Skip to content

Issues: rapidsai/cuvs

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

207 Open 56 Closed
207 Open 56 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

[FEA] CAGRA attach_dataset_on_build Python API support feature request New feature or request
#806 opened Apr 3, 2025 by rchitale7
[BUG] cuvs-bench Bug in data_export bug Something isn't working
#796 opened Apr 1, 2025 by tarang-jain
[FEA] Support for half data types for balanced kmeans fit() feature request New feature or request
#788 opened Mar 25, 2025 by jinsolp
[FEA] Expose trustworthiness_score on more double inputs
#775 opened Mar 18, 2025 by jcrist
[BUG] Very rare case of NN Descent returning max_float values for the distances bug Something isn't working
#771 opened Mar 17, 2025 by jinsolp
cuvs-java: CagraBuildAndSearchIT crashes with pure virtual method called terminate called without an active exception
#764 opened Mar 14, 2025 by ChrisHegarty
[FEA] Improve CAGRA-HNSW index conversion feature request New feature or request
#762 opened Mar 13, 2025 by tfeher
1
[BUG] Low recall with CAGRA when sparsity or dimensionality is high bug Something isn't working
#761 opened Mar 13, 2025 by lokeshwer
[FEA] Add CMake component that contains libdiskann.so feature request New feature or request
#760 opened Mar 13, 2025 by gforsyth
2
[FEA] Add pgvector to cuvs-bench feature request New feature or request
#759 opened Mar 13, 2025 by cjnolet
[BUG] Throw a better error when from_cagra is called with out-of-core built CAGRA index bug Something isn't working
#758 opened Mar 13, 2025 by cjnolet
[BUG] Enable "SVE" opt level for Faiss on Grace CPU bug Something isn't working
#755 opened Mar 11, 2025 by LizYou
[BUG] Stop using private RMM macros in cuvs bug Something isn't working
#754 opened Mar 6, 2025 by bdice
[BUG]CuVS-bench cagra + hnswlib runs into issue with quantized vector evaluation bug Something isn't working
#752 opened Mar 6, 2025 by AmeliaYe
[FEA] Support building all-neighbors graphs on disk feature request New feature or request
#749 opened Mar 4, 2025 by cjnolet
[FEA] Support on-disk DiskANN build feature request New feature or request
#748 opened Mar 4, 2025 by cjnolet
[FEA] Unified single-node multi-GPU APIs feature request New feature or request
#747 opened Mar 4, 2025 by cjnolet
[FEA] We have nightlyt (and release) Rust, Go, and Java artifacts that need to be deployed Build feature request New feature or request improvement Improves an existing functionality
#746 opened Mar 4, 2025 by cjnolet
[FEA] Find a formula to convert HNSWLIB build params to CAGRA build params (for HNSW search) feature request New feature or request
#740 opened Mar 1, 2025 by cjnolet
[BUG] "MetricObjective" needs to be plumbed through algorithms in cuvs-bench bug Something isn't working
#739 opened Mar 1, 2025 by cjnolet
1
[FEA] reduce libcuvs binary size feature request New feature or request
#735 opened Feb 27, 2025 by jameslamb
Less recall post-refinement bug Something isn't working
#734 opened Feb 27, 2025 by AmeliaYe
1
[BUG] cuVS CAGRA gets stalled when using SLURM bug Something isn't working
#732 opened Feb 26, 2025 by abs51295
[DOC] Support billion-scale CAGRA build with conversion to HNSW doc Improvements or additions to documentation
#728 opened Feb 25, 2025 by cjnolet
1
[FEA] General batch knn multi-gpu algorithm implementation feature request New feature or request
#727 opened Feb 25, 2025 by cjnolet
@jinsolp
ProTip! Follow long discussions with comments:>50.