tighten wheel size limits, expand CI-skipping logic, other small build changes

.github/workflows/pr.yaml

@@ -61,37 +61,146 @@ jobs:
     uses: rapidsai/shared-workflows/.github/workflows/changed-files.yaml@main
     with:
       files_yaml: |
+        build_docs:
+          - '**'
+          - '!.devcontainer/**'
+          - '!.git-blame-ignore-revs'
+          - '!.github/CODEOWNERS'
+          - '!.github/ISSUE_TEMPLATE/**'
+          - '!.github/copy-pr-bot.yaml'
+          - '!.github/labeler.yml'
+          - '!.github/ops-bot.yaml'
+          - '!.github/release.yml'
+          - '!.github/workflows/new-issues-to-triage-projects.yml'
+          - '!.github/workflows/pr_assign_author.yml'
+          - '!.github/workflows/pr_issue_status_automation.yml'
+          - '!.github/workflows/trigger-breaking-change-alert.yaml'
+          - '!.pre-commit-config.yaml'
+          - '!ci/build_wheel*.sh'
+          - '!ci/check_style.sh'
+          - '!ci/release/update-version.sh'
+          - '!ci/test_notebooks.sh'
+          - '!ci/test_python*.sh'
+          - '!ci/test_wheel*.sh'
+          - '!codecov.yml'
         test_cpp:
           - '**'
           - '!.devcontainer/**'
+          - '!.git-blame-ignore-revs'
+          - '!.github/CODEOWNERS'
+          - '!.github/ISSUE_TEMPLATE/**'
+          - '!.github/copy-pr-bot.yaml'
+          - '!.github/labeler.yml'
+          - '!.github/ops-bot.yaml'
+          - '!.github/release.yml'
+          - '!.github/workflows/new-issues-to-triage-projects.yml'
+          - '!.github/workflows/pr_assign_author.yml'
+          - '!.github/workflows/pr_issue_status_automation.yml'
+          - '!.github/workflows/trigger-breaking-change-alert.yaml'
           - '!.pre-commit-config.yaml'
+          - '!BUILD.md'
           - '!CONTRIBUTING.md'
           - '!README.md'
+          - '!ci/build_docs.sh'
+          - '!ci/build_python.sh'
+          - '!ci/build_wheel*.sh'
+          - '!ci/check_style.sh'
+          - '!ci/notebooks/**'
           - '!ci/release/update-version.sh'
+          - '!ci/test_notebooks.sh'
+          - '!ci/test_python*.sh'
+          - '!ci/test_wheel*.sh'
           - '!docs/**'
           - '!img/**'
           - '!notebooks/**'
           - '!python/**'
           - '!thirdparty/LICENSES/**'
+          - '!wiki/**'
         test_notebooks:
           - '**'
           - '!.devcontainer/**'
+          - '!.git-blame-ignore-revs'
+          - '!.github/CODEOWNERS'
+          - '!.github/ISSUE_TEMPLATE/**'
+          - '!.github/copy-pr-bot.yaml'
+          - '!.github/labeler.yml'
+          - '!.github/ops-bot.yaml'
+          - '!.github/release.yml'
+          - '!.github/workflows/new-issues-to-triage-projects.yml'
+          - '!.github/workflows/pr_assign_author.yml'
+          - '!.github/workflows/pr_issue_status_automation.yml'
+          - '!.github/workflows/trigger-breaking-change-alert.yaml'
           - '!.pre-commit-config.yaml'
+          - '!BUILD.md'
           - '!CONTRIBUTING.md'
           - '!README.md'
+          - '!ci/check_style.sh'
           - '!ci/release/update-version.sh'
           - '!thirdparty/LICENSES/**'
-        test_python:
+          - '!wiki/**'
+        test_python_conda:
           - '**'
           - '!.devcontainer/**'
+          - '!.git-blame-ignore-revs'
+          - '!.github/CODEOWNERS'
+          - '!.github/ISSUE_TEMPLATE/**'
+          - '!.github/copy-pr-bot.yaml'
+          - '!.github/labeler.yml'
+          - '!.github/ops-bot.yaml'
+          - '!.github/release.yml'
+          - '!.github/workflows/new-issues-to-triage-projects.yml'
+          - '!.github/workflows/pr_assign_author.yml'
+          - '!.github/workflows/pr_issue_status_automation.yml'
+          - '!.github/workflows/trigger-breaking-change-alert.yaml'
           - '!.pre-commit-config.yaml'
+          - '!BUILD.md'
           - '!CONTRIBUTING.md'
           - '!README.md'
+          - '!ci/build_wheel*.sh'
+          - '!ci/check_style.sh'
           - '!ci/release/update-version.sh'
+          - '!ci/run_clang_tidy.sh'
+          - '!ci/run_ctests.sh'
+          - '!ci/test_wheel*.sh'
+          - '!ci/validate_wheel.sh'
           - '!docs/**'
           - '!img/**'
           - '!notebooks/**'
           - '!thirdparty/LICENSES/**'
+          - '!wiki/**'
+        test_python_wheels:
+          - '**'
+          - '!.devcontainer/**'
+          - '!.git-blame-ignore-revs'
+          - '!.github/CODEOWNERS'
+          - '!.github/ISSUE_TEMPLATE/**'
+          - '!.github/copy-pr-bot.yaml'
+          - '!.github/labeler.yml'
+          - '!.github/ops-bot.yaml'
+          - '!.github/release.yml'
+          - '!.github/workflows/new-issues-to-triage-projects.yml'
+          - '!.github/workflows/pr_assign_author.yml'
+          - '!.github/workflows/pr_issue_status_automation.yml'
+          - '!.github/workflows/trigger-breaking-change-alert.yaml'
+          - '!.pre-commit-config.yaml'
+          - '!BUILD.md'
+          - '!CONTRIBUTING.md'
+          - '!README.md'
+          - '!ci/build_cpp.sh'
+          - '!ci/build_python.sh'
+          - '!ci/check_style.sh'
+          - '!ci/notebooks/**'
+          - '!ci/release/update-version.sh'
+          - '!ci/run_clang_tidy.sh'
+          - '!ci/run_tests.sh'
+          - '!ci/test_cpp.sh'
+          - '!ci/test_notebooks.sh'
+          - '!ci/test_python*.sh'
+          - '!docs/**'
+          - '!img/**'
+          - '!notebooks/**'
+          - '!thirdparty/LICENSES/**'
+          - '!wiki/**'
   checks:
     secrets: inherit
     needs: telemetry-setup
@@ -145,7 +254,7 @@ jobs:
     needs: [conda-python-build, changed-files]
     secrets: inherit
     uses: rapidsai/shared-workflows/.github/workflows/conda-python-tests.yaml@main
-    if: fromJSON(needs.changed-files.outputs.changed_file_groups).test_python
+    if: fromJSON(needs.changed-files.outputs.changed_file_groups).test_python_conda
     with:
       build_type: pull-request
       script: "ci/test_python_singlegpu.sh"
@@ -154,7 +263,7 @@ jobs:
     needs: [conda-python-build, changed-files]
     secrets: inherit
     uses: rapidsai/shared-workflows/.github/workflows/conda-python-tests.yaml@main
-    if: fromJSON(needs.changed-files.outputs.changed_file_groups).test_python
+    if: fromJSON(needs.changed-files.outputs.changed_file_groups).test_python_conda
     with:
       # Select the amd64 entry with the highest CUDA and Python version
       matrix_filter: map(select(.ARCH=="amd64")) | [max_by([.CUDA_VER,.PY_VER]|map(split(".")|map(tonumber)))]
@@ -165,7 +274,7 @@ jobs:
     needs: [conda-python-build, changed-files]
     secrets: inherit
     uses: rapidsai/shared-workflows/.github/workflows/conda-python-tests.yaml@main
-    if: fromJSON(needs.changed-files.outputs.changed_file_groups).test_python
+    if: fromJSON(needs.changed-files.outputs.changed_file_groups).test_python_conda
     with:
       build_type: pull-request
       script: "ci/test_python_dask.sh"
@@ -174,7 +283,7 @@ jobs:
     needs: [conda-python-build, changed-files]
     secrets: inherit
     uses: rapidsai/shared-workflows/.github/workflows/conda-python-tests.yaml@main
-    if: fromJSON(needs.changed-files.outputs.changed_file_groups).test_python
+    if: fromJSON(needs.changed-files.outputs.changed_file_groups).test_python_conda
     with:
       build_type: pull-request
       script: "ci/test_python_scikit_learn_tests.sh"
@@ -196,7 +305,7 @@ jobs:
     needs: [conda-python-build, changed-files]
     secrets: inherit
     uses: rapidsai/shared-workflows/.github/workflows/conda-python-tests.yaml@main
-    if: fromJSON(needs.changed-files.outputs.changed_file_groups).test_python
+    if: fromJSON(needs.changed-files.outputs.changed_file_groups).test_python_conda
     with:
       build_type: pull-request
       script: "ci/test_python_cuml_accel_upstream.sh"
@@ -215,9 +324,10 @@ jobs:
       container_image: "rapidsai/ci-conda:26.04-latest"
       script: "ci/test_notebooks.sh"
   docs-build:
-    needs: conda-python-build
+    needs: [conda-python-build, changed-files]
     secrets: inherit
     uses: rapidsai/shared-workflows/.github/workflows/custom-job.yaml@main
+    if: fromJSON(needs.changed-files.outputs.changed_file_groups).build_docs
     with:
       build_type: pull-request
       node_type: "gpu-l4-latest-1"
@@ -255,7 +365,7 @@ jobs:
     needs: [wheel-build-cuml, changed-files]
     secrets: inherit
     uses: rapidsai/shared-workflows/.github/workflows/wheels-test.yaml@main
-    if: fromJSON(needs.changed-files.outputs.changed_file_groups).test_python
+    if: fromJSON(needs.changed-files.outputs.changed_file_groups).test_python_wheels
     with:
       build_type: pull-request
       script: ci/test_wheel.sh
@@ -264,7 +374,7 @@ jobs:
     needs: [wheel-build-cuml, changed-files]
     secrets: inherit
     uses: rapidsai/shared-workflows/.github/workflows/wheels-test.yaml@main
-    if: fromJSON(needs.changed-files.outputs.changed_file_groups).test_python
+    if: fromJSON(needs.changed-files.outputs.changed_file_groups).test_python_wheels
     with:
       build_type: pull-request
       script: ci/test_wheel_dask.sh

.pre-commit-config.yaml

@@ -1,5 +1,5 @@
 ---
-# SPDX-FileCopyrightText: Copyright (c) 2023-2025, NVIDIA CORPORATION.
+# SPDX-FileCopyrightText: Copyright (c) 2023-2026, NVIDIA CORPORATION.
 # SPDX-License-Identifier: Apache-2.0
 
 repos:
@@ -107,7 +107,7 @@ repos:
             args: ['format', '--cleanup']
             additional_dependencies: ['pyyaml>=6.0', 'packaging>=21.0']
     - repo: https://github.com/rapidsai/pre-commit-hooks
-      rev: v1.1.0
+      rev: v1.3.3
       hooks:
         - id: verify-copyright
           name: verify-copyright-cuml
@@ -164,6 +164,12 @@ repos:
         - id: verify-alpha-spec
         - id: verify-codeowners
           args: [--fix, --project-prefix=cuml]
+        - id: verify-pyproject-license
+          # ignore the top-level pyproject.toml, which doesn't
+          # have or need a [project] table
+          exclude: |
+            (?x)
+              ^pyproject[.]toml$
     - repo: https://github.com/rapidsai/dependency-file-generator
       rev: v1.20.0
       hooks:

ci/build_wheel.sh

@@ -9,6 +9,8 @@ package_dir=$2
 
 source rapids-configure-sccache
 source rapids-date-string
+RAPIDS_INIT_PIP_REMOVE_NVIDIA_INDEX="true"
+export RAPIDS_INIT_PIP_REMOVE_NVIDIA_INDEX
 source rapids-init-pip
 
 export SCCACHE_S3_PREPROCESSOR_CACHE_KEY_PREFIX="${package_name}/${RAPIDS_CONDA_ARCH}/cuda${RAPIDS_CUDA_VERSION%%.*}/wheel/preprocessor-cache"
@@ -32,7 +34,7 @@ RAPIDS_PIP_WHEEL_ARGS=(
 #
 # Passing '--build-constraint' and '--no-build-isolation` together results in an error from 'pip',
 # but we want to keep environment variable PIP_CONSTRAINT set unconditionally.
-# PIP_NO_BUILD_ISOLATION=0 means "add --no-build-isolation" (ref: https://github.com/pypa/pip/issues/573
+# PIP_NO_BUILD_ISOLATION=0 means "add --no-build-isolation" (ref: https://github.com/pypa/pip/issues/5735)
 if [[ "${PIP_NO_BUILD_ISOLATION:-}" != "0" ]]; then
     RAPIDS_PIP_WHEEL_ARGS+=(--build-constraint="${PIP_CONSTRAINT}")
 fi

ci/build_wheel_cuml.sh

@@ -4,6 +4,8 @@
 
 set -euo pipefail
 
+RAPIDS_INIT_PIP_REMOVE_NVIDIA_INDEX="true"
+export RAPIDS_INIT_PIP_REMOVE_NVIDIA_INDEX
 source rapids-init-pip
 
 package_name="cuml"

ci/build_wheel_libcuml.sh

@@ -1,9 +1,11 @@
 #!/bin/bash
-# SPDX-FileCopyrightText: Copyright (c) 2025, NVIDIA CORPORATION.
+# SPDX-FileCopyrightText: Copyright (c) 2025-2026, NVIDIA CORPORATION.
 # SPDX-License-Identifier: Apache-2.0
 
 set -euo pipefail
 
+RAPIDS_INIT_PIP_REMOVE_NVIDIA_INDEX="true"
+export RAPIDS_INIT_PIP_REMOVE_NVIDIA_INDEX
 source rapids-init-pip
 
 package_name="libcuml"

ci/test_wheel.sh

@@ -1,9 +1,11 @@
 #!/bin/bash
-# SPDX-FileCopyrightText: Copyright (c) 2023-2025, NVIDIA CORPORATION.
+# SPDX-FileCopyrightText: Copyright (c) 2023-2026, NVIDIA CORPORATION.
 # SPDX-License-Identifier: Apache-2.0
 
 set -euo pipefail
 
+RAPIDS_INIT_PIP_REMOVE_NVIDIA_INDEX="true"
+export RAPIDS_INIT_PIP_REMOVE_NVIDIA_INDEX
 source rapids-init-pip
 
 RAPIDS_PY_CUDA_SUFFIX="$(rapids-wheel-ctk-name-gen "${RAPIDS_CUDA_VERSION}")"

ci/test_wheel_dask.sh

@@ -1,9 +1,11 @@
 #!/bin/bash
-# SPDX-FileCopyrightText: Copyright (c) 2025, NVIDIA CORPORATION.
+# SPDX-FileCopyrightText: Copyright (c) 2025-2026, NVIDIA CORPORATION.
 # SPDX-License-Identifier: Apache-2.0
 
 set -euo pipefail
 
+RAPIDS_INIT_PIP_REMOVE_NVIDIA_INDEX="true"
+export RAPIDS_INIT_PIP_REMOVE_NVIDIA_INDEX
 source rapids-init-pip
 
 RAPIDS_PY_CUDA_SUFFIX="$(rapids-wheel-ctk-name-gen "${RAPIDS_CUDA_VERSION}")"

ci/test_wheel_integrations.sh

@@ -4,6 +4,8 @@
 
 set -euo pipefail
 
+RAPIDS_INIT_PIP_REMOVE_NVIDIA_INDEX="true"
+export RAPIDS_INIT_PIP_REMOVE_NVIDIA_INDEX
 source rapids-init-pip
 
 RAPIDS_PY_CUDA_SUFFIX="$(rapids-wheel-ctk-name-gen "${RAPIDS_CUDA_VERSION}")"

ci/validate_wheel.sh

@@ -1,18 +1,40 @@
 #!/bin/bash
-# SPDX-FileCopyrightText: Copyright (c) 2024-2025, NVIDIA CORPORATION.
+# SPDX-FileCopyrightText: Copyright (c) 2024-2026, NVIDIA CORPORATION.
 # SPDX-License-Identifier: Apache-2.0
 
 set -euo pipefail
 
 package_dir=$1
 wheel_dir_relative_path=$2
 
+RAPIDS_CUDA_MAJOR="${RAPIDS_CUDA_VERSION%%.*}"
+
 cd "${package_dir}"
 
 rapids-logger "validate packages with 'pydistcheck'"
 
+PYDISTCHECK_ARGS=(
+    --inspect
+)
+
+# PyPI hard limit is 1GiB, but try to keep these as small as possible
+if [[ "${package_dir}" == "python/libcuml" ]]; then
+    if [[ "${RAPIDS_CUDA_MAJOR}" == "12" ]]; then
+        PYDISTCHECK_ARGS+=(
+            --max-allowed-size-compressed '475Mi'
+        )
+    else
+        PYDISTCHECK_ARGS+=(
+            --max-allowed-size-compressed '275Mi'
+        )
+    fi
+elif [[ "${package_dir}" != "python/cuml" ]]; then
+    rapids-echo-stderr "unrecognized package_dir: '${package_dir}'"
+    exit 1
+fi
+
 pydistcheck \
-    --inspect \
+    "${PYDISTCHECK_ARGS[@]}" \
     "$(echo "${wheel_dir_relative_path}"/*.whl)"
 
 rapids-logger "validate packages with 'twine'"