kolinko/effort

An implementation of bucketMul LLM inference

38
/ 100
Emerging

This project helps machine learning practitioners fine-tune the performance of large language models (LLMs) on Apple Silicon. It takes an LLM model and allows you to adjust the 'effort' level in real-time, controlling the balance between inference speed and output quality. This is ideal for researchers and developers experimenting with LLM deployment on macOS.

227 stars. No commits in the last 6 months.

Use this if you need to rapidly experiment with different LLM inference speeds and quality levels on Apple Silicon hardware.

Not ideal if you are looking for a solution for LLM inference on non-Apple hardware or if you require maximum possible quality without any compromise on speed.

LLM deployment machine learning inference model optimization Apple Silicon real-time adjustments
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

227

Forks

16

Language

Swift

License

MIT

Last pushed

Jul 01, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/kolinko/effort"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.