NVIDIA / NVIDIA/cuEmbed

Embedding cache support

Open
#7 3 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Cuda
Stars
50
Forks
9
PR merge metrics
No merged PRs in 30d

Description

Many thanks for the great work!

I was wondering if the embedding cache, which I understand as the deduplication of the indices during table lookup by caching in order to gain performance, will be supported in CuEmbed?

Also, do you think there will be any performance gain/loss since there will be extra operations such as sorting in the forward pass?

Kind regards

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 asks whether embedding-cache support will be added to CuEmbed and whether deduplication, caching, and sorting affect performance. No files, tests, or entry points are named. First identify the embedding lookup implementation and existing performance benchmarks, then determine the cache design and measurable completion criteria.

Written by the indexing model from the issue text.

Assessment

Domain
machine-learning, performance
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.