Merge pull request #1 from TomAugspurger/tom/initial-setup

Initial setup for dask-upstream-testing

.github/workflows/cron.yaml

@@ -1,78 +1,38 @@
-on:
-  # TODO: change to cron-based schedule one this is working
-  push:
-    branches:
-      - main
+# Based off https://github.com/rapidsai/cudf/blob/branch-25.02/.github/workflows/pandas-tests.yaml
+name: Test dask-upstream
 
+on:
+  schedule:
+    # 18:15 UTC daily.
+    # We want to run after the nightly pipeline finishes.
+    # https://github.com/rapidsai/workflows/blob/main/.github/workflows/nightly-pipeline-trigger.yaml is
+    # currently set to 5:00 UTC and takes ~12 hours
+    - cron: "15 18 * * *"
+
 jobs:
-  test:
-    name: "Test dask and distributed"
-    # TODO: change to appropriate image
-    runs-on: "linux-amd64-gpu-v100-latest-1"
-    container:
-      image: rapidsai/distributed:24.12-cuda11.8.0-devel-ubuntu20.04-py3.12
-      env:
-        NVIDIA_VISIBLE_DEVICES: ${{ env.NVIDIA_VISIBLE_DEVICES }}
+  setup:
+    runs-on: ubuntu-latest
+    outputs:
+      date: ${{ steps.date.outputs.date }}
+      branch: ${{ steps.branch.outputs.branch }}
     steps:
-    - name: Checkout ourselves
-      uses: actions/checkout@v4
-      with:
-        path: utils
-    - name: Checkout dask
-      uses: actions/checkout@v4
-      with:
-        repository: dask/dask
-        path: dask
-    - name: Checkout distributed
-      uses: actions/checkout@v4
-      with:
-        repository: dask/distributed
-        path: distributed
-    - name: Run
-      run: |
-        (cd dask; git rev-parse HEAD;
-         cd ../distributed; git rev-parse HEAD) | tee commit-hashes.txt
-    - name: Upload commit hashes
-      uses: actions/upload-artifact@v4
-      with:
-        name: commit-hashes.txt
-        path: commit-hashes.txt
-    - name: Setup python
-      uses: actions/setup-python@v5
-      with:
-        python-version: 3.12
-    - name: Get last artifact URL from last run
-      id: get_last_id
-      run: |
-        pip install requests
-        VAL=$(python utils/get.py)
-        echo "${VAL}"
-        echo "${VAL}" >> $GITHUB_OUTPUT
-    - name: Download artifact from last run if exists
-      if: ${{ fromJSON(steps.get_last_id.outputs.INFO).exists }}
-      continue-on-error: true
-      uses: actions/download-artifact@v4
-      with:
-        name: commit-hashes.txt
-        path: previous-run
-        github-token: ${{ secrets.GITHUB_TOKEN }}
-        run-id: ${{ fromJSON(steps.get_last_id.outputs.INFO).id }}
-    - name: Check if test run is needed
-      id: check_run_needed
-      run: |
-        ls -l previous-run/
-        if [ ! -f previous-run/commit-hashes.txt ]; then
-          echo "No previous run hashes, need to re-run"
-          echo 'INFO={"rerun": true}' >> $GITHUB_OUTPUT
-        elif cmp -s commit-hashes.txt previous-run/commit-hashes.txt; then
-          echo "Previous run hash same as this one, no need to re-run"
-          echo 'INFO={"rerun": false}' >> $GITHUB_OUTPUT
-        else
-          echo "Previous run hash different, need to re-run"
-          echo 'INFO={"rerun": true}' >> $GITHUB_OUTPUT
-        fi
-    - name: Run tests
-      if: ${{ fromJSON(steps.check_run_needed.outputs.INFO).rerun }}
-      run: |
-        echo Running tests
-        nvidia-smi
+      - name: Get current date
+        id: date
+        run: echo name=date::$(date +'%Y-%m-%d')" >> "$GITHUB_OUTPUT"
+      - name: Get current branch
+        id: branch
+        run: echo "branch=${GITHUB_HEAD_REF:-${GITHUB_REF#refs/heads/}}" >> $GITHUB_OUTPUT
+
+  dask-tests:
+    needs: setup
+    # run the Dask and Distributed unit tests
+    secrets: inherit
+    uses: rapidsai/shared-workflows/.github/workflows/[email protected]
+    with:
+      # This selects "ARCH=amd64 + the latest supported Python + CUDA".
+      matrix_filter: map(select(.ARCH == "amd64")) | group_by(.CUDA_VER|split(".")|map(tonumber)|.[0]) | map(max_by([(.PY_VER|split(".")|map(tonumber)), (.CUDA_VER|split(".")|map(tonumber))]))
+      build_type: nightly
+      branch: ${{ needs.setup.outputs.branch }}
+      date: ${{ needs.setup.outputs.date }}
+      sha: ${{ github.sha }}
+      script: scripts/run.sh

.gitignore

@@ -0,0 +1,2 @@
+dask
+distributed

.pre-commit-config.yaml

@@ -0,0 +1,18 @@
+# Copyright (c) 2025, NVIDIA CORPORATION.
+
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v5.0.0
+    hooks:
+      - id: trailing-whitespace
+        exclude: |
+          (?x)^(
+            ^cpp/cmake/thirdparty/patches/.*|
+            ^python/cudf/cudf/tests/data/subword_tokenizer_data/.*
+          )
+      - id: end-of-file-fixer
+        exclude: |
+          (?x)^(
+            ^cpp/cmake/thirdparty/patches/.*|
+            ^python/cudf/cudf/tests/data/subword_tokenizer_data/.*
+          )

README.md

@@ -1 +1,9 @@
 # Dask Upstream Testing
+
+This repository contains the scripts to run Dask's `gpu`-marked tests on a schedule.
+
+## Version Policy
+
+The primary goal here is to quickly identify breakages in tests defined in `dask/dask` and `dask/distributed`, so we'll use the latest `main` from each of those.
+
+When breakages occur, they'll generally be fixed either in Dask or in the the nightly versions of the downstream packages (rapids, cupy, numba, etc.). And so we install the nightly (rather than `latest`) version of the downstream packages.

scripts/run.sh

@@ -0,0 +1,36 @@
+#!/usr/bin/env bash
+# SPDX-FileCopyrightText: Copyright (c) 2025, NVIDIA CORPORATION & AFFILIATES.
+
+# Install
+set -euo pipefail
+
+RAPIDS_PY_CUDA_SUFFIX="cu${RAPIDS_CUDA_VERSION:-12}"
+
+# TODO: set this to main once dask-cudf is compatible
+# DASK_VERSION=main
+DASK_VERSION=2024.12.1
+export PIP_YES=true
+export PIP_PRE=true
+
+pip install --extra-index-url=https://pypi.anaconda.org/rapidsai-wheels-nightly/simple \
+  "cudf-${RAPIDS_PY_CUDA_SUFFIX}" \
+  "dask-cudf-${RAPIDS_PY_CUDA_SUFFIX}" \
+  "ucx-py-${RAPIDS_PY_CUDA_SUFFIX}" \
+  "scipy" \
+  "dask-cuda"
+
+echo "Installing dask@{DASK_VERSION}"
+
+if [ ! -d "dask" ]; then
+    git clone https://github.com/dask/dask
+fi
+
+if [ ! -d "distributed" ]; then
+    git clone https://github.com/dask/distributed
+fi
+
+pip uninstall dask distributed
+cd dask && git clean -fdx && git checkout $DASK_VERSION && pip install -e .[test] && cd ..
+cd distributed && git clean -fdx && git checkout $DASK_VERSION && pip install -e . && cd ..
+
+./scripts/test.sh

scripts/test.sh

@@ -0,0 +1,17 @@
+#!/usr/bin/env bash
+# SPDX-FileCopyrightText: Copyright (c) 2023-2025, NVIDIA CORPORATION & AFFILIATES.
+
+pushd dask
+pytest dask -v -m gpu
+dask_status=$?
+popd
+
+pushd distributed
+pytest distributed -v -m gpu --runslow
+distributed_status=$?
+popd
+
+if [ $dask_status -ne 0 ] || [ $distributed_status -ne 0 ]; then
+    echo "Tests faild"
+    exit 1
+fi