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

Add float16 support in python for cagra/brute_force/ivf_pq and scalar quantizer #637

Merged
merged 2 commits into from
Feb 4, 2025

Conversation

benfred
Copy link
Member

@benfred benfred commented Feb 1, 2025

No description provided.

@benfred benfred added improvement Improves an existing functionality non-breaking Introduces a non-breaking change labels Feb 1, 2025
@benfred benfred self-assigned this Feb 1, 2025
@benfred benfred requested review from a team as code owners February 1, 2025 01:59
@benfred
Copy link
Member Author

benfred commented Feb 1, 2025

note that:

  • ivf_flat doesn't support float16 in the c++ api - so hasn't been added here
  • cagra doesn't support float16 in the 'extend' or 'serializeToHnswLIb' functionality in c++ (which aren't currently exposed to python)(
  • refine/pairwise_distance already supported float16 in python ( Add support for float16 to the python pairwise distance api #547 etc)

@cjnolet
Copy link
Member

cjnolet commented Feb 4, 2025

/merge

@rapids-bot rapids-bot bot merged commit 8c683b0 into rapidsai:branch-25.02 Feb 4, 2025
61 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
cpp improvement Improves an existing functionality non-breaking Introduces a non-breaking change Python
Projects
Development

Successfully merging this pull request may close these issues.

2 participants