Merge branch 'main' into atmn/vendor-in-vectorize

Author: atmnp

.gitattributes

@@ -0,0 +1,5 @@
+# SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: BSD-2-Clause
+
+# SCM syntax highlighting & preventing 3-way merges
+pixi.lock merge=binary linguist-language=YAML linguist-generated=true

.github/workflows/pr.yaml

@@ -19,13 +19,11 @@ jobs:
       - compute-matrix
       - build-conda
       - test-conda
-      - test-conda-ctypes-binding
       - test-simulator
       - build-wheels
       - build-wheels-windows
       - test-wheels-windows
       - test-wheels
-      - test-wheels-ctypes-binding
       - test-wheels-deps-wheels
       - test-thirdparty
       - build-docs
@@ -80,18 +78,6 @@ jobs:
       script: "ci/test_conda.sh"
       run_codecov: false
       matrix: ${{ needs.compute-matrix.outputs.TEST_MATRIX }}
-  test-conda-ctypes-binding:
-    needs:
-      - build-conda
-      - compute-matrix
-    uses: ./.github/workflows/conda-python-tests.yaml
-    with:
-      build_type: pull-request
-      script: "ci/test_conda_ctypes_binding.sh"
-      run_codecov: false
-      # This selects "ARCH=amd64 and CUDA >=12, with the latest supported Python for each CUDA major version".
-      matrix: ${{ needs.compute-matrix.outputs.TEST_MATRIX }}
-      matrix_filter: map(select(.ARCH == "amd64" and (.CUDA_VER | split(".") | .[0] | tonumber >= 12))) | group_by(.CUDA_VER|split(".")|map(tonumber)|.[0]) | map(max_by([(.PY_VER|split(".")|map(tonumber)), (.CUDA_VER|split(".")|map(tonumber))]))
   test-simulator:
     needs:
       - build-conda
@@ -124,17 +110,6 @@ jobs:
       build_type: pull-request
       script: "ci/test_wheel.sh false"
       matrix: ${{ needs.compute-matrix.outputs.TEST_MATRIX }}
-  test-wheels-ctypes-binding:
-    needs:
-      - build-wheels
-      - compute-matrix
-    uses: ./.github/workflows/wheels-test.yaml
-    with:
-      build_type: pull-request
-      script: "ci/test_wheel_ctypes_binding.sh"
-      # This selects "ARCH=amd64 and CUDA >=12, with the latest supported Python for each CUDA major version".
-      matrix: ${{ needs.compute-matrix.outputs.TEST_MATRIX }}
-      matrix_filter: map(select(.ARCH == "amd64" and (.CUDA_VER | split(".") | .[0] | tonumber >= 12))) | group_by(.CUDA_VER|split(".")|map(tonumber)|.[0]) | map(max_by([(.PY_VER|split(".")|map(tonumber)), (.CUDA_VER|split(".")|map(tonumber))]))
   test-wheels-deps-wheels:
     needs:
       - build-wheels

.gitignore

@@ -8,3 +8,14 @@ build
 *.so
 numba_cuda/numba/cuda/tests/cudadrv/test_device_functions.*
 numba_cuda/numba/cuda/tests/cudadrv/undefined_extern.*
+testing/*.a
+testing/*.cubin
+testing/*.fatbin
+testing/*.ltoir
+testing/*.ltoir.o
+testing/*.o
+testing/*.ptx
+# pixi environments
+.pixi/*
+!.pixi/config.toml
+*.log

.spdx-ignore

@@ -32,3 +32,4 @@ numba_cuda/numba/cuda/include/*/cuda_*.hpp
 
 # GitHub configuration files
 .github/CODEOWNERS
+pixi.lock

README.md

@@ -37,12 +37,19 @@ they are compiled for the appropriate compute capability.
 ```
 cd testing
 # Optionally, build test binaries and point to their location for the test suite
-make
+make -j $(nproc)
 export NUMBA_CUDA_TEST_BIN_DIR=`pwd`
 # Execute tests
 pytest -n auto -v
 ```
 
+Alternatively, you can use [pixi](https://pixi.sh/latest/installation/) to wrap all of that up for you:
+
+```
+# run tests against CUDA 13
+pixi run -e cu13 test -n auto -v
+```
+
 
 Testing should discover the `numba.cuda` module from the `numba_cuda` package. You
 can check where `numba.cuda` files are being located by running

ci/coverage_report.sh

@@ -10,16 +10,17 @@ rapids-logger "Install wheel with test dependencies and coverage tools"
 package=$(realpath wheel/numba_cuda*.whl)
 echo "Package path: ${package}"
 python -m pip install \
-    "${package}[test]" \
+    "${package}" \
     "cuda-python==${CUDA_VER_MAJOR_MINOR%.*}.*" \
     "cuda-core==0.3.*" \
     pytest-cov \
-    coverage
+    coverage \
+    --group test
 
 rapids-logger "Build test binaries"
 export NUMBA_CUDA_TEST_BIN_DIR=`pwd`/testing
 pushd $NUMBA_CUDA_TEST_BIN_DIR
-make
+make -j $(nproc)
 
 rapids-logger "Check GPU usage"
 nvidia-smi

ci/test_conda.sh

@@ -66,7 +66,7 @@ nvidia-smi
 rapids-logger "Build test binaries"
 export NUMBA_CUDA_TEST_BIN_DIR=`pwd`/testing
 pushd $NUMBA_CUDA_TEST_BIN_DIR
-make
+make -j $(nproc)
 
 rapids-logger "Show Numba system info"
 python -m numba --sysinfo

ci/test_conda_ctypes_binding.sh

@@ -9,8 +9,8 @@ CUDA_VER_MAJOR_MINOR=${CUDA_VER%.*}
 rapids-logger "Install cuDF Wheel"
 
 pip install \
-    --extra-index-url=https://pypi.anaconda.org/rapidsai-wheels-nightly/simple \
-    "cudf-cu12>=25.10.0a0,<=25.10" "dask-cuda>=25.10.0a0,<=25.10"
+    --extra-index-url=https://pypi.nvidia.com \
+    "cudf-cu12==25.10.*"
 
 
 rapids-logger "Remove Extraneous numba-cuda"
@@ -20,10 +20,12 @@ rapids-logger "Install wheel with test dependencies"
 package=$(realpath wheel/numba_cuda*.whl)
 echo "Package path: ${package}"
 python -m pip install \
-    "${package}[test]" \
+    "${package}" \
     "cuda-python==${CUDA_VER_MAJOR_MINOR%.*}.*" \
     "cuda-core==0.3.*" \
     "nvidia-nvjitlink-cu12" \
+    --group test
+
 
 
 rapids-logger "Shallow clone cuDF repository"
@@ -39,13 +41,13 @@ rapids-logger "Show Numba system info"
 python -m numba --sysinfo
 
 rapids-logger "Run Scalar UDF tests"
-python -m pytest python/cudf/cudf/tests/dataframe/methods/test_apply.py -W ignore::UserWarning -W ignore::DeprecationWarning:numba.cuda.core.config
+python -m pytest python/cudf/cudf/tests/dataframe/methods/test_apply.py -W ignore::UserWarning
 
 rapids-logger "Run GroupBy UDF tests"
-python -m pytest python/cudf/cudf/tests/groupby/test_apply.py -k test_groupby_apply_jit -W ignore::UserWarning -W ignore::DeprecationWarning:numba.cuda.core.config
+python -m pytest python/cudf/cudf/tests/groupby/test_apply.py -k test_groupby_apply_jit -W ignore::UserWarning
 
 rapids-logger "Run NRT Stats Counting tests"
-python -m pytest python/cudf/cudf/tests/private_objects/test_nrt_stats.py  -W ignore::UserWarning -W ignore::DeprecationWarning:numba.cuda.core.config
+python -m pytest python/cudf/cudf/tests/private_objects/test_nrt_stats.py  -W ignore::UserWarning
 
 
 popd

ci/test_thirdparty.sh

@@ -31,7 +31,7 @@ $CUDA_VER_MAJOR = ($env:CUDA_VER -split '\.')[0] -join '.'
 rapids-logger "Install wheel with test dependencies"
 $package = Resolve-Path wheel\numba_cuda*.whl | Select-Object -ExpandProperty Path
 echo "Package path: $package"
-python -m pip install "${package}[cu${CUDA_VER_MAJOR},test-cu${CUDA_VER_MAJOR}]"
+python -m pip install "${package}[cu${CUDA_VER_MAJOR}]" --group "test-cu${CUDA_VER_MAJOR}"
 python -m pip install "llvmlite<0.45" "numba==0.61.*" # WAR for https://github.com/numba/llvmlite/issues/1297