NVIDIA / NVIDIA/raft

[FEA] `raft-ann-bench.run` should distinguish the output from different search modes

Open
#2,147 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

feature request Vector Search
Dominant language
Cuda
Stars
1k
Forks
251
Avg merge
1d 8h
Merged PRs (30d)
31

Description

Is your feature request related to a problem? Please describe.

Currently raft-ann-bench.run does not distinguish the output from different search modes (latency or throughtput). As a result, the result file may be overwritten when we run raft-ann-bench.run in different search mods.

Describe the solution you'd like

Encode the search mode in the file name. E.g. hnswlib,base,k10,bs1,latency.json.

Contributor guide

No contributing guide indexed for this repository

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 the raft-ann-bench.run entry point and trace how its output filename is assembled for latency and throughput modes. Run both search modes to confirm the current collision, then verify that each mode produces a distinct filename such as the proposed latency-suffixed form.

Written by the indexing model from the issue text.

Assessment

Domain
performance
Issue type
Feature
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
45/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.