NVIDIA / NVIDIA/cuvs

[QST] How to predict the memory required to build an index with CagraIndex using IVFPQ

Open
#566 14 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

What is your question?
I am trying to build a CagraIndex(intermediate graph using IVFPQ) with 10M 768D documents. Anytime I am trying to build the index I am getting OOM exceptions.

My Machine:

  1. g5.2xlarge
  2. CPU RAM: 32GB
  3. GPU memory: 24GB
  4. Using Faiss python bindings to build the index. I have validated that Faiss is using the Cuvs and not raft.

I would like to know how I can predict the machine size required to build the index?

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 by reproducing the CagraIndex build with the stated 10M 768D dataset, IVFPQ configuration, Faiss Python bindings, and g5.2xlarge memory limits. Trace the index-building memory requirements and document a reliable sizing method, with completion defined as guidance that explains or predicts the required CPU and GPU memory.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
search
Issue type
Documentation
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.