NVIDIA / NVIDIA/cuvs

[BUG] "MetricObjective" needs to be plumbed through algorithms in cuvs-bench

Open
#739 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

It looks like when cuvs-bench was migrated from RAFT, the metric objective (latency vs throughput) was broken. See this line of code, which was added to cuvs-bench but doesn't exist in the raft-ann-bench, for example. We need to fix this.

cc @achirkin @divyegala

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 with cpp/bench/ann/src/hnswlib/hnswlib_wrapper.h at the linked line, then compare the cuvs-bench migration with the corresponding raft-ann-bench implementation. Trace how MetricObjective reaches each algorithm and verify that latency-versus-throughput behavior is preserved across the affected benchmarks.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
performance
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.