Merge remote-tracking branch 'origin/branch-25.02' into vamana_cleanup

Author: bkarsin

.pre-commit-config.yaml

@@ -1,6 +1,11 @@
-# Copyright (c) 2022-2023, NVIDIA CORPORATION.
+# Copyright (c) 2022-2025, NVIDIA CORPORATION.
 
 repos:
+      - repo: https://github.com/pre-commit/pre-commit-hooks
+        rev: v5.0.0
+        hooks:
+              - id: trailing-whitespace
+              - id: end-of-file-fixer
       - repo: https://github.com/PyCQA/isort
         rev: 5.12.0
         hooks:
@@ -81,7 +86,7 @@ repos:
                 exclude: .*/thirdparty/.*
               - id: include-check
                 name: include-check
-                entry: python ./cpp/scripts/include_checker.py cpp/bench cpp/include cpp/test
+                entry: python ./cpp/scripts/include_checker.py cpp/bench cpp/include cpp/tests
                 pass_filenames: false
                 language: python
                 additional_dependencies: [gitpython]

README.md

@@ -29,9 +29,9 @@ cuVS contains state-of-the-art implementations of several algorithms for running
 
 Vector search is an information retrieval method that has been growing in popularity over the past few  years, partly because of the rising importance of multimedia embeddings created from unstructured data and the need to perform semantic search on the embeddings to find items which are semantically similar to each other.
 
-Vector search is also used in _data mining and machine learning_ tasks and comprises an important step in many _clustering_ and _visualization_ algorithms like [UMAP](https://arxiv.org/abs/2008.00325), [t-SNE](https://lvdmaaten.github.io/tsne/), K-means, and [HDBSCAN](https://hdbscan.readthedocs.io/en/latest/how_hdbscan_works.html). 
+Vector search is also used in _data mining and machine learning_ tasks and comprises an important step in many _clustering_ and _visualization_ algorithms like [UMAP](https://arxiv.org/abs/2008.00325), [t-SNE](https://lvdmaaten.github.io/tsne/), K-means, and [HDBSCAN](https://hdbscan.readthedocs.io/en/latest/how_hdbscan_works.html).
 
-Finally, faster vector search enables interactions between dense vectors and graphs. Converting a pile of dense vectors into nearest neighbors graphs unlocks the entire world of graph analysis algorithms, such as those found in [GraphBLAS](https://graphblas.org/) and [cuGraph](https://github.com/rapidsai/cugraph). 
+Finally, faster vector search enables interactions between dense vectors and graphs. Converting a pile of dense vectors into nearest neighbors graphs unlocks the entire world of graph analysis algorithms, such as those found in [GraphBLAS](https://graphblas.org/) and [cuGraph](https://github.com/rapidsai/cugraph).
 
 Below are some common use-cases for vector search
 
@@ -45,7 +45,7 @@ Below are some common use-cases for vector search
   - Audio search
   - Molecular search
   - Model training
-  
+
 
 - ### Data mining
   - Clustering algorithms
@@ -71,7 +71,7 @@ In addition to the items above, cuVS takes on the burden of keeping non-trivial
 
 ## cuVS Technology Stack
 
-cuVS is built on top of the RAPIDS RAFT library of high performance machine learning primitives and provides all the necessary routines for vector search and clustering on the GPU. 
+cuVS is built on top of the RAPIDS RAFT library of high performance machine learning primitives and provides all the necessary routines for vector search and clustering on the GPU.
 
 ![cuVS is built on top of low-level CUDA libraries and provides many important routines that enable vector search and clustering on the GPU](img/tech_stack.png "cuVS Technology Stack")
 
@@ -103,7 +103,7 @@ pip install cuvs-cu11 --extra-index-url=https://pypi.nvidia.com
 And CUDA 12 packages:
 ```bash
 pip install cuvs-cu12 --extra-index-url=https://pypi.nvidia.com
-```    
+```
 
 ### Nightlies
 If installing a version that has not yet been released, the `rapidsai` channel can be replaced with `rapidsai-nightly`:
@@ -240,7 +240,7 @@ If you are interested in contributing to the cuVS library, please read our [Cont
 
 ## References
 
-For the interested reader, many of the accelerated implementations in cuVS are also based on research papers which can provide a lot more background. We also ask you to please cite the corresponding algorithms by referencing them in your own research. 
+For the interested reader, many of the accelerated implementations in cuVS are also based on research papers which can provide a lot more background. We also ask you to please cite the corresponding algorithms by referencing them in your own research.
 - [CAGRA: Highly Parallel Graph Construction and Approximate Nearest Neighbor Search](https://arxiv.org/abs/2308.15136)
 - [Top-K Algorithms on GPU: A Comprehensive Study and New Methods](https://dl.acm.org/doi/10.1145/3581784.3607062)
 - [Fast K-NN Graph Construction by GPU Based NN-Descent](https://dl.acm.org/doi/abs/10.1145/3459637.3482344?casa_token=O_nan1B1F5cAAAAA:QHWDEhh0wmd6UUTLY9_Gv6c3XI-5DXM9mXVaUXOYeStlpxTPmV3nKvABRfoivZAaQ3n8FWyrkWw>)

ci/run_cuvs_pytests.sh

@@ -6,4 +6,4 @@ set -euo pipefail
 # Support invoking run_pytests.sh outside the script directory
 cd "$(dirname "$(realpath "${BASH_SOURCE[0]}")")"/../python/cuvs/cuvs
 
-pytest --cache-clear --verbose "$@" test
+pytest --cache-clear --verbose "$@" tests

ci/test_python.sh

@@ -52,7 +52,7 @@ pytest \
  --cov=cuvs \
  --cov-report=xml:"${RAPIDS_COVERAGE_DIR}/cuvs-coverage.xml" \
  --cov-report=term \
- test
+ tests
 
 rapids-logger "Test script exiting with value: $EXITCODE"
 exit ${EXITCODE}

ci/test_wheel_cuvs.sh

@@ -13,4 +13,4 @@ python -m pip install \
     ./local-libcuvs-dep/libcuvs*.whl \
     "$(echo ./dist/cuvs*.whl)[test]"
 
-python -m pytest ./python/cuvs/cuvs/test
+python -m pytest ./python/cuvs/cuvs/tests

cpp/.clang-format

@@ -27,7 +27,7 @@ AlwaysBreakAfterDefinitionReturnType: None
 AlwaysBreakAfterReturnType: None
 AlwaysBreakBeforeMultilineStrings: true
 AlwaysBreakTemplateDeclarations: Yes
-BinPackArguments:  false       
+BinPackArguments:  false
 BinPackParameters: false
 BraceWrapping:
   AfterClass:            false

cpp/CMakeLists.txt

@@ -685,6 +685,7 @@ target_compile_definitions(cuvs::cuvs INTERFACE $<$<BOOL:${CUVS_NVTX}>:NVTX_ENAB
       src/neighbors/cagra_c.cpp
       $<$<BOOL:${BUILD_CAGRA_HNSWLIB}>:src/neighbors/hnsw_c.cpp>
       src/neighbors/refine/refine_c.cpp
+      src/preprocessing/quantize/scalar_c.cpp
       src/distance/pairwise_distance_c.cpp
     )
 
@@ -797,7 +798,7 @@ endif()
 if(BUILD_TESTS)
   enable_testing()
   add_subdirectory(internal)
-  add_subdirectory(test)
+  add_subdirectory(tests)
 endif()
 
 # ##################################################################################################

cpp/bench/ann/CMakeLists.txt

@@ -20,6 +20,7 @@ list(APPEND CMAKE_MODULE_PATH "${CUVS_SOURCE_DIR}")
 option(CUVS_ANN_BENCH_USE_FAISS_GPU_FLAT "Include faiss' brute-force knn algorithm in benchmark" ON)
 option(CUVS_ANN_BENCH_USE_FAISS_GPU_IVF_FLAT "Include faiss' ivf flat algorithm in benchmark" ON)
 option(CUVS_ANN_BENCH_USE_FAISS_GPU_IVF_PQ "Include faiss' ivf pq algorithm in benchmark" ON)
+option(CUVS_ANN_BENCH_USE_FAISS_GPU_CAGRA "Include faiss' cagra algorithm in benchmark" ON)
 option(CUVS_ANN_BENCH_USE_FAISS_CPU_FLAT "Include faiss' cpu brute-force algorithm in benchmark" ON)
 option(CUVS_ANN_BENCH_USE_FAISS_CPU_IVF_FLAT "Include faiss' cpu ivf flat algorithm in benchmark"
        ON
@@ -275,18 +276,28 @@ endif()
 if(CUVS_ANN_BENCH_USE_FAISS_GPU_IVF_FLAT AND CUVS_FAISS_ENABLE_GPU)
   ConfigureAnnBench(
     NAME FAISS_GPU_IVF_FLAT PATH src/faiss/faiss_gpu_benchmark.cu LINKS ${CUVS_FAISS_TARGETS}
+    raft::raft
   )
 endif()
 
 if(CUVS_ANN_BENCH_USE_FAISS_GPU_IVF_PQ AND CUVS_FAISS_ENABLE_GPU)
   ConfigureAnnBench(
     NAME FAISS_GPU_IVF_PQ PATH src/faiss/faiss_gpu_benchmark.cu LINKS ${CUVS_FAISS_TARGETS}
+    raft::raft
   )
 endif()
 
 if(CUVS_ANN_BENCH_USE_FAISS_GPU_FLAT AND CUVS_FAISS_ENABLE_GPU)
   ConfigureAnnBench(
     NAME FAISS_GPU_FLAT PATH src/faiss/faiss_gpu_benchmark.cu LINKS ${CUVS_FAISS_TARGETS}
+    raft::raft
+  )
+endif()
+
+if(CUVS_ANN_BENCH_USE_FAISS_GPU_CAGRA AND CUVS_FAISS_ENABLE_GPU)
+  ConfigureAnnBench(
+    NAME FAISS_GPU_CAGRA PATH src/faiss/faiss_gpu_benchmark.cu LINKS ${CUVS_FAISS_TARGETS}
+    raft::raft
   )
 endif()
 

cpp/bench/ann/src/cuvs/cuvs_mg_ivf_flat_wrapper.h

@@ -137,4 +137,4 @@ void cuvs_mg_ivf_flat<T, IdxT>::search(
     handle_, *index_, search_params_, queries_view, neighbors_view, distances_view);
 }
 
-}  // namespace cuvs::bench
+}  // namespace cuvs::bench

cpp/bench/ann/src/cuvs/cuvs_mg_ivf_pq_wrapper.h

@@ -136,4 +136,4 @@ void cuvs_mg_ivf_pq<T, IdxT>::search(
     handle_, *index_, search_params_, queries_view, neighbors_view, distances_view);
 }
 
-}  // namespace cuvs::bench
+}  // namespace cuvs::bench