doc.

dmlc · Oct 16, 2024 · e8e9481 · e8e9481
1 parent ce64ac9
commit e8e9481
Show file tree

Hide file tree

Showing 4 changed files with 5 additions and 3 deletions.
diff --git a/doc/parameter.rst b/doc/parameter.rst
@@ -245,7 +245,7 @@ Parameters for Non-Exact Tree Methods
     trees. After 3.0, this parameter affects GPU algorithms as well.
 
 
-* ``extmem_concat_pages``, [default = ``false``]
+* ``extmem_single_page``, [default = ``false``]
 
   This parameter is only used for the ``hist`` tree method with ``device=cuda`` and
   ``subsample != 1.0``. Before 3.0, pages were always concatenated.

diff --git a/doc/tutorials/external_memory.rst b/doc/tutorials/external_memory.rst
@@ -25,7 +25,7 @@ The external memory support has undergone multiple development iterations. Like
 :py:class:`~xgboost.QuantileDMatrix` with :py:class:`~xgboost.DataIter`, XGBoost loads
 data batch-by-batch using a custom iterator supplied by the user. However, unlike the
 :py:class:`~xgboost.QuantileDMatrix`, external memory does not concatenate the batches
-(unless specified by the ``extmem_concat_pages``) . Instead, it caches all batches in the
+(unless specified by the ``extmem_single_page``) . Instead, it caches all batches in the
 external memory and fetch them on-demand. Go to the end of the document to see a
 comparison between :py:class:`~xgboost.QuantileDMatrix` and the external memory version of
 :py:class:`~xgboost.ExtMemQuantileDMatrix`.

diff --git a/include/xgboost/c_api.h b/include/xgboost/c_api.h
@@ -351,7 +351,7 @@ XGB_DLL int XGDMatrixCreateFromCudaArrayInterface(char const *data, char const *
 
 /*! \brief handle to a external data iterator */
 typedef void *DataIterHandle;  // NOLINT(*)
-/*! \brief handle to a internal data holder. */
+/** @brief handle to an internal data holder. */
 typedef void *DataHolderHandle;  // NOLINT(*)
 
 

diff --git a/src/data/quantile_dmatrix.cu b/src/data/quantile_dmatrix.cu
@@ -2,6 +2,7 @@
  * Copyright 2020-2024, XGBoost Contributors
  */
 #include <algorithm>  // for max
+#include <limits>     // for numeric_limits
 #include <numeric>    // for partial_sum
 #include <utility>    // for pair
 #include <vector>     // for vector
@@ -97,6 +98,7 @@ void MakeSketches(Context const* ctx,
       }
       if (sketches.back().second > (1ul << (sketches.size() - 1)) ||
           sketches.back().second == static_cast<bst_idx_t>(max_quantile_blocks)) {
+        // Cut the sub-stream.
         auto n_cuts_per_feat =
             common::detail::RequiredSampleCutsPerColumn(p.max_bin, ext_info.accumulated_rows);
         // Prune to a single block