Merge branch 'cagra-improve-ace-revedge' of github.com:enp1s0/cuvs into cagra-improve-ace-revedge

Author: enp1s0

.devcontainer/cuda12.9-pip/devcontainer.json

@@ -5,7 +5,7 @@
     "args": {
       "CUDA": "12.9",
       "PYTHON_PACKAGE_MANAGER": "pip",
-      "BASE": "rapidsai/devcontainers:26.12-cpp-cuda12.9-ucx1.19.0-openmpi5.0.10"
+      "BASE": "rapidsai/devcontainers:26.12-cpp-cuda12.9-ucx1.21.0-openmpi5.0.10"
     },
     "cacheFrom": [
       "ghcr.io/rapidsai/cuvs/devcontainer:26.12-cuda12.9-pip"

.devcontainer/cuda13.3-pip/devcontainer.json

@@ -5,7 +5,7 @@
     "args": {
       "CUDA": "13.3",
       "PYTHON_PACKAGE_MANAGER": "pip",
-      "BASE": "rapidsai/devcontainers:26.12-cpp-cuda13.3-ucx1.19.0-openmpi5.0.10"
+      "BASE": "rapidsai/devcontainers:26.12-cpp-cuda13.3-ucx1.21.0-openmpi5.0.10"
     },
     "cacheFrom": [
       "ghcr.io/rapidsai/cuvs/devcontainer:26.12-cuda13.3-pip"

.github/workflows/build.yaml

@@ -259,7 +259,15 @@ jobs:
     secrets:
       GPUTESTER_CRATES_TOKEN: ${{ secrets.GPUTESTER_CRATES_TOKEN }}
     uses: ./.github/workflows/publish-rust.yaml
+  docs-build-matrix:
+    permissions:
+      contents: read
+    uses: rapidsai/shared-workflows/.github/workflows/compute-matrix.yaml@main
+    with:
+      build_type: ${{ inputs.build_type || 'branch' }}
+      matrix_name: docs-build
   docs-build:
+    needs: [docs-build-matrix]
     if: github.ref_type == 'branch'
     permissions:
       actions: read
@@ -269,13 +277,16 @@ jobs:
       pull-requests: read
     secrets: inherit # zizmor: ignore[secrets-inherit]
     uses: rapidsai/shared-workflows/.github/workflows/custom-job.yaml@main
+    strategy:
+      fail-fast: false
+      matrix: ${{ fromJSON(needs.docs-build-matrix.outputs.matrix) }}
     with:
-      arch: "amd64"
+      arch: "${{ matrix.arch }}"
       branch: ${{ inputs.branch }}
       build_type: ${{ inputs.build_type || 'branch' }}
-      container_image: "rapidsai/ci-conda:26.12-latest"
+      container_image: "rapidsai/ci-conda:26.12-cuda${{ matrix.CUDA_VER }}-${{ matrix.LINUX_VER }}-py${{ matrix.PY_VER }}"
       date: ${{ inputs.date }}
-      node_type: "gpu-l4-latest-1"
+      node_type: "gpu-${{ matrix.GPU }}-${{ matrix.DRIVER }}-1"
       script: "ci/build_docs.sh"
       sha: ${{ inputs.sha }}
   wheel-build-libcuvs:

.github/workflows/pr.yaml

@@ -33,6 +33,7 @@ jobs:
       - go-build-matrix
       - go-build
       - docs-build
+      - docs-build-matrix
       - wheel-build-libcuvs
       - wheel-build-cuvs
       - wheel-tests-cuvs
@@ -162,6 +163,8 @@ jobs:
           - '!ci/test_wheel_cuvs.sh'
           - '!ci/validate_wheel.sh'
           - '!docs/**'
+          - '!examples/go/**'
+          - '!examples/java/**'
           - '!fern/**'
           - '!go/**'
           - '!img/**'
@@ -214,7 +217,15 @@ jobs:
           - '!conda/recipes/cuvs-bench/**'
           - '!conda/recipes/cuvs-bench-cpu/**'
           - '!docs/**'
-          - '!examples/**'
+          - '!examples/.clang-format'
+          - '!examples/.clang-tidy'
+          - '!examples/.clangd'
+          - '!examples/README.md'
+          - '!examples/build.sh'
+          - '!examples/c/**'
+          - '!examples/cmake/**'
+          - '!examples/cpp/**'
+          - '!examples/go/**'
           - '!fern/**'
           - '!go/**'
           - '!img/**'
@@ -268,6 +279,7 @@ jobs:
           - '!README.md'
           - '!SECURITY.md'
           - '!docs/**'
+          - '!examples/**'
           - '!fern/**'
           - '!go/**'
           - '!img/**'
@@ -325,6 +337,7 @@ jobs:
           - '!cpp/.clang-tidy'
           - '!cpp/doxygen/**'
           - '!docs/**'
+          - '!examples/**'
           - '!fern/**'
           - '!java/**'
           - '!go/**'
@@ -377,6 +390,7 @@ jobs:
           - '!ci/test_wheel_cuvs.sh'
           - '!ci/validate_wheel.sh'
           - '!docs/**'
+          - '!examples/**'
           - '!fern/**'
           - '!go/**'
           - '!img/**'
@@ -430,6 +444,15 @@ jobs:
           - '!ci/test_wheel_cuvs.sh'
           - '!ci/validate_wheel.sh'
           - '!docs/**'
+          - '!examples/.clang-format'
+          - '!examples/.clang-tidy'
+          - '!examples/.clangd'
+          - '!examples/README.md'
+          - '!examples/build.sh'
+          - '!examples/c/**'
+          - '!examples/cmake/**'
+          - '!examples/cpp/**'
+          - '!examples/java/**'
           - '!fern/**'
           - '!img/**'
           - '!java/**'
@@ -715,7 +738,15 @@ jobs:
       arch: "amd64"
       container_image: "rapidsai/ci-conda:26.12-cuda${{ matrix.CUDA_VER }}-${{ matrix.LINUX_VER }}-py${{ matrix.PY_VER }}"
       script: "ci/build_go.sh"
+  docs-build-matrix:
+    permissions:
+      contents: read
+    uses: rapidsai/shared-workflows/.github/workflows/compute-matrix.yaml@main
+    with:
+      build_type: pull-request
+      matrix_name: docs-build
   docs-build:
+    needs: [docs-build-matrix]
     permissions:
       actions: read
       contents: read
@@ -724,11 +755,15 @@ jobs:
       pull-requests: read
     secrets: inherit # zizmor: ignore[secrets-inherit]
     uses: rapidsai/shared-workflows/.github/workflows/custom-job.yaml@main
+    if: fromJSON(needs.changed-files.outputs.changed_file_groups).build_docs
+    strategy:
+      fail-fast: false
+      matrix: ${{ fromJSON(needs.docs-build-matrix.outputs.matrix) }}
     with:
       build_type: pull-request
-      node_type: "gpu-l4-latest-1"
-      arch: "amd64"
-      container_image: "rapidsai/ci-conda:26.12-latest"
+      node_type: "gpu-${{ matrix.GPU }}-${{ matrix.DRIVER }}-1"
+      arch: "${{ matrix.arch }}"
+      container_image: "rapidsai/ci-conda:26.12-cuda${{ matrix.CUDA_VER }}-${{ matrix.LINUX_VER }}-py${{ matrix.PY_VER }}"
       script: "ci/build_docs.sh"
   wheel-build-libcuvs:
     needs: [build-details, checks]

.pre-commit-config.yaml

@@ -121,7 +121,7 @@ repos:
         name: spotless-fmt
         entry: ci/checks/run_spotless.sh
         pass_filenames: false
-        files: ^java/(cuvs-java|cuvs-lucene)/([^/]+/)?src/.*\.java$
+        files: ^(java|examples/java)/(cuvs-java|cuvs-lucene)/([^/]+/)?src/.*\.java$
         exclude: .*/panama/.*
         language: script
         verbose: true

build.sh

@@ -19,7 +19,7 @@ ARGS=$*
 # scripts, and that this script resides in the repo dir!
 REPODIR=$(cd "$(dirname "$0")"; pwd)
 
-VALIDARGS="clean libcuvs python rust go java lucene docs tests bench-ann examples --uninstall  -v -g -n --allgpuarch --no-mg --mnmg-tests --no-cpu --cpu-only --no-shared-libs --no-nvtx --show_depr_warn --incl-cache-stats --time -h --run-java-tests"
+VALIDARGS="clean libcuvs python rust go java lucene docs tests bench-ann examples --uninstall  -v -g -n --allgpuarch --no-mg --mnmg-tests --no-cpu --cpu-only --no-shared-libs --no-nvtx --show_depr_warn --incl-cache-stats --time -h --run-java-tests --build-java-examples"
 HELP="$0 [<target> ...] [<flag> ...] [--cmake-args=\"<args>\"] [--cache-tool=<tool>] [--limit-tests=<targets>] [--limit-bench-ann=<targets>] [--build-metrics=<filename>]
  where <target> is:
    clean            - remove all existing build artifacts and configuration (start over)
@@ -57,6 +57,8 @@ HELP="$0 [<target> ...] [<flag> ...] [--cmake-args=\"<args>\"] [--cache-tool=<to
    --no-shared-libs            - build without shared libraries
    --show_depr_warn            - show cmake deprecation warnings
    --run-java-tests            - run Java tests after building
+   --build-java-examples       - also build the examples/java/cuvs-java and examples/java/cuvs-lucene
+                                 projects against the jars just built (with the 'java'/'lucene' targets)
    --build-metrics             - filename for generating build metrics report for libcuvs
    --incl-cache-stats          - include cache statistics in build metrics report
    --cmake-args=\\\"<args>\\\" - pass arbitrary list of CMake configuration options (escape all quotes in argument)
@@ -560,11 +562,14 @@ if (( NUMARGS == 0 )) || hasArg java; then
         echo "Please add 'libcuvs' to this script's arguments (ex. './build.sh libcuvs java') if libcuvs libraries are not already built"
     fi
     cd "${REPODIR}"/java
+    JAVA_BUILD_ARGS=()
     if hasArg --run-java-tests; then
-        ./build.sh --run-java-tests
-    else
-        ./build.sh
+        JAVA_BUILD_ARGS+=("--run-java-tests")
     fi
+    if hasArg --build-java-examples; then
+        JAVA_BUILD_ARGS+=("--build-java-examples")
+    fi
+    ./build.sh "${JAVA_BUILD_ARGS[@]}"
 fi
 
 # Build the cuvs-lucene codecs
@@ -573,11 +578,14 @@ if (( NUMARGS == 0 )) || hasArg lucene; then
         echo "Please add 'java' to this script's arguments (ex. './build.sh libcuvs java lucene') if the cuvs Java bindings are not already built"
     fi
     cd "${REPODIR}"/java/cuvs-lucene
+    LUCENE_BUILD_ARGS=()
     if hasArg --run-java-tests; then
-        ./build.sh --run-java-tests
-    else
-        ./build.sh
+        LUCENE_BUILD_ARGS+=("--run-java-tests")
+    fi
+    if hasArg --build-java-examples; then
+        LUCENE_BUILD_ARGS+=("--build-java-examples")
     fi
+    ./build.sh "${LUCENE_BUILD_ARGS[@]}"
 fi
 
 RAPIDS_VERSION="$(sed -E -e 's/^([0-9]{2})\.([0-9]{2})\.([0-9]{2}).*$/\1.\2.\3/' "${REPODIR}/VERSION")"

ci/build_java.sh

@@ -13,7 +13,7 @@ export SCCACHE_S3_USE_PREPROCESSOR_CACHE_MODE=true
 # TODO: Remove this argument-handling when build and test workflows are separated,
 #       and test_java.sh no longer calls build_java.sh
 #       ref: https://github.com/nvidia/cuvs/issues/868
-EXTRA_BUILD_ARGS=()
+EXTRA_BUILD_ARGS=("--build-java-examples")
 if [[ "${1:-}" == "--run-java-tests" ]]; then
   EXTRA_BUILD_ARGS+=("--run-java-tests")
 fi

ci/build_lucene.sh

@@ -9,7 +9,7 @@ set -euo pipefail
 # TODO: Remove the flag handling when build and test workflows are separated,
 #       and test_lucene.sh no longer calls build_lucene.sh
 #       ref: https://github.com/rapidsai/cuvs/issues/868
-EXTRA_BUILD_ARGS=()
+EXTRA_BUILD_ARGS=("--build-java-examples")
 CUVS_JAVA_ARTIFACT=""
 for arg in "$@"; do
   case "${arg}" in

ci/checks/run_spotless.sh

@@ -3,7 +3,7 @@
 # SPDX-License-Identifier: Apache-2.0
 
 # pre-commit hook wrapper that runs 'spotless:apply' to format the Java sources of every Maven
-# project under java/.
+# project under java/ and examples/java/.
 #
 # Most cuvs contributors do not work on the Java client and do not have Maven installed. For them,
 # running 'pre-commit run --all-files' matches every Java source file in the repo regardless of
@@ -15,11 +15,11 @@ set -euo pipefail
 
 # Keep these in sync with the spotless-fmt hook's 'files'/'exclude' entries in
 # .pre-commit-config.yaml.
-JAVA_SRC_PATTERN='^java/(cuvs-java|cuvs-lucene)/([^/]+/)?src/.*\.java$'
+JAVA_SRC_PATTERN='^(java|examples/java)/(cuvs-java|cuvs-lucene)/([^/]+/)?src/.*\.java$'
 JAVA_SRC_EXCLUDE='.*/panama/.*'
 
 java_sources_modified() {
-  git status --porcelain --untracked-files=all -- java/cuvs-java java/cuvs-lucene |
+  git status --porcelain --untracked-files=all -- java/cuvs-java java/cuvs-lucene examples/java |
     cut -c4- |
     grep -Ev "${JAVA_SRC_EXCLUDE}" |
     grep -Eq "${JAVA_SRC_PATTERN}"
@@ -42,7 +42,8 @@ POMS=(
   java/cuvs-java/pom.xml
   java/cuvs-lucene/pom.xml
   java/cuvs-lucene/bench/pom.xml
-  java/cuvs-lucene/examples/pom.xml
+  examples/java/cuvs-java/pom.xml
+  examples/java/cuvs-lucene/pom.xml
 )
 
 for pom in "${POMS[@]}"; do

ci/release/update-version.sh

@@ -172,16 +172,16 @@ done
 NEXT_FULL_JAVA_TAG="${NEXT_SHORT_TAG}.${PATCH_PEP440}"
 sed_runner "s/VERSION=\".*\"/VERSION=\"${NEXT_FULL_JAVA_TAG}\"/g" java/build.sh
 sed_runner "s/VERSION=\".*\"/VERSION=\"${NEXT_FULL_JAVA_TAG}\"/g" java/cuvs-lucene/build.sh
-for FILE in java/*/pom.xml java/cuvs-lucene/bench/pom.xml java/cuvs-lucene/examples/pom.xml; do
+for FILE in java/*/pom.xml java/cuvs-lucene/bench/pom.xml examples/java/cuvs-java/pom.xml examples/java/cuvs-lucene/pom.xml; do
   sed_runner "/<!--CUVS_JAVA#VERSION_UPDATE_MARKER_START-->.*<!--CUVS_JAVA#VERSION_UPDATE_MARKER_END-->/s//<!--CUVS_JAVA#VERSION_UPDATE_MARKER_START--><version>${NEXT_FULL_JAVA_TAG}<\/version><!--CUVS_JAVA#VERSION_UPDATE_MARKER_END-->/g" "${FILE}"
 done
 
 sed_runner "s| CuVS [[:digit:]]\{2\}\.[[:digit:]]\{2\} | CuVS ${NEXT_SHORT_TAG} |g" java/README.md
-sed_runner "s|-[[:digit:]]\{2\}\.[[:digit:]]\{2\}\.[[:digit:]]\{1,2\}\.jar|-${NEXT_FULL_JAVA_TAG}\.jar|g" java/examples/README.md
-sed_runner "s|/[[:digit:]]\{2\}\.[[:digit:]]\{2\}\.[[:digit:]]\{1,2\}/|/${NEXT_FULL_JAVA_TAG}/|g" java/examples/README.md
+sed_runner "s|-[[:digit:]]\{2\}\.[[:digit:]]\{2\}\.[[:digit:]]\{1,2\}\.jar|-${NEXT_FULL_JAVA_TAG}\.jar|g" examples/java/cuvs-java/README.md
+sed_runner "s|/[[:digit:]]\{2\}\.[[:digit:]]\{2\}\.[[:digit:]]\{1,2\}/|/${NEXT_FULL_JAVA_TAG}/|g" examples/java/cuvs-java/README.md
 
 # This pattern is deliberately narrow: java/cuvs-lucene/README.md also links to a blog post whose
 # title contains a release number, and that reference must not be rewritten.
 sed_runner "s|<version>[[:digit:]]\{2\}\.[[:digit:]]\{2\}\.[[:digit:]]\{1,2\}</version>|<version>${NEXT_FULL_JAVA_TAG}</version>|g" java/cuvs-lucene/README.md
 
-sed_runner "s|target/examples-[\.0-9]*-jar|target/examples-${NEXT_FULL_JAVA_TAG}-jar|g" java/cuvs-lucene/examples/README.md
+sed_runner "s|target/examples-[\.0-9]*-jar|target/examples-${NEXT_FULL_JAVA_TAG}-jar|g" examples/java/cuvs-lucene/README.md