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

[Backport 2.17] Makes sure KNNVectorValues aren't recreated unnecessarily when quantization isn't needed (#2133) #2140

Conversation

shatejas
Copy link
Collaborator

@shatejas shatejas commented Sep 24, 2024

[Backport 2.17] Makes sure KNNVectorValues aren't recreated unnecessarily when quantization isn't needed (#2133)

Signed-off-by: Tejas Shah [email protected]
(cherry picked from commit e33afa5)

Description

Backport PR for #2133

Check List

  • New functionality includes testing.
  • New functionality has been documented.
  • API changes companion pull request created.
  • Commits are signed per the DCO using --signoff.
  • Public documentation issue/PR created.

By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.
For more information on following Developer Certificate of Origin and signing off your commits, please check here.

@navneet1v navneet1v changed the title [Backport 2.17] Makes sure KNNVectorValues aren't recreated unnecessarily when quanti… [Backport 2.17] Makes sure KNNVectorValues aren't recreated unnecessarily when quantization isn't needed (#2133) Sep 24, 2024
@shatejas shatejas force-pushed the backport/backport-2133-to-2.17 branch from 4e98c64 to 18e0c2c Compare September 24, 2024 19:25
@@ -20,6 +20,7 @@ Compatible with OpenSearch 2.17.0
* Fix memory overflow caused by cache behavior [#2015](https://github.com/opensearch-project/k-NN/pull/2015)
* Use correct type for binary vector in ivf training [#2086](https://github.com/opensearch-project/k-NN/pull/2086)
* Switch MINGW32 to MINGW64 [#2090](https://github.com/opensearch-project/k-NN/pull/2090)
* * Does not create additional KNNVectorValues in NativeEngines990KNNVectorWriter when quantization is not needed [#2133](https://github.com/opensearch-project/k-NN/pull/2133)
Copy link
Collaborator

Choose a reason for hiding this comment

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

there should be only * here. @shatejas

…zation isn't needed (opensearch-project#2133)

Signed-off-by: Tejas Shah <[email protected]>
(cherry picked from commit e33afa5)
@naveentatikonda naveentatikonda merged commit ca6b03f into opensearch-project:2.17 Sep 27, 2024
96 of 97 checks passed
naveentatikonda added a commit to naveentatikonda/k-NN that referenced this pull request Sep 27, 2024
naveentatikonda added a commit to naveentatikonda/k-NN that referenced this pull request Sep 27, 2024
…n quantization isn't needed (opensearch-project#2133) (opensearch-project#2140)"

This reverts commit ca6b03f.

Signed-off-by: Naveen Tatikonda <[email protected]>
naveentatikonda added a commit that referenced this pull request Sep 27, 2024
…n quantization isn't needed (#2133) (#2140)" (#2161)

This reverts commit ca6b03f.

Signed-off-by: Naveen Tatikonda <[email protected]>
navneet1v added a commit to navneet1v/k-NN that referenced this pull request Sep 28, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants