NVIDIA / NVIDIA/cuvs

[FEA] Reduce template parameters

Open
#110 2 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, there's a lot of template params that could easily become runtime parameter. Every template param causes the need to compile more instantiations. If we reduce template params, we will improve compile time and binary size.

  • Pairwise distances distance metric arg
  • ANN filter type (make polymorphic)
  • Reduce CAGRA / CAGRA-Q templates (make more runtime hyper-params)

@tfeher @divyegala @achirkin @benfred please add to this list as opportunities arise.

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

The issue identifies pairwise-distance metrics, the ANN filter type, and CAGRA/CAGRA-Q templates as starting areas; no files or tests are named. Locate those entry points first, then determine which parameters can become runtime values. Done means reducing the selected template parameters while improving compile time and binary size.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
performance
Issue type
Refactor
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.