Registry / vector-search / libcuvs-cu12

libcuvs-cu12

JSON →
library26.6.0pypypiunverified

cuVS C++ shared library for GPU-accelerated vector search (includes CAGRA, IVF-PQ, HNSW). Version 26.4.0. Released as part of RAPIDS monthly releases.

pip install libcuvs-cu12
INSTALL
IMPORT
SIG · LIBCUVS-CU12
L
libcuvs-cu12
vector-searchpythonv26.6.0
Install
51.6s avg
Import
Disk
3430MB
Pass rate
4/ 10
Env Coverage4 / 10
glibc
3.93.13
musl
3.93.13
Install & Compatibility
Where this runs
tested against v26.2.0 · pip install
no network on importno background threads
Install × environment matrix
Each cell = how many times install + import succeeded across repeated harness runs. Partial = flaky.
glibc = Debian/Ubuntu slim · musl = Alpine Linux
musl
glibc
py 3.10
✕ build_error
✓ 59.2s
py 3.11
✕ build_error
✓ 57.8s
py 3.12
✕ build_error
✓ 44.8s
py 3.13
✕ build_error
✓ 44.4s
py 3.9
✕ build_error
✕ build_error
3430MB installed
● package 3430MB
Code
Verified usage

Verified import paths — ran on the pinned version, not inferred.

cuvs
import cuvs
import libcuvs_cu12
libcuvs-cu12 is a C++ backend; the Python API is in the `cuvs` package.
CagraIndex
from cuvs.neighbors import cagra
from libcuvs_cu12 import CagraIndex
CAGRA index is accessed via the `cuvs` Python package.

Build a CAGRA index and search using the `cuvs` Python package. libcuvs-cu12 is the C++ backend installed automatically.

import cupy as cp import cuvs from cuvs.neighbors import cagra rs = cuvs.raft.RaftResourceManager() data = cp.random.random((1000, 128)) index = cagra.build(rs, data) queries = cp.random.random((10, 128)) distances, neighbors = cagra.search(index, queries, k=10)
Debug
Known issues
breakingHNSW GPU hierarchy is now default as of v26.04.00. Existing HNSW parameters may need adjustment.
fix
Review HNSW build parameters; refer to migration guide.
affects: >=26.4.0
breakingStatic linking of libcudart is now default (v26.04.00). May conflict with existing CUDA runtime libraries.
fix
Set CUDA dynamic linking if needed; see RAPIDS docs.
affects: >=26.4.0
breakingCAGRA C API enums changed to stable values (v25.12.00). Old enum values no longer work.
fix
Update enum usage to match new C API header.
affects: >=25.12.0,<26.0.0
deprecatedJava bindings: `destroyIndex()` replaced by `close()` (v25.10.00).
fix
Use `close()` method instead of `destroyIndex()`.
affects: >=25.10.0
gotchalibcuvs-cu12 is a C++ library; do not import directly in Python. Instead, use the `cuvs` Python package.
fix
Install `cuvs` (pip install cuvs) which depends on libcuvs-cu12.
affects: all
Upgrade
Version history
26.6.0latest on PyPI · released Jun 9, 2026
Audit
Dependencies
cupy-cuda12xrequiredRequired for GPU operations and data transfer
nvidia-cuda-runtime-cu12requiredCUDA runtime shared library
Agent activity
30 hits · last 30 days
node
26
OpenAI (training)
1
Resources