Skip to content

[REVIEW] L1 distance support for iterative search CAGRA build#1831

Merged
rapids-bot[bot] merged 9 commits into
NVIDIA:mainfrom
yan-zaretskiy:cagra-l1-iterative-search
Mar 7, 2026
Merged

[REVIEW] L1 distance support for iterative search CAGRA build#1831
rapids-bot[bot] merged 9 commits into
NVIDIA:mainfrom
yan-zaretskiy:cagra-l1-iterative-search

Conversation

@yan-zaretskiy

Copy link
Copy Markdown
Contributor

This PR adds L1 distance support for building the CAGRA index with the iterative search approach. This is work related to #1159. A follow-up PR will add L1 support for NN-Descent.

@copy-pr-bot

copy-pr-bot Bot commented Feb 20, 2026

Copy link
Copy Markdown

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

@yan-zaretskiy yan-zaretskiy added non-breaking Introduces a non-breaking change feature request New feature or request labels Feb 20, 2026
@aamijar

aamijar commented Feb 21, 2026

Copy link
Copy Markdown
Contributor

/ok to test bd694e9

@aamijar

aamijar commented Feb 25, 2026

Copy link
Copy Markdown
Contributor

/ok to test 9b3e233

@tarang-jain tarang-jain left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

LGTM! It is quite amazing that we can add a metric for several different template combinations with the help of an automated python script. The descriptor and the distance op seem accurate. Also love the use of requires in place of SFINAE.

@aamijar

aamijar commented Feb 25, 2026

Copy link
Copy Markdown
Contributor

/ok to test 59e8735

@divyegala divyegala mentioned this pull request Feb 26, 2026
8 tasks
@aamijar

aamijar commented Feb 26, 2026

Copy link
Copy Markdown
Contributor

/ok to test c175003

@divyegala divyegala left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

CMake approval only

@aamijar

aamijar commented Mar 3, 2026

Copy link
Copy Markdown
Contributor

/ok to test a77f56a

@aamijar

aamijar commented Mar 5, 2026

Copy link
Copy Markdown
Contributor

/ok to test 135c05b

@aamijar

aamijar commented Mar 5, 2026

Copy link
Copy Markdown
Contributor

/ok to test f4fa078

@tarang-jain

Copy link
Copy Markdown
Contributor

/ok to test f0f8487

@aamijar

aamijar commented Mar 7, 2026

Copy link
Copy Markdown
Contributor

/merge

@rapids-bot
rapids-bot Bot merged commit bb85ea9 into NVIDIA:main Mar 7, 2026
151 of 153 checks passed
@yan-zaretskiy
yan-zaretskiy deleted the cagra-l1-iterative-search branch March 31, 2026 01:16
rapids-bot Bot pushed a commit that referenced this pull request May 9, 2026
CUDA 13 binary size reduction from 282 MB to 257 MB (-8.86%).

Benchmark:
<img width="1137" height="776" alt="image" src="https://github.com/user-attachments/assets/81b4f25a-c999-423d-a2c9-3e45566904bf" />

Apply updates from 
CAGRA related PRs:

- [x] #1800
- [ ] #1781
- [x] #1780
- [x] #1771
- [x] #1834
- [x] #1851
- [x] #1831

JIT related PRs:
- [x] #1812

Authors:
  - Divye Gala (https://github.com/divyegala)
  - Kyle Edwards (https://github.com/KyleFromNVIDIA)
  - Dante Gama Dessavre (https://github.com/dantegd)
  - Bradley Dice (https://github.com/bdice)

Approvers:
  - Kyle Edwards (https://github.com/KyleFromNVIDIA)
  - Dante Gama Dessavre (https://github.com/dantegd)

URL: #1807
landrumb pushed a commit to landrumb/cuvs that referenced this pull request Jul 8, 2026
…#1831)

This PR adds L1 distance support for building the CAGRA index with the iterative search approach. This is work related to NVIDIA#1159. A follow-up PR will add L1 support for NN-Descent.

Authors:
  - Yan Zaretskiy (https://github.com/yan-zaretskiy)
  - Anupam (https://github.com/aamijar)
  - Tarang Jain (https://github.com/tarang-jain)

Approvers:
  - Tarang Jain (https://github.com/tarang-jain)
  - Divye Gala (https://github.com/divyegala)

URL: NVIDIA#1831
landrumb pushed a commit to landrumb/cuvs that referenced this pull request Jul 8, 2026
CUDA 13 binary size reduction from 282 MB to 257 MB (-8.86%).

Benchmark:
<img width="1137" height="776" alt="image" src="https://github.com/user-attachments/assets/81b4f25a-c999-423d-a2c9-3e45566904bf" />

Apply updates from 
CAGRA related PRs:

- [x] NVIDIA#1800
- [ ] NVIDIA#1781
- [x] NVIDIA#1780
- [x] NVIDIA#1771
- [x] NVIDIA#1834
- [x] NVIDIA#1851
- [x] NVIDIA#1831

JIT related PRs:
- [x] NVIDIA#1812

Authors:
  - Divye Gala (https://github.com/divyegala)
  - Kyle Edwards (https://github.com/KyleFromNVIDIA)
  - Dante Gama Dessavre (https://github.com/dantegd)
  - Bradley Dice (https://github.com/bdice)

Approvers:
  - Kyle Edwards (https://github.com/KyleFromNVIDIA)
  - Dante Gama Dessavre (https://github.com/dantegd)

URL: NVIDIA#1807
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

feature request New feature or request non-breaking Introduces a non-breaking change

Projects

Status: Done

Development

Successfully merging this pull request may close these issues.

5 participants