/src/rolling/range_rolling_current_row.cu
@@ -16,7 +16,7 @@
 
 #include <rmm/resource_ref.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 #include <optional>
diff --git a/cpp/src/rolling/range_rolling_multi_column.cu b/cpp/src/rolling/range_rolling_multi_column.cu
index 802a4c99e90e..a5527a1ad7bf 100644
--- a/cpp/src/rolling/range_rolling_multi_column.cu
+++ b/cpp/src/rolling/range_rolling_multi_column.cu
@@ -28,7 +28,7 @@
 #include <cuda/functional>
 #include <cuda/iterator>
 #include <cuda/std/tuple>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/copy.h>
 
 #include <memory>
diff --git a/cpp/src/rolling/range_rolling_unbounded.cu b/cpp/src/rolling/range_rolling_unbounded.cu
index 00b009fdd59e..0306a1ca2545 100644
--- a/cpp/src/rolling/range_rolling_unbounded.cu
+++ b/cpp/src/rolling/range_rolling_unbounded.cu
@@ -16,7 +16,7 @@
 
 #include <rmm/resource_ref.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 #include <optional>
diff --git a/cpp/src/rolling/rolling.cpp b/cpp/src/rolling/rolling.cpp
index 0cc1455f8980..52d9e51865ec 100644
--- a/cpp/src/rolling/rolling.cpp
+++ b/cpp/src/rolling/rolling.cpp
@@ -15,7 +15,7 @@
 
 #include <rmm/resource_ref.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 
diff --git a/cpp/src/scalar/scalar.cpp b/cpp/src/scalar/scalar.cpp
index 97945228c6f7..0b00470c9171 100644
--- a/cpp/src/scalar/scalar.cpp
+++ b/cpp/src/scalar/scalar.cpp
@@ -14,7 +14,7 @@
 
 #include <rmm/device_buffer.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <string>
 
diff --git a/cpp/src/scalar/scalar_factories.cpp b/cpp/src/scalar/scalar_factories.cpp
index 8216723b7afe..08fbe2729acc 100644
--- a/cpp/src/scalar/scalar_factories.cpp
+++ b/cpp/src/scalar/scalar_factories.cpp
@@ -10,7 +10,7 @@
 #include <cudf/utilities/traits.hpp>
 #include <cudf/utilities/type_dispatcher.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace {
diff --git a/cpp/src/search/contains_column.cu b/cpp/src/search/contains_column.cu
index 1a9c6d46ace7..30cc96317532 100644
--- a/cpp/src/search/contains_column.cu
+++ b/cpp/src/search/contains_column.cu
@@ -12,7 +12,7 @@
 #include <cudf/table/table_view.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace detail {
diff --git a/cpp/src/search/contains_scalar.cu b/cpp/src/search/contains_scalar.cu
index c6f329e5e1f8..71899a74aac1 100644
--- a/cpp/src/search/contains_scalar.cu
+++ b/cpp/src/search/contains_scalar.cu
@@ -22,7 +22,7 @@
 
 #include <rmm/exec_policy.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/transform.h>
 
 namespace cudf {
diff --git a/cpp/src/search/contains_table.cu b/cpp/src/search/contains_table.cu
index 189199ef1cf6..7f28b9f7f64e 100644
--- a/cpp/src/search/contains_table.cu
+++ b/cpp/src/search/contains_table.cu
@@ -16,7 +16,7 @@
 #include <rmm/device_uvector.hpp>
 
 #include <cuco/static_set.cuh>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <algorithm>
 
diff --git a/cpp/src/search/contains_table_impl.cuh b/cpp/src/search/contains_table_impl.cuh
index 3d8f1f5df9c5..d330eb02c502 100644
--- a/cpp/src/search/contains_table_impl.cuh
+++ b/cpp/src/search/contains_table_impl.cuh
@@ -21,7 +21,7 @@
 #include <cuco/static_set.cuh>
 #include <cuda/functional>
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf::detail {
 
diff --git a/cpp/src/search/search_ordered.cu b/cpp/src/search/search_ordered.cu
index b579d9f40975..82a45012877f 100644
--- a/cpp/src/search/search_ordered.cu
+++ b/cpp/src/search/search_ordered.cu
@@ -16,7 +16,7 @@
 
 #include <rmm/exec_policy.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/binary_search.h>
 
 namespace cudf {
diff --git a/cpp/src/sort/is_sorted.cu b/cpp/src/sort/is_sorted.cu
index 8976cf3bd3dd..149fa647991d 100644
--- a/cpp/src/sort/is_sorted.cu
+++ b/cpp/src/sort/is_sorted.cu
@@ -16,7 +16,7 @@
 #include <rmm/exec_policy.hpp>
 
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/count.h>
 #include <thrust/sort.h>
 #include <thrust/transform.h>
diff --git a/cpp/src/sort/rank.cu b/cpp/src/sort/rank.cu
index 2d2babeb34ba..8bf85594887a 100644
--- a/cpp/src/sort/rank.cu
+++ b/cpp/src/sort/rank.cu
@@ -25,7 +25,7 @@
 #include <cuda/std/algorithm>
 #include <cuda/std/type_traits>
 #include <cuda/std/utility>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/iterator/transform_iterator.h>
 #include <thrust/reduce.h>
 #include <thrust/scan.h>
diff --git a/cpp/src/sort/segmented_sort_impl.cuh b/cpp/src/sort/segmented_sort_impl.cuh
index 39966c791186..5da85f7f391c 100644
--- a/cpp/src/sort/segmented_sort_impl.cuh
+++ b/cpp/src/sort/segmented_sort_impl.cuh
@@ -17,7 +17,7 @@
 #include <rmm/device_uvector.hpp>
 
 #include <cub/device/device_segmented_sort.cuh>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace detail {
diff --git a/cpp/src/sort/segmented_top_k.cu b/cpp/src/sort/segmented_top_k.cu
index b32367be2a8a..96dcb606a16a 100644
--- a/cpp/src/sort/segmented_top_k.cu
+++ b/cpp/src/sort/segmented_top_k.cu
@@ -20,7 +20,7 @@
 #include <cudf/utilities/memory_resource.hpp>
 
 #include <cuda/std/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/binary_search.h>
 #include <thrust/execution_policy.h>
 #include <thrust/remove.h>
diff --git a/cpp/src/sort/sort.cu b/cpp/src/sort/sort.cu
index cf88f13b5614..36e6beda142a 100644
--- a/cpp/src/sort/sort.cu
+++ b/cpp/src/sort/sort.cu
@@ -15,7 +15,7 @@
 #include <cudf/utilities/default_stream.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace detail {
diff --git a/cpp/src/sort/sort.hpp b/cpp/src/sort/sort.hpp
index ec3f0493261e..d5ac2a7eced8 100644
--- a/cpp/src/sort/sort.hpp
+++ b/cpp/src/sort/sort.hpp
@@ -8,7 +8,7 @@
 #include <cudf/sorting.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace detail {
diff --git a/cpp/src/sort/sort_column_impl.cuh b/cpp/src/sort/sort_column_impl.cuh
index eb1614ac3c15..fd48deb56e14 100644
--- a/cpp/src/sort/sort_column_impl.cuh
+++ b/cpp/src/sort/sort_column_impl.cuh
@@ -21,7 +21,7 @@
 
 #include <cub/device/device_merge_sort.cuh>
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/gather.h>
 
 namespace cudf {
diff --git a/cpp/src/sort/sort_radix.cu b/cpp/src/sort/sort_radix.cu
index 8feb4469a28b..04467c584b7b 100644
--- a/cpp/src/sort/sort_radix.cu
+++ b/cpp/src/sort/sort_radix.cu
@@ -12,7 +12,7 @@
 
 #include <cub/device/device_radix_sort.cuh>
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/transform.h>
 
 namespace cudf {
diff --git a/cpp/src/sort/sort_radix.hpp b/cpp/src/sort/sort_radix.hpp
index 60192438ed29..4e077666427e 100644
--- a/cpp/src/sort/sort_radix.hpp
+++ b/cpp/src/sort/sort_radix.hpp
@@ -7,7 +7,7 @@
 #include <cudf/column/column_view.hpp>
 #include <cudf/types.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace detail {
diff --git a/cpp/src/sort/sorted_order_radix.cu b/cpp/src/sort/sorted_order_radix.cu
index bbb6d63a8a92..d703fa38baa2 100644
--- a/cpp/src/sort/sorted_order_radix.cu
+++ b/cpp/src/sort/sorted_order_radix.cu
@@ -16,7 +16,7 @@
 
 #include <cub/device/device_radix_sort.cuh>
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/sequence.h>
 #include <thrust/transform.h>
 
diff --git a/cpp/src/sort/stable_sort.cu b/cpp/src/sort/stable_sort.cu
index 726037210243..7be0e9a3f725 100644
--- a/cpp/src/sort/stable_sort.cu
+++ b/cpp/src/sort/stable_sort.cu
@@ -15,7 +15,7 @@
 #include <cudf/utilities/default_stream.hpp>
 #include <cudf/utilities/memory_resource.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace detail {
diff --git a/cpp/src/sort/top_k.cu b/cpp/src/sort/top_k.cu
index 6221791ccf7d..6937034f85ea 100644
--- a/cpp/src/sort/top_k.cu
+++ b/cpp/src/sort/top_k.cu
@@ -25,7 +25,6 @@
 #include <cuda/iterator>
 #include <cuda/std/execution>
 #include <cuda/stream>
-#include <cuda/stream_ref>
 
 namespace cudf {
 namespace detail {
diff --git a/cpp/src/transform/bools_to_mask.cu b/cpp/src/transform/bools_to_mask.cu
index 886ddccaaca3..6b35591a415a 100644
--- a/cpp/src/transform/bools_to_mask.cu
+++ b/cpp/src/transform/bools_to_mask.cu
@@ -16,7 +16,7 @@
 #include <cudf/utilities/traits.hpp>
 #include <cudf/utilities/type_dispatcher.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace detail {
diff --git a/cpp/src/transform/compute_column.cu b/cpp/src/transform/compute_column.cu
index 3f4112379cca..dd80e3c672cc 100644
--- a/cpp/src/transform/compute_column.cu
+++ b/cpp/src/transform/compute_column.cu
@@ -22,7 +22,7 @@
 
 #include <rmm/resource_ref.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <algorithm>
 
diff --git a/cpp/src/transform/compute_column_kernel.cuh b/cpp/src/transform/compute_column_kernel.cuh
index 979fec7c5889..814fc283b0ce 100644
--- a/cpp/src/transform/compute_column_kernel.cuh
+++ b/cpp/src/transform/compute_column_kernel.cuh
@@ -14,7 +14,7 @@
 #include <cudf/table/table_device_view.cuh>
 #include <cudf/types.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf::detail {
 /**
diff --git a/cpp/src/transform/compute_column_kernel.hpp b/cpp/src/transform/compute_column_kernel.hpp
index e19a6ba2bd76..f8a2311bbc97 100644
--- a/cpp/src/transform/compute_column_kernel.hpp
+++ b/cpp/src/transform/compute_column_kernel.hpp
@@ -11,7 +11,7 @@
 #include <cudf/table/table_device_view.cuh>
 #include <cudf/types.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf::detail {
 /**
diff --git a/cpp/src/transform/encode.cu b/cpp/src/transform/encode.cu
index a413b8581e3c..e18a284d3f68 100644
--- a/cpp/src/transform/encode.cu
+++ b/cpp/src/transform/encode.cu
@@ -21,7 +21,7 @@
 #include <rmm/device_uvector.hpp>
 #include <rmm/exec_policy.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <memory>
 #include <numeric>
diff --git a/cpp/src/transform/mask_to_bools.cu b/cpp/src/transform/mask_to_bools.cu
index 7d6b25abff5f..0a4f465f9a1b 100644
--- a/cpp/src/transform/mask_to_bools.cu
+++ b/cpp/src/transform/mask_to_bools.cu
@@ -15,7 +15,7 @@
 #include <rmm/exec_policy.hpp>
 
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/transform.h>
 
 namespace cudf {
diff --git a/cpp/src/transform/nans_to_nulls.cu b/cpp/src/transform/nans_to_nulls.cu
index 5e3264476b54..4da8521e7e24 100644
--- a/cpp/src/transform/nans_to_nulls.cu
+++ b/cpp/src/transform/nans_to_nulls.cu
@@ -18,7 +18,7 @@
 
 #include <cuda/iterator>
 #include <cuda/std/limits>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace detail {
diff --git a/cpp/src/transform/one_hot_encode.cu b/cpp/src/transform/one_hot_encode.cu
index 552fa68eed73..85f9c4f2a65b 100644
--- a/cpp/src/transform/one_hot_encode.cu
+++ b/cpp/src/transform/one_hot_encode.cu
@@ -20,7 +20,7 @@
 #include <rmm/exec_policy.hpp>
 
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/transform.h>
 
 #include <algorithm>
diff --git a/cpp/src/transform/row_bit_count.cu b/cpp/src/transform/row_bit_count.cu
index 469f2fa1c9cf..121ac6c0669f 100644
--- a/cpp/src/transform/row_bit_count.cu
+++ b/cpp/src/transform/row_bit_count.cu
@@ -25,7 +25,7 @@
 
 #include <cuda/functional>
 #include <cuda/std/optional>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/tabulate.h>
 
 namespace cudf {
diff --git a/cpp/src/transform/transform.cu b/cpp/src/transform/transform.cu
index da02a416ad77..f092bea6b815 100644
--- a/cpp/src/transform/transform.cu
+++ b/cpp/src/transform/transform.cu
@@ -21,7 +21,7 @@
 #include <cudf/utilities/type_dispatcher.hpp>
 
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <cudf_fragments.hpp>
 #include <jit/cache.hpp>
diff --git a/cpp/src/unary/cast_ops.cu b/cpp/src/unary/cast_ops.cu
index c148afc9a7f6..b11f2d77069a 100644
--- a/cpp/src/unary/cast_ops.cu
+++ b/cpp/src/unary/cast_ops.cu
@@ -24,7 +24,7 @@
 #include <rmm/exec_policy.hpp>
 
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/transform.h>
 
 namespace cudf {
diff --git a/cpp/src/unary/math_ops.cu b/cpp/src/unary/math_ops.cu
index 5f06f304a109..e294e9b00715 100644
--- a/cpp/src/unary/math_ops.cu
+++ b/cpp/src/unary/math_ops.cu
@@ -19,7 +19,7 @@
 #include <cuda/std/bit>
 #include <cuda/std/cmath>
 #include <cuda/std/type_traits>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/transform.h>
 
 namespace cudf {
diff --git a/cpp/src/unary/nan_ops.cu b/cpp/src/unary/nan_ops.cu
index 452f1ce67715..6c2343cda3b6 100644
--- a/cpp/src/unary/nan_ops.cu
+++ b/cpp/src/unary/nan_ops.cu
@@ -15,7 +15,7 @@
 #include <cudf/utilities/memory_resource.hpp>
 #include <cudf/utilities/type_dispatcher.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 namespace cudf {
 namespace detail {
diff --git a/cpp/src/unary/true_if.cuh b/cpp/src/unary/true_if.cuh
index ecab424ef526..9a1f5cd7bb39 100644
--- a/cpp/src/unary/true_if.cuh
+++ b/cpp/src/unary/true_if.cuh
@@ -10,7 +10,7 @@
 
 #include <rmm/exec_policy.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/transform.h>
 
 namespace cudf {
diff --git a/cpp/src/unary/unary_ops.cuh b/cpp/src/unary/unary_ops.cuh
index f9ba9ee4833c..2bdd97e8d395 100644
--- a/cpp/src/unary/unary_ops.cuh
+++ b/cpp/src/unary/unary_ops.cuh
@@ -14,7 +14,7 @@
 
 #include <rmm/exec_policy.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/transform.h>
 
 namespace cudf {
diff --git a/cpp/tests/bitmask/bitmask_tests.cpp b/cpp/tests/bitmask/bitmask_tests.cpp
index 6ad379d3de9f..7030c28550d8 100644
--- a/cpp/tests/bitmask/bitmask_tests.cpp
+++ b/cpp/tests/bitmask/bitmask_tests.cpp
@@ -21,7 +21,7 @@
 #include <rmm/device_buffer.hpp>
 #include <rmm/device_uvector.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <stdexcept>
 
diff --git a/cpp/tests/bitmask/set_nullmask_tests.cu b/cpp/tests/bitmask/set_nullmask_tests.cu
index 398d47429e5d..c51b44418ce4 100644
--- a/cpp/tests/bitmask/set_nullmask_tests.cu
+++ b/cpp/tests/bitmask/set_nullmask_tests.cu
@@ -13,7 +13,7 @@
 #include <rmm/exec_policy.hpp>
 
 #include <cuda/iterator>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/host_vector.h>
 #include <thrust/transform.h>
 
diff --git a/cpp/tests/column/column_device_view_test.cu b/cpp/tests/column/column_device_view_test.cu
index b7608c3fac73..69fe71be4cd5 100644
--- a/cpp/tests/column/column_device_view_test.cu
+++ b/cpp/tests/column/column_device_view_test.cu
@@ -18,7 +18,7 @@
 
 #include <rmm/exec_policy.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/copy.h>
 
 struct ColumnDeviceViewTest : public cudf::test::BaseFixture {};
diff --git a/cpp/tests/copying/shift_tests.cpp b/cpp/tests/copying/shift_tests.cpp
index ae4a12e4f12b..a3c9cad9e9c4 100644
--- a/cpp/tests/copying/shift_tests.cpp
+++ b/cpp/tests/copying/shift_tests.cpp
@@ -14,7 +14,7 @@
 #include <cudf/utilities/memory_resource.hpp>
 #include <cudf/utilities/traits.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <limits>
 #include <memory>
diff --git a/cpp/tests/join/join_tests.cpp b/cpp/tests/join/join_tests.cpp
index 0e835a467556..db625b8d35ad 100644
--- a/cpp/tests/join/join_tests.cpp
+++ b/cpp/tests/join/join_tests.cpp
@@ -29,7 +29,7 @@
 #include <rmm/device_uvector.hpp>
 #include <rmm/mr/statistics_resource_adaptor.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <algorithm>
 #include <future>
diff --git a/cpp/tests/join/semi_anti_join_tests.cpp b/cpp/tests/join/semi_anti_join_tests.cpp
index 541ec46ab744..11fb4af2a35c 100644
--- a/cpp/tests/join/semi_anti_join_tests.cpp
+++ b/cpp/tests/join/semi_anti_join_tests.cpp
@@ -24,7 +24,7 @@
 #include <rmm/mr/statistics_resource_adaptor.hpp>
 #include <rmm/resource_ref.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/iterator/transform_iterator.h>
 
 #include <limits>
diff --git a/cpp/tests/utilities/column_utilities.cu b/cpp/tests/utilities/column_utilities.cu
index 5d6b2664a651..862ac9372c04 100644
--- a/cpp/tests/utilities/column_utilities.cu
+++ b/cpp/tests/utilities/column_utilities.cu
@@ -30,7 +30,7 @@
 #include <cuda/std/cmath>
 #include <cuda/std/iterator>
 #include <cuda/std/limits>
-#include <cuda/stream_ref>
+#include <cuda/stream>
 #include <thrust/copy.h>
 #include <thrust/equal.h>
 #include <thrust/execution_policy.h>
diff --git a/cpp/tests/utilities/memory_resource_utilities.cpp b/cpp/tests/utilities/memory_resource_utilities.cpp
index 117758d670d3..06e57bb027a4 100644
--- a/cpp/tests/utilities/memory_resource_utilities.cpp
+++ b/cpp/tests/utilities/memory_resource_utilities.cpp
@@ -9,7 +9,7 @@
 
 #include <rmm/error.hpp>
 
-#include <cuda/stream_ref>
+#include <cuda/stream>
 
 #include <cstddef>
 #include <utility>