lmstudio-ai / lmstudio-ai/mlx-engine

LFM 2.5 VL is not using ModelKit

Open
#261 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
1.2k
Forks
133
Avg merge
21h 6m
Merged PRs (30d)
1

Description

The LFM 2.5 VL model (e.g. lmstudio-community/LFM2.5-VL-1.6B-MLX-4bit) is not using ModelKit, so we do not get prompt caching for text-only prompts.

I created the will/lfm-2.5-unified branch to document the failure. Adding to ModelKit would fix.

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 reviewing the will/lfm-2.5-unified branch, which documents the LFM 2.5 VL failure, and locate the ModelKit integration for the lmstudio-community/LFM2.5-VL-1.6B-MLX-4bit model. Verify that text-only prompts use ModelKit and receive prompt caching; the issue is done when this model no longer bypasses ModelKit.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai, machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 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.