Skip to content
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.

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

CAGRA ANN bench: parse build options for IVF-PQ build algo #1912

Merged

Conversation

tfeher
Copy link
Contributor

@tfeher tfeher commented Oct 18, 2023

This PR enables fine tuning the the parameters for CAGRA index building using the IVF-PQ build algo.

This is only affects ANN bechmarks (an example json file is added). The public API of CAGRA is not changed because:

  • Advanced users can achieve the same effect by calling build_knn_graph and optimize individually.
  • Long term we consider NN descent to be the preferred build algo, which does not need IVF-PQ parameters.

@tfeher tfeher added improvement Improvement / enhancement to an existing function non-breaking Non-breaking change Vector Search labels Oct 18, 2023
@tfeher tfeher requested a review from a team as a code owner October 18, 2023 23:12
@github-actions github-actions bot added the cpp label Oct 18, 2023
@tfeher tfeher requested a review from a team as a code owner October 18, 2023 23:25
Copy link
Member

@cjnolet cjnolet left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM!

@cjnolet
Copy link
Member

cjnolet commented Nov 7, 2023

/merge

@rapids-bot rapids-bot bot merged commit c7aa826 into rapidsai:branch-23.12 Nov 7, 2023
57 checks passed
benfred pushed a commit to benfred/raft that referenced this pull request Nov 8, 2023
…1912)

This PR enables fine tuning the the parameters for CAGRA index building using the IVF-PQ build algo.

This is only affects ANN bechmarks (an example json file is added). The public API of CAGRA is not changed because:
- Advanced users can achieve the same effect by calling `build_knn_graph` and `optimize` individually.
- Long term we consider NN descent to be the preferred build algo, which does not need IVF-PQ parameters.

Authors:
  - Tamas Bela Feher (https://github.com/tfeher)
  - Corey J. Nolet (https://github.com/cjnolet)

Approvers:
  - Corey J. Nolet (https://github.com/cjnolet)

URL: rapidsai#1912
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
cpp improvement Improvement / enhancement to an existing function non-breaking Non-breaking change python Vector Search
Projects
Development

Successfully merging this pull request may close these issues.

3 participants