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

fix: quantization precision #537

Merged
merged 2 commits into from
Jul 23, 2024
Merged

fix: quantization precision #537

merged 2 commits into from
Jul 23, 2024

Conversation

usamoi
Copy link
Collaborator

@usamoi usamoi commented Jul 23, 2024

It's still a little worser than faiss-ivfpq.

This pr deprecates veci8 by the way.

@VoVAllen
Copy link
Member

What's the precision problem?

@usamoi
Copy link
Collaborator Author

usamoi commented Jul 23, 2024

What's the precision problem?

Spherical k-means is used for both product quantization and IVF before. But it should not be used in product quantization. This pr removes normalization in k-means when it's used for PQ.

@usamoi usamoi added this pull request to the merge queue Jul 23, 2024
Merged via the queue into tensorchord:main with commit 9667902 Jul 23, 2024
13 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants