NVIDIA / NVIDIA/cuvs

[FEA] Make Vamana Sector Aligned (SSD) Index Compatible With diskannpy.

Open
#1,501 1 comment 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

A serialized vamana ssd index needs to be readily deserialized by diskannpy. This is a tracker to add all additional serialized files that are needed to support this. The complete list of files is at https://github.com/microsoft/DiskANN/blob/a26f824be5a597b49a7bf33f51ee75121e7c03af/python/src/_static_disk_index.py#L51

  • We must investigate if {index_prefix}_sample_data.bin and {index_prefix}_sample_ids.bin is essential or optional
  • As mentioned in #905, the pq_pivots currently are to be supplied by the user
  • For the remaining files, match the correct suffixes with expectations of diskannpy

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 the file list in diskannpy's python/src/_static_disk_index.py at the linked revision, then compare those suffix expectations with the serialized Vamana SSD index. Investigate whether {index_prefix}_sample_data.bin and {index_prefix}_sample_ids.bin are required, and account for the pq_pivots behavior noted in #905. Done means the remaining serialized files use suffixes that diskannpy can deserialize.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
search
Issue type
Feature
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.