Forward-merge release/26.10 into main

.github/workflows/build.yaml

@@ -61,34 +61,54 @@
       contents: read
     uses: rapidsai/shared-workflows/.github/workflows/compute-matrix.yaml@release/26.10
     with:
-      build_type: pull-request
+      build_type: ${{ inputs.build_type || 'branch' }}
       matrix_name: conda-cpp-build
   rocky8-clib-standalone-build:
-    needs: [build-details, rocky8-clib-standalone-build-matrix]
+    needs: [rocky8-clib-standalone-build-matrix]
+    runs-on: linux-${{ matrix.ARCH }}-cpu16
+    env:
+      RAPIDS_BUILD_TYPE: ${{ inputs.build_type || 'branch' }}
     permissions:
       actions: read
       contents: read
       id-token: write
       packages: read
       pull-requests: read
-    secrets: inherit # zizmor: ignore[secrets-inherit]
-    uses: rapidsai/shared-workflows/.github/workflows/custom-job.yaml@release/26.10
     strategy:
       fail-fast: false
       matrix: ${{ fromJSON(needs.rocky8-clib-standalone-build-matrix.outputs.matrix) }}
-    with:
-      build_type: ${{ inputs.build_type || 'branch' }}
-      build-datetime: ${{ needs.build-details.outputs.build-datetime }}
-      branch: ${{ inputs.branch }}
-      arch: "${{matrix.ARCH}}"
-      date: ${{ inputs.date }}
-      container_image: "rapidsai/ci-wheel:26.10-cuda${{ matrix.CUDA_VER }}-${{ matrix.LINUX_VER }}-py${{ matrix.PY_VER }}"
-      node_type: "cpu16"
-      requires_license_builder: true
-      script: "ci/build_standalone_c.sh"
-      artifact-name: "libcuvs_c_${{ matrix.CUDA_VER }}_${{ matrix.ARCH }}.tar.gz"
-      file_to_upload: "libcuvs_c.tar.gz"
-      sha: ${{ inputs.sha }}
+    steps:
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+        with:
+          ref: ${{ inputs.sha || github.sha }}
+          fetch-depth: 0
+          persist-credentials: false
+      - name: Standardize repository information
+        uses: rapidsai/shared-actions/rapids-github-info@main
+        with:
+          branch: ${{ inputs.branch }}
+          date: ${{ inputs.date }}
+          sha: ${{ inputs.sha }}
+      - uses: aws-actions/configure-aws-credentials@cbe3b392738ccf3f987d68400dafcf4b0624a56c # v6.2.4
+        with:
+          role-to-assume: ${{ vars.AWS_ROLE_ARN }}
+          aws-region: ${{ vars.AWS_REGION }}
+          role-duration-seconds: 10800
+      - name: Setup sccache-dist
+        uses: rapidsai/shared-actions/setup-sccache-dist@main
+        with:
+          request-timeout: 7140
+      - name: Build standalone C tarball
+        env:
+          CUVS_TARBALL_CUDA_VERSION: ${{ matrix.CUDA_VER }}
+          CUVS_TARBALL_PYTHON_VERSION: ${{ matrix.PY_VER }}
+        run: |
+          ./build.sh tarball --tarball-build-tests
+      - name: Upload artifacts
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
+        with:
+          name: libcuvs_c_${{ matrix.CUDA_VER }}_${{ matrix.ARCH }}.tar.gz
+          path: libcuvs_c.tar.gz
   rust-build-matrix:
     needs: cpp-build
     permissions:
@@ -128,7 +148,7 @@
       contents: read
     uses: rapidsai/shared-workflows/.github/workflows/compute-matrix.yaml@release/26.10
     with:
-      build_type: pull-request
+      build_type: ${{ inputs.build_type || 'branch' }}
       matrix_name: conda-cpp-build
       matrix_filter: map(select(.ARCH == "amd64"))
   go-build:
@@ -161,7 +181,7 @@
       contents: read
     uses: rapidsai/shared-workflows/.github/workflows/compute-matrix.yaml@release/26.10
     with:
-      build_type: pull-request
+      build_type: ${{ inputs.build_type || 'branch' }}
       matrix_name: conda-cpp-build
       matrix_filter: map(select(.ARCH == "amd64"))
   java-build:
@@ -190,7 +210,8 @@
       file_to_upload: "java/cuvs-java/target/"
       sha: ${{ inputs.sha }}
   lucene-build:
-    # Depends on the Java job for the cuvs-java artifact that cuvs-lucene builds against.
+    # Depends on the Java job for the cuvs-java artifact that cuvs-lucene builds against, and
+    # reuses its matrix so the two always agree on the set of CUDA versions.
     needs: [java-build-matrix, java-build]
     permissions:
       actions: read

.github/workflows/pr.yaml

@@ -27,7 +27,10 @@
       - rocky8-clib-tests
       - conda-java-build-and-tests-matrix
       - conda-java-build-and-tests
+      - conda-java-tests-other-arch-matrix
+      - conda-java-tests-other-arch
       - conda-lucene-build-and-tests
+      - conda-lucene-tests-other-arch
       - rust-build-matrix
       - rust-build
       - go-build-matrix
@@ -563,30 +566,45 @@
       build_type: pull-request
       matrix_name: conda-cpp-build
   rocky8-clib-standalone-build:
-    needs: [build-details, rocky8-clib-standalone-build-matrix]
+    needs: [rocky8-clib-standalone-build-matrix]
+    runs-on: linux-${{ matrix.ARCH }}-cpu16
+    env:
+      RAPIDS_BUILD_TYPE: pull-request
     permissions:
       actions: read
       contents: read
       id-token: write
       packages: read
       pull-requests: read
-    secrets: inherit # zizmor: ignore[secrets-inherit]
-    uses: rapidsai/shared-workflows/.github/workflows/custom-job.yaml@release/26.10
     strategy:
       fail-fast: false
       matrix: ${{ fromJSON(needs.rocky8-clib-standalone-build-matrix.outputs.matrix) }}
-    with:
-      build_type: pull-request
-      build-datetime: ${{ needs.build-details.outputs.build-datetime }}
-      arch: "${{matrix.arch}}"
-      date: ${{ inputs.date }}_c
-      container_image: "rapidsai/ci-wheel:26.10-cuda${{ matrix.CUDA_VER }}-${{ matrix.LINUX_VER }}-py${{ matrix.PY_VER }}"
-      node_type: "cpu16"
-      requires_license_builder: true
-      script: "ci/build_standalone_c.sh --build-tests"
-      artifact-name: "libcuvs_c_${{ matrix.CUDA_VER }}_${{ matrix.ARCH }}.tar.gz"
-      file_to_upload: "libcuvs_c.tar.gz"
-      sha: ${{ inputs.sha }}
+    steps:
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+        with:
+          ref: ${{ inputs.sha || github.sha }}
+          fetch-depth: 0
+          persist-credentials: false
+      - uses: aws-actions/configure-aws-credentials@cbe3b392738ccf3f987d68400dafcf4b0624a56c # v6.2.4
+        with:
+          role-to-assume: ${{ vars.AWS_ROLE_ARN }}
+          aws-region: ${{ vars.AWS_REGION }}
+          role-duration-seconds: 10800
+      - name: Setup sccache-dist
+        uses: rapidsai/shared-actions/setup-sccache-dist@main
+        with:
+          request-timeout: 7140
+      - name: Build standalone C tarball
+        env:
+          CUVS_TARBALL_CUDA_VERSION: ${{ matrix.CUDA_VER }}
+          CUVS_TARBALL_PYTHON_VERSION: ${{ matrix.PY_VER }}
+        run: |
+          ./build.sh tarball --tarball-build-tests
+      - name: Upload artifacts
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
+        with:
+          name: libcuvs_c_${{ matrix.CUDA_VER }}_${{ matrix.ARCH }}.tar.gz
+          path: libcuvs_c.tar.gz
   rocky8-clib-tests-matrix:
     needs: [rocky8-clib-standalone-build, changed-files]
     permissions:
@@ -650,6 +668,39 @@
       script: "ci/test_java.sh"
       artifact-name: "cuvs-java-cuda${{ matrix.CUDA_VER }}"
       file_to_upload: "java/cuvs-java/target/"
+  conda-java-tests-other-arch-matrix:
+    # All architectures the C++ core builds for, except amd64.
+    needs: [conda-cpp-build, changed-files]
+    permissions:
+      contents: read
+    uses: rapidsai/shared-workflows/.github/workflows/compute-matrix.yaml@release/26.10
+    if: fromJSON(needs.changed-files.outputs.changed_file_groups).test_java || fromJSON(needs.changed-files.outputs.changed_file_groups).test_cpp
+    with:
+      build_type: pull-request
+      matrix_name: conda-cpp-build
+      matrix_filter: map(select(.ARCH != "amd64"))
+  conda-java-tests-other-arch:
+    # Verifies that the amd64-built cuvs-java jar (jextract-generated Panama bindings and
+    # all) also works correctly on every non-amd64 architecture, by running its own IT test
+    # suite against the amd64-built classes without recompiling -- see ci/test_java_prebuilt.sh.
+    needs: [conda-java-tests-other-arch-matrix, conda-java-build-and-tests]
+    permissions:
+      actions: read
+      contents: read
+      id-token: write
+      packages: read
+      pull-requests: read
+    secrets: inherit # zizmor: ignore[secrets-inherit]
+    uses: rapidsai/shared-workflows/.github/workflows/custom-job.yaml@release/26.10
+    strategy:
+      fail-fast: false
+      matrix: ${{ fromJSON(needs.conda-java-tests-other-arch-matrix.outputs.matrix) }}
+    with:
+      build_type: pull-request
+      node_type: "gpu-l4-latest-1"
+      arch: "${{ matrix.ARCH }}"
+      container_image: "rapidsai/ci-conda:26.10-cuda${{ matrix.CUDA_VER }}-${{ matrix.LINUX_VER }}-py${{ matrix.PY_VER }}"
+      script: "ci/test_java_prebuilt.sh ${{ matrix.ARCH }} cuvs-java-cuda${{ matrix.CUDA_VER }}"
   conda-lucene-build-and-tests:
     # Depends on the Java job for the cuvs-java artifact that cuvs-lucene builds against, and
     # reuses its matrix so the two always agree on the set of CUDA versions.
@@ -675,6 +726,29 @@
       script: "ci/test_lucene.sh cuvs-java-cuda${{ matrix.CUDA_VER }}"
       artifact-name: "cuvs-lucene-cuda${{ matrix.CUDA_VER }}"
       file_to_upload: "java/cuvs-lucene/target/"
+  conda-lucene-tests-other-arch:
+    # Verifies that cuvs-lucene, built against the amd64-built cuvs-java jar, also works
+    # correctly on every non-amd64 architecture, by running its test suite against the
+    # amd64-built classes without recompiling -- see ci/test_lucene_prebuilt.sh. Reuses
+    # conda-java-tests-other-arch-matrix so the two always agree on which architectures to test.
+    needs: [conda-java-tests-other-arch-matrix, conda-java-build-and-tests, conda-lucene-build-and-tests]
+    permissions:
+      actions: read
+      contents: read
+      id-token: write
+      packages: read
+      pull-requests: read
+    secrets: inherit # zizmor: ignore[secrets-inherit]
+    uses: rapidsai/shared-workflows/.github/workflows/custom-job.yaml@release/26.10
+    strategy:
+      fail-fast: false
+      matrix: ${{ fromJSON(needs.conda-java-tests-other-arch-matrix.outputs.matrix) }}
+    with:
+      build_type: pull-request
+      node_type: "gpu-l4-latest-1"
+      arch: "${{ matrix.ARCH }}"
+      container_image: "rapidsai/ci-conda:26.10-cuda${{ matrix.CUDA_VER }}-${{ matrix.LINUX_VER }}-py${{ matrix.PY_VER }}"
+      script: "ci/test_lucene_prebuilt.sh ${{ matrix.ARCH }} cuvs-java-cuda${{ matrix.CUDA_VER }} cuvs-lucene-cuda${{ matrix.CUDA_VER }}"
   rust-build-matrix:
     needs: [conda-cpp-build, changed-files]
     permissions:

.github/workflows/test.yaml

@@ -104,6 +104,41 @@
       script: "ci/test_java.sh"
       artifact-name: "cuvs-java-cuda${{ matrix.CUDA_VER }}"
       file_to_upload: "java/cuvs-java/target/"
+  conda-java-tests-other-arch-matrix:
+    # All architectures the C++ core builds for, except amd64 -- so a newly added
+    # architecture is automatically picked up here without a workflow change.
+    permissions:
+      contents: read
+    uses: rapidsai/shared-workflows/.github/workflows/compute-matrix.yaml@release/26.10
+    with:
+      build_type: ${{ inputs.build_type }}
+      matrix_name: conda-cpp-build
+      matrix_filter: map(select(.ARCH != "amd64"))
+  conda-java-tests-other-arch:
+    # Verifies that the amd64-built cuvs-java jar (jextract-generated Panama bindings and
+    # all) also works correctly on every non-amd64 architecture, by running its own IT test
+    # suite against the amd64-built classes without recompiling -- see ci/test_java_prebuilt.sh.
+    needs: [conda-java-tests-other-arch-matrix, conda-java-build-and-tests]
+    permissions:
+      actions: read
+      contents: read
+      id-token: write
+      packages: read
+      pull-requests: read
+    secrets: inherit # zizmor: ignore[secrets-inherit]
+    uses: rapidsai/shared-workflows/.github/workflows/custom-job.yaml@release/26.10
+    strategy:
+      fail-fast: false
+      matrix: ${{ fromJSON(needs.conda-java-tests-other-arch-matrix.outputs.matrix) }}
+    with:
+      build_type: ${{ inputs.build_type }}
+      branch: ${{ inputs.branch }}
+      date: ${{ inputs.date }}
+      sha: ${{ inputs.sha }}
+      node_type: "gpu-l4-latest-1"
+      arch: "${{ matrix.ARCH }}"
+      container_image: "rapidsai/ci-conda:26.10-cuda${{ matrix.CUDA_VER }}-${{ matrix.LINUX_VER }}-py${{ matrix.PY_VER }}"
+      script: "ci/test_java_prebuilt.sh ${{ matrix.ARCH }} cuvs-java-cuda${{ matrix.CUDA_VER }}"
   conda-lucene-build-and-tests:
     # Depends on the Java job for the cuvs-java artifact that cuvs-lucene builds against, and
     # reuses its matrix so the two always agree on the set of CUDA versions.
@@ -132,6 +167,32 @@
       script: "ci/test_lucene.sh cuvs-java-cuda${{ matrix.CUDA_VER }}"
       artifact-name: "cuvs-lucene-cuda${{ matrix.CUDA_VER }}"
       file_to_upload: "java/cuvs-lucene/target/"
+  conda-lucene-tests-other-arch:
+    # Verifies that cuvs-lucene, built against the amd64-built cuvs-java jar, also works
+    # correctly on every non-amd64 architecture, by running its test suite against the
+    # amd64-built classes without recompiling -- see ci/test_lucene_prebuilt.sh. Reuses
+    # conda-java-tests-other-arch-matrix so the two always agree on which architectures to test.
+    needs: [conda-java-tests-other-arch-matrix, conda-java-build-and-tests, conda-lucene-build-and-tests]
+    permissions:
+      actions: read
+      contents: read
+      id-token: write
+      packages: read
+      pull-requests: read
+    secrets: inherit # zizmor: ignore[secrets-inherit]
+    uses: rapidsai/shared-workflows/.github/workflows/custom-job.yaml@release/26.10
+    strategy:
+      fail-fast: false
+      matrix: ${{ fromJSON(needs.conda-java-tests-other-arch-matrix.outputs.matrix) }}
+    with:
+      build_type: ${{ inputs.build_type }}
+      branch: ${{ inputs.branch }}
+      date: ${{ inputs.date }}
+      sha: ${{ inputs.sha }}
+      node_type: "gpu-l4-latest-1"
+      arch: "${{ matrix.ARCH }}"
+      container_image: "rapidsai/ci-conda:26.10-cuda${{ matrix.CUDA_VER }}-${{ matrix.LINUX_VER }}-py${{ matrix.PY_VER }}"
+      script: "ci/test_lucene_prebuilt.sh ${{ matrix.ARCH }} cuvs-java-cuda${{ matrix.CUDA_VER }} cuvs-lucene-cuda${{ matrix.CUDA_VER }}"
   wheel-tests-cuvs:
     permissions:
       actions: read

.gitignore

@@ -19,6 +19,7 @@ dist/
 python/**/**/*.cpp
 python/cuvs/record.txt
 log
+infrequent_licenses/
 .ipynb_checkpoints
 .DS_Store
 dask-worker-space/
@@ -29,6 +30,7 @@ temporary_*.json
 rust/target/
 rust/Cargo.lock
 rmm_log.txt
+*.tar.gz
 
 ## example notebooks
 notebooks/simplewiki-2020-11-01-nq-distilbert-base-v1.pt

Dockerfile.standalone

@@ -0,0 +1,23 @@
+# SPDX-FileCopyrightText: Copyright (c) 2025-2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+#
+# Environment and runner for the standalone C build.
+#
+# End-user instructions: https://docs.nvidia.com/cuvs/installation#build-the-standalone-c-library-with-docker
+
+ARG CUDA_VERSION=notset
+ARG PYTHON_VERSION=notset
+ARG RAPIDS_VERSION=notset
+FROM rapidsai/ci-wheel:${RAPIDS_VERSION}-cuda${CUDA_VERSION}-rockylinux8-py${PYTHON_VERSION}
+
+# Output directory for the standalone archive. Bind-mount a host folder here
+# (e.g. -v $(pwd)/build:/build) so libcuvs_c.tar.gz is written to the host.
+ENV CUVS_TARBALL_BUILD_OUTPUT_DIR=/build
+ENV CUVS_TARBALL_IN_CONTAINER=1
+
+# Run from repo root; the repo is expected to be bind-mounted at /workspace.
+WORKDIR /workspace
+
+# Run the build script, which writes the standalone tarball to the mounted output dir.
+# Example: docker run -v $(pwd):/workspace -v $(pwd)/build:/build cuvs-standalone-c [--tarball-build-tests]
+ENTRYPOINT ["/bin/bash", "-c", "ci/standalone_c/build_standalone_c.sh \"$@\"", "--"]

README.md

@@ -84,6 +84,10 @@ cuVS comes with pre-built packages that can be installed through [conda](https:/
 
 Please see the [Build and Install Guide](https://docs.rapids.ai/api/cuvs/nightly/build/) for more information on installing the available cuVS packages and building from source.
 
+### Standalone C library (Docker)
+
+To build the standalone C library tarball (`libcuvs_c.tar.gz`) for use in your own C/C++ projects, see **[Building the standalone C library with Docker](https://docs.nvidia.com/cuvs/installation#build-the-standalone-c-library-with-docker)**.
+
 ## Getting Started
 
 The following code snippets train an approximate nearest neighbors index for the CAGRA algorithm in the various different languages supported by cuVS.