chat / KVCache requires re-prepare of media

Open
#281 3 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

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

Research direction

Start with the chat/KVCache flow described here and compare the related issue ml-explore/mlx-swift-examples#277. Trace where the VLM input prepares images and video, then define how that prepared state should be retained and what behavior demonstrates that re-preparation is avoided.

Written by the indexing model from the issue text.

Description

See also ml-explore/mlx-swift-examples#277

Although KVCache is useful to avoid recomputing state, the full input to the VLM has to be rebuilt each time -- this includes preparing the images and video. It would be nice if we could encapsulate that state somehow.

Dominant language
Swift
Stars
2.7k
Forks
426
No merged PRs in 30d

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.

More from ml-explore/mlx-swift-examples

All issues in ml-explore/mlx-swift-examples

Similar issues

More Swift issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.