[backport] [CI] Build a CPU-only wheel under name xgboost-cpu (#10603…

…) (#10614)

* [CI] Build a CPU-only wheel under name `xgboost-cpu` (#10603)

* [CI] Fix test environment. (#10609)

* [CI] Fix test environment.

* Remove shell.

* Remove.

* Update Dockerfile.i386

* replace channel for sycl dependencies (#10576)

Co-authored-by: Dmitry Razdoburdin <>

* Optionally skip cupy on windows. (#10611)

---------

Co-authored-by: Jiaming Yuan <[email protected]>
Co-authored-by: Dmitry Razdoburdin <[email protected]>

.github/workflows/i386.yml

@@ -23,7 +23,7 @@ jobs:
       with:
         submodules: 'true'
     - name: Set up Docker Buildx
-      uses: docker/setup-buildx-action@v3
+      uses: docker/setup-buildx-action@v3.4.0
       with:
         driver-opts: network=host
     - name: Build and push container

dev/release-artifacts.py

@@ -2,6 +2,7 @@
 
 tqdm, sh are required to run this script.
 """
+
 import argparse
 import os
 import shutil
@@ -106,6 +107,15 @@ def make_pysrc_wheel(
     if not os.path.exists(dist):
         os.mkdir(dist)
 
+    # Apply patch to remove NCCL dependency
+    # Save the original content of pyproject.toml so that we can restore it later
+    with DirectoryExcursion(ROOT):
+        with open("python-package/pyproject.toml", "r") as f:
+            orig_pyproj_lines = f.read()
+        with open("tests/buildkite/remove_nccl_dep.patch", "r") as f:
+            patch_lines = f.read()
+        subprocess.run(["patch", "-p0"], input=patch_lines, text=True)
+
     with DirectoryExcursion(os.path.join(ROOT, "python-package")):
         subprocess.check_call(["python", "-m", "build", "--sdist"])
         if rc is not None:
@@ -117,6 +127,10 @@ def make_pysrc_wheel(
         target = os.path.join(dist, name)
         shutil.move(src, target)
 
+    with DirectoryExcursion(ROOT):
+        with open("python-package/pyproject.toml", "w") as f:
+            print(orig_pyproj_lines, file=f, end="")
+
 
 def download_py_packages(
     branch: str, major: int, minor: int, commit_hash: str, outdir: str

doc/install.rst

@@ -76,6 +76,19 @@ Capabilities of binary wheels for each platform:
 | Windows             | |tick|  |  |cross|             |
 +---------------------+---------+----------------------+
 
+Minimal installation (CPU-only)
+*******************************
+The default installation with ``pip`` will install the full XGBoost package, including the support for the GPU algorithms and federated learning.
+
+You may choose to reduce the size of the installed package and save the disk space, by opting to install ``xgboost-cpu`` instead:
+
+.. code-block:: bash
+
+  pip install xgboost-cpu
+
+The ``xgboost-cpu`` variant will have drastically smaller disk footprint, but does not provide some features, such as the GPU algorithms and
+federated learning.
+
 Conda
 *****
 

python-package/pyproject.toml

@@ -7,13 +7,13 @@ build-backend = "packager.pep517"
 
 [project]
 name = "xgboost"
-version = "2.1.0"
+description = "XGBoost Python Package"
+readme = { file = "README.rst", content-type = "text/x-rst" }
 authors = [
     { name = "Hyunsu Cho", email = "[email protected]" },
     { name = "Jiaming Yuan", email = "[email protected]" }
 ]
-description = "XGBoost Python Package"
-readme = { file = "README.rst", content-type = "text/x-rst" }
+version = "2.1.0"
 requires-python = ">=3.8"
 license = { text = "Apache-2.0" }
 classifiers = [

python-package/xgboost/testing/__init__.py

@@ -45,6 +45,7 @@
     get_cancer,
     get_digits,
     get_sparse,
+    make_batches,
     memory,
 )
 
@@ -161,7 +162,16 @@ def no_cudf() -> PytestSkip:
 
 
 def no_cupy() -> PytestSkip:
-    return no_mod("cupy")
+    skip_cupy = no_mod("cupy")
+    if not skip_cupy["condition"] and system() == "Windows":
+        import cupy as cp
+
+        # Cupy might run into issue on Windows due to missing compiler
+        try:
+            cp.array([1, 2, 3]).sum()
+        except Exception:  # pylint: disable=broad-except
+            skip_cupy["condition"] = True
+    return skip_cupy
 
 
 def no_dask_cudf() -> PytestSkip:
@@ -247,34 +257,6 @@ def as_arrays(
         return X, y, w
 
 
-def make_batches(
-    n_samples_per_batch: int,
-    n_features: int,
-    n_batches: int,
-    use_cupy: bool = False,
-    *,
-    vary_size: bool = False,
-) -> Tuple[List[np.ndarray], List[np.ndarray], List[np.ndarray]]:
-    X = []
-    y = []
-    w = []
-    if use_cupy:
-        import cupy
-
-        rng = cupy.random.RandomState(1994)
-    else:
-        rng = np.random.RandomState(1994)
-    for i in range(n_batches):
-        n_samples = n_samples_per_batch + i * 10 if vary_size else n_samples_per_batch
-        _X = rng.randn(n_samples, n_features)
-        _y = rng.randn(n_samples)
-        _w = rng.uniform(low=0, high=1, size=n_samples)
-        X.append(_X)
-        y.append(_y)
-        w.append(_w)
-    return X, y, w
-
-
 def make_regression(
     n_samples: int, n_features: int, use_cupy: bool
 ) -> Tuple[ArrayLike, ArrayLike, ArrayLike]:

python-package/xgboost/testing/data.py

@@ -9,6 +9,7 @@
     Callable,
     Dict,
     Generator,
+    List,
     NamedTuple,
     Optional,
     Tuple,
@@ -501,6 +502,36 @@ def get_mq2008(
     )
 
 
+def make_batches(  # pylint: disable=too-many-arguments,too-many-locals
+    n_samples_per_batch: int,
+    n_features: int,
+    n_batches: int,
+    use_cupy: bool = False,
+    *,
+    vary_size: bool = False,
+    random_state: int = 1994,
+) -> Tuple[List[np.ndarray], List[np.ndarray], List[np.ndarray]]:
+    """Make batches of dense data."""
+    X = []
+    y = []
+    w = []
+    if use_cupy:
+        import cupy  # pylint: disable=import-error
+
+        rng = cupy.random.RandomState(random_state)
+    else:
+        rng = np.random.RandomState(random_state)
+    for i in range(n_batches):
+        n_samples = n_samples_per_batch + i * 10 if vary_size else n_samples_per_batch
+        _X = rng.randn(n_samples, n_features)
+        _y = rng.randn(n_samples)
+        _w = rng.uniform(low=0, high=1, size=n_samples)
+        X.append(_X)
+        y.append(_y)
+        w.append(_w)
+    return X, y, w
+
+
 RelData = Tuple[sparse.csr_matrix, npt.NDArray[np.int32], npt.NDArray[np.int32]]
 
 

tests/buildkite/build-manylinux2014.sh

@@ -0,0 +1,63 @@
+#!/bin/bash
+
+set -euo pipefail
+
+if [ $# -ne 1 ]; then
+  echo "Usage: $0 {x86_64,aarch64}"
+  exit 1
+fi
+
+arch=$1
+
+source tests/buildkite/conftest.sh
+
+WHEEL_TAG="manylinux2014_${arch}"
+command_wrapper="tests/ci_build/ci_build.sh ${WHEEL_TAG}"
+python_bin="/opt/python/cp310-cp310/bin/python"
+
+echo "--- Build binary wheel for ${WHEEL_TAG}"
+# Patch to add warning about manylinux2014 variant
+patch -p0 < tests/buildkite/remove_nccl_dep.patch
+patch -p0 < tests/buildkite/manylinux2014_warning.patch
+$command_wrapper bash -c \
+  "cd python-package && ${python_bin} -m pip wheel --no-deps -v . --wheel-dir dist/"
+git checkout python-package/pyproject.toml python-package/xgboost/core.py  # discard the patch
+
+$command_wrapper auditwheel repair --plat ${WHEEL_TAG} python-package/dist/*.whl
+$command_wrapper ${python_bin} tests/ci_build/rename_whl.py  \
+  --wheel-path wheelhouse/*.whl  \
+  --commit-hash ${BUILDKITE_COMMIT}  \
+  --platform-tag ${WHEEL_TAG}
+rm -rf python-package/dist/
+mkdir python-package/dist/
+mv -v wheelhouse/*.whl python-package/dist/
+
+echo "--- Build binary wheel for ${WHEEL_TAG} (CPU only)"
+# Patch to rename pkg to xgboost-cpu
+patch -p0 < tests/buildkite/remove_nccl_dep.patch
+patch -p0 < tests/buildkite/cpu_only_pypkg.patch
+$command_wrapper bash -c \
+  "cd python-package && ${python_bin} -m pip wheel --no-deps -v . --wheel-dir dist/"
+git checkout python-package/pyproject.toml  # discard the patch
+
+$command_wrapper auditwheel repair --plat ${WHEEL_TAG} python-package/dist/xgboost_cpu-*.whl
+$command_wrapper ${python_bin} tests/ci_build/rename_whl.py  \
+  --wheel-path wheelhouse/xgboost_cpu-*.whl  \
+  --commit-hash ${BUILDKITE_COMMIT}  \
+  --platform-tag ${WHEEL_TAG}
+rm -v python-package/dist/xgboost_cpu-*.whl
+mv -v wheelhouse/xgboost_cpu-*.whl python-package/dist/
+
+echo "--- Upload Python wheel"
+for wheel in python-package/dist/*.whl
+do
+  buildkite-agent artifact upload "${wheel}"
+done
+if [[ ($is_pull_request == 0) && ($is_release_branch == 1) ]]
+then
+  for wheel in python-package/dist/*.whl
+  do
+    aws s3 cp "${wheel}" s3://xgboost-nightly-builds/${BRANCH_NAME}/ \
+      --acl public-read --no-progress
+  done
+fi

tests/buildkite/cpu_only_pypkg.patch

@@ -0,0 +1,55 @@
+diff --git python-package/README.rst python-package/README.rst
+index 1fc0bb5a0..f1c68470b 100644
+--- python-package/README.rst
++++ python-package/README.rst
+@@ -1,20 +1,15 @@
+-======================
+-XGBoost Python Package
+-======================
++=================================
++XGBoost Python Package (CPU only)
++=================================
+
+ |PyPI version|
+
+-Installation
+-============
++The ``xgboost-cpu`` package provides for a minimal installation, with no support for the GPU algorithms
++or federated learning. It is provided to allow XGBoost to be installed in a space-constrained
++environments.
+
+-From `PyPI <https://pypi.python.org/pypi/xgboost>`_
+----------------------------------------------------
++Note. ``xgboost-cpu`` package is only provided for x86_64 (amd64) Linux and Windows platforms.
++For other platforms, please install ``xgboost`` from https://pypi.org/project/xgboost/.
+
+-For a stable version, install using ``pip``::
+-
+-    pip install xgboost
+-
+-.. |PyPI version| image:: https://badge.fury.io/py/xgboost.svg
+-   :target: http://badge.fury.io/py/xgboost
+-
+-For building from source, see `build <https://xgboost.readthedocs.io/en/latest/build.html>`_.
++Note. ``xgboost-cpu`` does not provide an sdist (source distribution). You may install sdist
++from https://pypi.org/project/xgboost/.
+diff --git python-package/pyproject.toml python-package/pyproject.toml
+index 46c1451c2..c5dc908d9 100644
+--- python-package/pyproject.toml
++++ python-package/pyproject.toml
+@@ -6,7 +6,7 @@ backend-path = ["."]
+ build-backend = "packager.pep517"
+
+ [project]
+-name = "xgboost"
++name = "xgboost-cpu"
+ description = "XGBoost Python Package"
+ readme = { file = "README.rst", content-type = "text/x-rst" }
+ authors = [
+@@ -82,3 +82,6 @@ class-attribute-naming-style = "snake_case"
+
+ # Allow single-letter variables
+ variable-rgx = "[a-zA-Z_][a-z0-9_]{0,30}$"
++
++[tool.hatch.build.targets.wheel]
++packages = ["xgboost/"]

tests/buildkite/manylinux2014_warning.patch

@@ -1,17 +1,3 @@
-diff --git python-package/pyproject.toml python-package/pyproject.toml
-index a273d8c13..dee49686a 100644
---- python-package/pyproject.toml
-+++ python-package/pyproject.toml
-@@ -30,8 +30,7 @@ classifiers = [
- ]
- dependencies = [
-     "numpy",
--    "scipy",
--    "nvidia-nccl-cu12 ; platform_system == 'Linux' and platform_machine != 'aarch64'"
-+    "scipy"
- ]
-
- [project.urls]
 diff --git python-package/xgboost/core.py python-package/xgboost/core.py
 index e8bc735e6..030972ef2 100644
 --- python-package/xgboost/core.py