Merge pull request #1109 from rapidsai/branch-23.02

[RELEASE] dask-cuda v23.02

.github/CODEOWNERS

@@ -2,8 +2,9 @@
 dask_cuda/  @rapidsai/daskcuda-python-codeowners
 
 #build/ops code owners
-.github/           @rapidsai/ops-codeowners 
+.github/           @rapidsai/ops-codeowners
 ci/                @rapidsai/ops-codeowners
 conda/             @rapidsai/ops-codeowners
 **/Dockerfile      @rapidsai/ops-codeowners
 **/.dockerignore   @rapidsai/ops-codeowners
+dependencies.yaml  @rapidsai/ops-codeowners

.github/ops-bot.yaml

@@ -5,4 +5,5 @@ auto_merger: true
 branch_checker: true
 label_checker: true
 release_drafter: true
-external_contributors: false
+copy_prs: true
+recently_updated: true

.github/workflows/build.yaml

@@ -0,0 +1,74 @@
+name: build
+
+on:
+  push:
+    branches:
+      - "branch-*"
+    tags:
+      - v[0-9][0-9].[0-9][0-9].[0-9][0-9]
+  workflow_dispatch:
+    inputs:
+      branch:
+        required: true
+        type: string
+      date:
+        required: true
+        type: string
+      sha:
+        required: true
+        type: string
+      build_type:
+        type: string
+        default: nightly
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  conda-python-build:
+    secrets: inherit
+    uses: rapidsai/shared-action-workflows/.github/workflows/[email protected]
+    with:
+      build_type: ${{ inputs.build_type || 'branch' }}
+      branch: ${{ inputs.branch }}
+      date: ${{ inputs.date }}
+      sha: ${{ inputs.sha }}
+  docs-build:
+    if: ${{ startsWith(github.ref, 'refs/heads/branch-') }}
+    needs: [conda-python-build]
+    secrets: inherit
+    uses: rapidsai/shared-action-workflows/.github/workflows/[email protected]
+    with:
+      build_type: branch
+      node_type: "gpu-latest-1"
+      arch: "amd64"
+      container_image: "rapidsai/ci:latest"
+      run_script: "ci/build_docs.sh"
+  upload-conda:
+    needs: [conda-python-build]
+    secrets: inherit
+    uses: rapidsai/shared-action-workflows/.github/workflows/[email protected]
+    with:
+      build_type: ${{ inputs.build_type || 'branch' }}
+      branch: ${{ inputs.branch }}
+      date: ${{ inputs.date }}
+      sha: ${{ inputs.sha }}
+  wheel-build:
+    runs-on: ubuntu-latest
+    container:
+      image: rapidsai/ci:latest
+    defaults:
+      run:
+        shell: bash
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+      - name: Build wheel
+        run: ci/build_python_pypi.sh
+      - name: Publish distribution 📦 to PyPI
+        if: inputs.build_type == 'nightly'
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          password: ${{ secrets.RAPIDSAI_PYPI_TOKEN }}

.github/workflows/pr.yaml

@@ -0,0 +1,60 @@
+name: pr
+
+on:
+  push:
+    branches:
+      - "pull-request/[0-9]+"
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  pr-builder:
+    needs:
+      - checks
+      - conda-python-build
+      - conda-python-tests
+      - docs-build
+      - wheel-build
+    secrets: inherit
+    uses: rapidsai/shared-action-workflows/.github/workflows/[email protected]
+  checks:
+    secrets: inherit
+    uses: rapidsai/shared-action-workflows/.github/workflows/[email protected]
+  conda-python-build:
+    needs: checks
+    secrets: inherit
+    uses: rapidsai/shared-action-workflows/.github/workflows/[email protected]
+    with:
+      build_type: pull-request
+  conda-python-tests:
+    needs: conda-python-build
+    secrets: inherit
+    uses: rapidsai/shared-action-workflows/.github/workflows/[email protected]
+    with:
+      build_type: pull-request
+  docs-build:
+    needs: conda-python-build
+    secrets: inherit
+    uses: rapidsai/shared-action-workflows/.github/workflows/[email protected]
+    with:
+      build_type: pull-request
+      node_type: "gpu-latest-1"
+      arch: "amd64"
+      container_image: "rapidsai/ci:latest"
+      run_script: "ci/build_docs.sh"
+  wheel-build:
+    needs: checks
+    runs-on: ubuntu-latest
+    container:
+      image: rapidsai/ci:latest
+    defaults:
+      run:
+        shell: bash
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+      - name: Build wheel
+        run: ci/build_python_pypi.sh

.github/workflows/test.yaml

@@ -0,0 +1,24 @@
+name: test
+
+on:
+  workflow_dispatch:
+    inputs:
+      branch:
+        required: true
+        type: string
+      date:
+        required: true
+        type: string
+      sha:
+        required: true
+        type: string
+
+jobs:
+  conda-python-tests:
+    secrets: inherit
+    uses: rapidsai/shared-action-workflows/.github/workflows/[email protected]
+    with:
+      build_type: nightly
+      branch: ${{ inputs.branch }}
+      date: ${{ inputs.date }}
+      sha: ${{ inputs.sha }}

.pre-commit-config.yaml

@@ -1,6 +1,11 @@
 repos:
+      - repo: https://github.com/pre-commit/pre-commit-hooks
+        rev: v4.3.0
+        hooks:
+              - id: trailing-whitespace
+              - id: end-of-file-fixer
       - repo: https://github.com/pycqa/isort
-        rev: 5.10.1
+        rev: 5.12.0
         hooks:
               - id: isort
       - repo: https://github.com/ambv/black
@@ -11,5 +16,23 @@ repos:
         rev: 3.8.3
         hooks:
               - id: flake8
+      - repo: https://github.com/codespell-project/codespell
+        rev: v2.1.0
+        hooks:
+              - id: codespell
+                exclude: |
+                  (?x)^(
+                    .*test.*|
+                    ^CHANGELOG.md$|
+                    ^.*versioneer.py$
+                  )
+      - repo: https://github.com/pre-commit/mirrors-mypy
+        rev: 'v0.991'
+        hooks:
+              - id: mypy
+                additional_dependencies: [types-cachetools]
+                args: ["--module=dask_cuda", "--ignore-missing-imports"]
+                pass_filenames: false
+
 default_language_version:
       python: python3

.readthedocs.yml

@@ -4,4 +4,4 @@ sphinx:
   configuration: rtd/conf.py
 
 formats:
-  - htmlzip
+  - htmlzip

CHANGELOG.md

@@ -1,3 +1,44 @@
+# dask-cuda 23.02.00 (9 Feb 2023)
+
+## 🚨 Breaking Changes
+
+- Pin `dask` and `distributed` for release ([#1106](https://github.com/rapidsai/dask-cuda/pull/1106)) [@galipremsagar](https://github.com/galipremsagar)
+
+## 🐛 Bug Fixes
+
+- pre-commit: Update isort version to 5.12.0 ([#1098](https://github.com/rapidsai/dask-cuda/pull/1098)) [@wence-](https://github.com/wence-)
+- explicit-comms: don't mix `-` and `_` in config ([#1096](https://github.com/rapidsai/dask-cuda/pull/1096)) [@madsbk](https://github.com/madsbk)
+- Update `cudf.Buffer` pointer access method ([#1094](https://github.com/rapidsai/dask-cuda/pull/1094)) [@pentschev](https://github.com/pentschev)
+- Update tests for Python 3.10 ([#1086](https://github.com/rapidsai/dask-cuda/pull/1086)) [@pentschev](https://github.com/pentschev)
+- Use `pkgutil.iter_modules` to get un-imported module for `test_pre_import` ([#1085](https://github.com/rapidsai/dask-cuda/pull/1085)) [@charlesbluca](https://github.com/charlesbluca)
+- Make proxy tests with `LocalCUDACluster` asynchronous ([#1084](https://github.com/rapidsai/dask-cuda/pull/1084)) [@pentschev](https://github.com/pentschev)
+- Ensure consistent results from `safe_sizeof()` in test ([#1071](https://github.com/rapidsai/dask-cuda/pull/1071)) [@madsbk](https://github.com/madsbk)
+- Pass missing argument to groupby benchmark compute ([#1069](https://github.com/rapidsai/dask-cuda/pull/1069)) [@mattf](https://github.com/mattf)
+- Reorder channel priority. ([#1067](https://github.com/rapidsai/dask-cuda/pull/1067)) [@bdice](https://github.com/bdice)
+- Fix owner check when the owner is a cupy array ([#1061](https://github.com/rapidsai/dask-cuda/pull/1061)) [@wence-](https://github.com/wence-)
+
+## 🛠️ Improvements
+
+- Pin `dask` and `distributed` for release ([#1106](https://github.com/rapidsai/dask-cuda/pull/1106)) [@galipremsagar](https://github.com/galipremsagar)
+- Update shared workflow branches ([#1105](https://github.com/rapidsai/dask-cuda/pull/1105)) [@ajschmidt8](https://github.com/ajschmidt8)
+- Proxify: make duplicate check optional ([#1101](https://github.com/rapidsai/dask-cuda/pull/1101)) [@madsbk](https://github.com/madsbk)
+- Fix whitespace & add URLs in `pyproject.toml` ([#1092](https://github.com/rapidsai/dask-cuda/pull/1092)) [@jakirkham](https://github.com/jakirkham)
+- pre-commit: spell, whitespace, and mypy check ([#1091](https://github.com/rapidsai/dask-cuda/pull/1091)) [@madsbk](https://github.com/madsbk)
+- shuffle: use cuDF's `partition_by_hash()` when available ([#1090](https://github.com/rapidsai/dask-cuda/pull/1090)) [@madsbk](https://github.com/madsbk)
+- add initial docs build ([#1089](https://github.com/rapidsai/dask-cuda/pull/1089)) [@AjayThorve](https://github.com/AjayThorve)
+- Remove `--get-cluster-configuration` option, check for scheduler in `dask cuda config` ([#1088](https://github.com/rapidsai/dask-cuda/pull/1088)) [@charlesbluca](https://github.com/charlesbluca)
+- Add timeout to `pytest` command ([#1082](https://github.com/rapidsai/dask-cuda/pull/1082)) [@ajschmidt8](https://github.com/ajschmidt8)
+- shuffle-benchmark: add `--partition-distribution` ([#1081](https://github.com/rapidsai/dask-cuda/pull/1081)) [@madsbk](https://github.com/madsbk)
+- Ensure tests run for Python `3.10` ([#1080](https://github.com/rapidsai/dask-cuda/pull/1080)) [@ajschmidt8](https://github.com/ajschmidt8)
+- Use TrackingResourceAdaptor to get better debug info ([#1079](https://github.com/rapidsai/dask-cuda/pull/1079)) [@madsbk](https://github.com/madsbk)
+- Improve shuffle-benchmark ([#1074](https://github.com/rapidsai/dask-cuda/pull/1074)) [@madsbk](https://github.com/madsbk)
+- Update builds for CUDA `11.8` and Python `310` ([#1072](https://github.com/rapidsai/dask-cuda/pull/1072)) [@ajschmidt8](https://github.com/ajschmidt8)
+- Shuffle by partition to reduce memory usage significantly ([#1068](https://github.com/rapidsai/dask-cuda/pull/1068)) [@madsbk](https://github.com/madsbk)
+- Enable copy_prs. ([#1063](https://github.com/rapidsai/dask-cuda/pull/1063)) [@bdice](https://github.com/bdice)
+- Add GitHub Actions Workflows ([#1062](https://github.com/rapidsai/dask-cuda/pull/1062)) [@bdice](https://github.com/bdice)
+- Unpin `dask` and `distributed` for development ([#1060](https://github.com/rapidsai/dask-cuda/pull/1060)) [@galipremsagar](https://github.com/galipremsagar)
+- Switch to the new dask CLI ([#981](https://github.com/rapidsai/dask-cuda/pull/981)) [@jacobtomlinson](https://github.com/jacobtomlinson)
+
 # dask-cuda 22.12.00 (8 Dec 2022)
 
 ## 🚨 Breaking Changes

ci/build_docs.sh

@@ -0,0 +1,38 @@
+#!/bin/bash
+
+set -euo pipefail
+
+rapids-logger "Create test conda environment"
+. /opt/conda/etc/profile.d/conda.sh
+
+rapids-dependency-file-generator \
+    --output conda \
+    --file_key docs \
+    --matrix "cuda=${RAPIDS_CUDA_VERSION%.*};arch=$(arch);py=${RAPIDS_PY_VERSION}" | tee env.yaml
+
+rapids-mamba-retry env create --force -f env.yaml -n docs
+conda activate docs
+
+rapids-print-env
+
+rapids-logger "Downloading artifacts from previous jobs"
+
+PYTHON_CHANNEL=$(rapids-download-conda-from-s3 python)
+VERSION_NUMBER=$(rapids-get-rapids-version-from-git)
+
+rapids-mamba-retry install \
+    --channel "${PYTHON_CHANNEL}" \
+    dask-cuda
+
+# Build Python docs
+rapids-logger "Build Python docs"
+pushd docs
+sphinx-build -b dirhtml ./source _html
+sphinx-build -b text ./source _text
+popd
+
+if [[ "${RAPIDS_BUILD_TYPE}" == "branch" ]]; then
+  rapids-logger "Upload Docs to S3"
+  aws s3 sync --no-progress --delete docs/_html "s3://rapidsai-docs/dask-cuda/${VERSION_NUMBER}/html"
+  aws s3 sync --no-progress --delete docs/_text "s3://rapidsai-docs/dask-cuda/${VERSION_NUMBER}/txt"
+fi

ci/build_python.sh

@@ -0,0 +1,17 @@
+#!/bin/bash
+# Copyright (c) 2022, NVIDIA CORPORATION.
+
+set -euo pipefail
+
+source rapids-env-update
+
+export CMAKE_GENERATOR=Ninja
+
+rapids-print-env
+
+rapids-logger "Begin py build"
+
+rapids-mamba-retry mambabuild \
+  conda/recipes/dask-cuda
+
+rapids-upload-conda-to-s3 python

ci/build_python_pypi.sh

@@ -0,0 +1,18 @@
+#!/bin/bash
+
+
+python -m pip install build --user
+
+# While conda provides these during conda-build, they are also necessary during
+# the setup.py build for PyPI
+export GIT_DESCRIBE_TAG=$(git describe --abbrev=0 --tags)
+export GIT_DESCRIBE_NUMBER=$(git rev-list ${GIT_DESCRIBE_TAG}..HEAD --count)
+
+# Compute/export VERSION_SUFFIX
+source rapids-env-update
+
+python -m build \
+  --sdist \
+  --wheel \
+  --outdir dist/ \
+  .

ci/check_style.sh

@@ -0,0 +1,18 @@
+#!/bin/bash
+# Copyright (c) 2020-2022, NVIDIA CORPORATION.
+
+set -euo pipefail
+
+rapids-logger "Create checks conda environment"
+. /opt/conda/etc/profile.d/conda.sh
+
+rapids-dependency-file-generator \
+  --output conda \
+  --file_key checks \
+  --matrix "cuda=${RAPIDS_CUDA_VERSION%.*};arch=$(arch);py=${RAPIDS_PY_VERSION}" | tee env.yaml
+
+rapids-mamba-retry env create --force -f env.yaml -n checks
+conda activate checks
+
+# Run pre-commit checks
+pre-commit run --hook-stage manual --all-files --show-diff-on-failure

ci/cpu/build.sh

@@ -24,7 +24,7 @@ export GPUCI_CONDA_RETRY_SLEEP=30
 export INSTALL_DASK_MAIN=0
 
 # Dask version to install when `INSTALL_DASK_MAIN=0`
-export DASK_STABLE_VERSION="2022.11.1"
+export DASK_STABLE_VERSION="2023.1.1"
 
 # Switch to project root; also root of repo checkout
 cd "$WORKSPACE"

ci/gpu/build.sh

@@ -26,7 +26,7 @@ cd "$WORKSPACE"
 export GIT_DESCRIBE_TAG=`git describe --tags`
 export MINOR_VERSION=`echo $GIT_DESCRIBE_TAG | grep -o -E '([0-9]+\.[0-9]+)'`
 export UCX_PATH=$CONDA_PREFIX
-export UCXPY_VERSION=0.29.*
+export UCXPY_VERSION=0.30
 unset GIT_DESCRIBE_TAG
 
 # Enable NumPy's __array_function__ protocol (needed for NumPy 1.16.x,
@@ -38,7 +38,7 @@ export NUMPY_EXPERIMENTAL_ARRAY_FUNCTION=1
 export INSTALL_DASK_MAIN=0
 
 # Dask version to install when `INSTALL_DASK_MAIN=0`
-export DASK_STABLE_VERSION="2022.11.1"
+export DASK_STABLE_VERSION="2023.1.1"
 
 # Temporary workaround for Jupyter errors.
 # See https://github.com/rapidsai/dask-cuda/issues/1040