Multi segment cagra search

.gitignore

@@ -1,9 +1,14 @@
 # SPDX-FileCopyrightText: Copyright (c) 2025, NVIDIA CORPORATION.
 # SPDX-License-Identifier: Apache-2.0
 
+# Maven
 *.jar
-target
-**/.DS_Store
-bin
+target/
+
+# IDE - IntelliJ
+.idea/
+*.iml
+
+# IDE - Eclipse
 .project
 cuvs-workdir

bench/pom.xml

@@ -11,7 +11,7 @@
 
     <groupId>com.nvidia.cuvs.lucene.benchmarks</groupId>
     <artifactId>cuvs-lucene-benchmarks</artifactId>
-    <!--CUVS_LUCENE#VERSION_UPDATE_MARKER_START--><version>26.08.0</version><!--CUVS_LUCENE#VERSION_UPDATE_MARKER_END-->
+    <!--CUVS_LUCENE#VERSION_UPDATE_MARKER_START--><version>26.08.0-SNAPSHOT</version><!--CUVS_LUCENE#VERSION_UPDATE_MARKER_END-->
     <packaging>jar</packaging>
 
     <name>cuvs-lucene-benchmarks</name>
@@ -85,7 +85,7 @@
         <dependency>
             <groupId>com.nvidia.cuvs.lucene</groupId>
             <artifactId>cuvs-lucene</artifactId>
-            <!--CUVS_LUCENE#VERSION_UPDATE_MARKER_START--><version>26.08.0</version><!--CUVS_LUCENE#VERSION_UPDATE_MARKER_END-->
+            <!--CUVS_LUCENE#VERSION_UPDATE_MARKER_START--><version>26.08.0-SNAPSHOT</version><!--CUVS_LUCENE#VERSION_UPDATE_MARKER_END-->
         </dependency>
 	    <dependency>
 	        <groupId>commons-io</groupId>

build.sh

@@ -1,14 +1,14 @@
 #!/bin/bash
 
-# SPDX-FileCopyrightText: Copyright (c) 2025-2026, NVIDIA CORPORATION.
+# SPDX-FileCopyrightText: Copyright (c) 2025-2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 # SPDX-License-Identifier: Apache-2.0
 
 set -e -u -o pipefail
 
 ARGS="$*"
 NUMARGS=$#
 
-VERSION="26.08.0" # Note: The version is updated automatically when ci/release/update-version.sh is invoked
+VERSION="26.08.0-SNAPSHOT" # Note: The version is updated automatically when ci/release/update-version.sh is invoked
 GROUP_ID="com.nvidia.cuvs.lucene"
 
 function hasArg {

examples/pom.xml

@@ -11,7 +11,7 @@
 
   <groupId>com.nvidia.cuvs.lucene.examples</groupId>
   <artifactId>examples</artifactId>
-  <!--CUVS_LUCENE#VERSION_UPDATE_MARKER_START--><version>26.08.0</version><!--CUVS_LUCENE#VERSION_UPDATE_MARKER_END-->
+  <!--CUVS_LUCENE#VERSION_UPDATE_MARKER_START--><version>26.08.0-SNAPSHOT</version><!--CUVS_LUCENE#VERSION_UPDATE_MARKER_END-->
   <name>examples</name>
 
   <properties>
@@ -100,7 +100,7 @@
     <dependency>
       <groupId>com.nvidia.cuvs.lucene</groupId>
       <artifactId>cuvs-lucene</artifactId>
-      <!--CUVS_LUCENE#VERSION_UPDATE_MARKER_START--><version>26.08.0</version><!--CUVS_LUCENE#VERSION_UPDATE_MARKER_END-->
+      <!--CUVS_LUCENE#VERSION_UPDATE_MARKER_START--><version>26.08.0-SNAPSHOT</version><!--CUVS_LUCENE#VERSION_UPDATE_MARKER_END-->
     </dependency>
   </dependencies>
 

examples/src/main/java/com/nvidia/cuvs/lucene/examples/IndexAndSearchonGPUExample.java

@@ -1,5 +1,5 @@
 /*
- * SPDX-FileCopyrightText: Copyright (c) 2025-2026, NVIDIA CORPORATION.
+ * SPDX-FileCopyrightText: Copyright (c) 2025-2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
  * SPDX-License-Identifier: Apache-2.0
  */
 package com.nvidia.cuvs.lucene.examples;
@@ -30,9 +30,12 @@
 import org.apache.lucene.index.IndexWriterConfig;
 import org.apache.lucene.index.LeafReader;
 import org.apache.lucene.index.LeafReaderContext;
+import org.apache.lucene.index.Term;
 import org.apache.lucene.search.IndexSearcher;
 import org.apache.lucene.search.KnnFloatVectorQuery;
+import org.apache.lucene.search.Query;
 import org.apache.lucene.search.ScoreDoc;
+import org.apache.lucene.search.TermQuery;
 import org.apache.lucene.search.TopDocs;
 import org.apache.lucene.store.Directory;
 import org.apache.lucene.store.FSDirectory;
@@ -56,6 +59,7 @@ public static void main(String[] args) throws Exception {
     final int COMMIT_FREQ = 2000;
     final String ID_FIELD = "id";
     final String VECTOR_FIELD = "vector_field";
+    final String STATUS_FIELD = "status";
 
     int numDocs = 2000;
     int dimension = 32;
@@ -70,6 +74,9 @@ public static void main(String[] args) throws Exception {
         Document document = new Document();
         document.add(new StringField(ID_FIELD, Integer.toString(i), Field.Store.YES));
         document.add(new KnnFloatVectorField(VECTOR_FIELD, dataset[i], EUCLIDEAN));
+        // Alternatively flip the status's for documents as an example.
+        document.add(
+            new StringField(STATUS_FIELD, i % 2 == 0 ? "active" : "in-active", Field.Store.YES));
         indexWriter.addDocument(document);
         count -= 1;
         if (count == 0) {
@@ -103,8 +110,11 @@ public static void main(String[] args) throws Exception {
       float[] queryVector = generateDataset(random, 1, dimension)[0];
       log.log(Level.FINE, "Query vector: " + Arrays.toString(queryVector));
 
+      // Make a filter query
+      Query filter = new TermQuery(new Term(STATUS_FIELD, "active"));
+
       KnnFloatVectorQuery query =
-          new GPUKnnFloatVectorQuery(VECTOR_FIELD, queryVector, topK, null, topK, 1);
+          new GPUKnnFloatVectorQuery(VECTOR_FIELD, queryVector, topK, filter, topK, 1);
       TopDocs results = searcher.search(query, topK);
 
       log.log(Level.FINE, "Search results (" + results.totalHits + " total hits):");
@@ -113,12 +123,15 @@ public static void main(String[] args) throws Exception {
         ScoreDoc scoreDoc = results.scoreDocs[i];
         Document doc = searcher.storedFields().document(scoreDoc.doc);
         String id = doc.get(ID_FIELD);
+        String status = doc.get(STATUS_FIELD);
         log.log(
             Level.FINE,
             "  Rank "
                 + (i + 1)
                 + ": doc "
                 + scoreDoc.doc
+                + " status "
+                + status
                 + " (id="
                 + id
                 + "), score="

license-header.txt

@@ -0,0 +1,4 @@
+/*
+ * SPDX-FileCopyrightText: Copyright (c) $YEAR, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+ * SPDX-License-Identifier: Apache-2.0
+ */

pom.xml

@@ -12,7 +12,7 @@
   <groupId>com.nvidia.cuvs.lucene</groupId>
   <artifactId>cuvs-lucene</artifactId>
   <!-- NOTE: The version automatically gets updated when ci/release/update-version.sh is invoked. -->
-  <!--CUVS_LUCENE#VERSION_UPDATE_MARKER_START--><version>26.08.0</version><!--CUVS_LUCENE#VERSION_UPDATE_MARKER_END-->
+  <!--CUVS_LUCENE#VERSION_UPDATE_MARKER_START--><version>26.08.0-SNAPSHOT</version><!--CUVS_LUCENE#VERSION_UPDATE_MARKER_END-->
   <name>cuvs-lucene</name>
   <packaging>jar</packaging>
 
@@ -36,6 +36,18 @@
       <url>https://github.com/rapidsai/cuvs-lucene</url>
   </scm>
 
+  <developers>
+      <developer>
+          <id>rapidsai</id>
+          <name>rapidsai</name>
+          <email>cuvs@rapids.ai</email>
+          <roles>
+              <role>Maintainer</role>
+              <role>Committer</role>
+          </roles>
+      </developer>
+  </developers>
+
   <properties>
     <maven.compiler.target>22</maven.compiler.target>
     <maven.compiler.source>22</maven.compiler.source>
@@ -68,6 +80,12 @@
                 <enabled>false</enabled>
             </snapshots>
         </repository>
+        <repository>
+            <id>central-snapshots</id>
+            <url>https://central.sonatype.com/repository/maven-snapshots/</url>
+            <snapshots><enabled>true</enabled></snapshots>
+            <releases><enabled>false</enabled></releases>
+        </repository>
     </repositories>
 
     <pluginRepositories>
@@ -129,10 +147,17 @@
     <dependency>
       <groupId>com.nvidia.cuvs</groupId>
       <artifactId>cuvs-java</artifactId>
-      <!--CUVS_LUCENE#VERSION_UPDATE_MARKER_START--><version>26.08.0</version><!--CUVS_LUCENE#VERSION_UPDATE_MARKER_END-->
+      <!--CUVS_LUCENE#VERSION_UPDATE_MARKER_START--><version>26.08.0-SNAPSHOT</version><!--CUVS_LUCENE#VERSION_UPDATE_MARKER_END-->
     </dependency>
   </dependencies>
 
+  <distributionManagement>
+    <snapshotRepository>
+      <id>central</id>
+      <url>https://central.sonatype.com/repository/maven-snapshots/</url>
+    </snapshotRepository>
+  </distributionManagement>
+
   <build>
     <plugins>
       <plugin>
@@ -158,6 +183,9 @@
                     <reflowLongStrings>true</reflowLongStrings>
                     <formatJavadoc>false</formatJavadoc>
                 </googleJavaFormat>
+                <licenseHeader>
+                    <file>${project.basedir}/license-header.txt</file>
+                </licenseHeader>
             </java>
         </configuration>
       </plugin>
@@ -219,6 +247,7 @@
                 <goal>jar</goal>
             </goals>
             <configuration>
+                <includePackageNames>com.nvidia.cuvs.lucene</includePackageNames>
                 <doclint>all,-missing</doclint>
                 <outputDirectory>${project.build.directory}/javadocs</outputDirectory>
             </configuration>

src/main/java/com/nvidia/cuvs/lucene/CuVS2510GPUVectorsFormat.java

@@ -1,12 +1,13 @@
 /*
- * SPDX-FileCopyrightText: Copyright (c) 2025-2026, NVIDIA CORPORATION.
+ * SPDX-FileCopyrightText: Copyright (c) 2025-2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
  * SPDX-License-Identifier: Apache-2.0
  */
 package com.nvidia.cuvs.lucene;
 
 import static com.nvidia.cuvs.lucene.ThreadLocalCuVSResourcesProvider.assertIsSupported;
 
 import com.nvidia.cuvs.LibraryException;
+import com.nvidia.cuvs.spi.CuVSProvider;
 import java.io.IOException;
 import org.apache.lucene.codecs.KnnVectorsFormat;
 import org.apache.lucene.codecs.KnnVectorsReader;
@@ -39,6 +40,7 @@ public class CuVS2510GPUVectorsFormat extends KnnVectorsFormat {
 
   static {
     try {
+      CuVSProvider.provider().enableRMMAsyncMemory();
       LUCENE_PROVIDER = LuceneProvider.getInstance("99");
       FLAT_VECTORS_FORMAT =
           LUCENE_PROVIDER.getLuceneFlatVectorsFormatInstance(DefaultFlatVectorScorer.INSTANCE);

src/main/java/com/nvidia/cuvs/lucene/CuVS2510GPUVectorsReader.java

@@ -1,5 +1,5 @@
 /*
- * SPDX-FileCopyrightText: Copyright (c) 2025-2026, NVIDIA CORPORATION.
+ * SPDX-FileCopyrightText: Copyright (c) 2025-2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
  * SPDX-License-Identifier: Apache-2.0
  */
 package com.nvidia.cuvs.lucene;
@@ -430,7 +430,10 @@ public void search(String field, float[] target, KnnCollector knnCollector, Bits
         }
       }
       topK = Math.min(knnCollector.k() + 10, mask[0].cardinality());
-      maskLength = mask[0].length();
+      // numDocs must be the total vector count so cuVS sizes the prefilter to cover every ordinal.
+      // BitSet.length() is (highest set bit + 1), which under a selective filter is smaller than the
+      // vector count, leaving the trailing ordinals outside the filter and thus default-accepted.
+      maskLength = acceptedOrds.length();
     }
 
     try {
@@ -443,6 +446,9 @@ public void search(String field, float[] target, KnnCollector knnCollector, Bits
               new CagraSearchParams.Builder()
                   .withItopkSize(Math.max(collector.getiTopK(), topK))
                   .withSearchWidth(collector.getSearchWidth())
+                  .withThreadBlockSize(collector.getThreadBlockSize())
+                  .withMaxIterations(collector.getMaxIterations())
+                  .withAlgo(collector.getSearchAlgo())
                   .build();
         } else {
           // Setting itopK as topK because in any case iTopK should be ATLEAST equal to topK
@@ -509,7 +515,11 @@ public void search(String field, float[] target, KnnCollector knnCollector, Bits
         if (knnCollector.earlyTerminated()) {
           break;
         }
-        if (ord < 0) {
+        // Empty top-k slots (fewer than k passing candidates) carry a sentinel distance of FLT_MAX.
+        // Prefer this over the neighbor-index sentinel: the index sentinel is not uniform across
+        // CAGRA search algorithms (single-CTA emits 0x7FFFFFFF, multi-CTA 0xFFFFFFFF), so the
+        // distance is the reliable, algorithm-independent signal for an empty slot.
+        if (score == Float.MAX_VALUE) {
           continue;
         }
         float correctedScore = scoreCorrectionFunction.apply(score);
@@ -600,6 +610,22 @@ private static void checkVersion(int versionMeta, int versionVectorData, IndexIn
     }
   }
 
+  /**
+   * Returns the {@link CagraIndex} for the given field, or {@code null} if unavailable
+   * (e.g., during a merge or when the field is missing).
+   *
+   * @param field the vector field name
+   * @return the CAGRA index, or {@code null}
+   */
+  public CagraIndex getCagraIndexForField(String field) {
+    if (cuvsIndices == null) return null;
+    FieldInfo info = fieldInfos.fieldInfo(field);
+    if (info == null) return null;
+    GPUIndex gpuIndex = cuvsIndices.get(info.number);
+    if (gpuIndex == null) return null;
+    return gpuIndex.getCagraIndex();
+  }
+
   /**
    * Gets the instance of FieldInfos.
    *