ml-explore / ml-explore/mlx-examples

Higher Speed High-Context processing w/ Minference

Open
#1,245 0 comments 2 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
9k
Forks
1.2k
PR merge metrics
No merged PRs in 30d

Description

Would it be possible to implement the KV architecture from MInference to speed up long-context inputs (ex. for Qwen2.5-1M)?

https://github.com/microsoft/MInference

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 names no target file, test, or entry point. Read the linked MInference project and inspect the Python MLX examples to identify the long-context processing path; done should include the requested KV architecture and faster processing for inputs such as Qwen2.5-1M.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
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.