NVIDIA / NVIDIA/cuvs

PQ preprocessor does not natively support padded datasets

Open
#2,567 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

feature request
Dominant language
Cuda
Stars
854
Forks
236
Avg merge
3d 3h
Merged PRs (30d)
62

Description

Currently, the make_device_pq_dataset can accept a padded_dataset type but internally copies it to a contiguous dense dataset since its helpers like train_from_rows do not support encoding padded datasets.

https://github.com/NVIDIA/cuvs/blob/51dc5d4523b5f50aeea19151d70af46f283654f3/cpp/src/preprocessing/quantize/pq.cu#L99-L111

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start in cpp/src/preprocessing/quantize/pq.cu around lines 99-111 and trace make_device_pq_dataset and its train_from_rows helpers. Determine how padded_dataset encoding can avoid the contiguous dense copy, then verify the preprocessor handles padded input correctly with relevant tests.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
data
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Active
Clarity
Mostly clear
Newbie friendliness
58/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.