Menu
Back to Open Source

🐙 GitHub Detail

L

patilyashvardhan2002-byte/lazy-moe

By patilyashvardhan2002-byte

The GPU-free LLM inference engine. Combines lazy expert loading + TurboQuant KV compression to run models that shouldn't fit on your hardware. Built from scratch, fully local, zero cloud.

GitHub Python Updated 25 May 2026

Live Snapshot

Stars

23

🍴

Forks

4

📄

License

Unknown

🧩

Type

Python

📘

About this open-source project

Live information fetched from GitHub.

The GPU-free LLM inference engine. Combines lazy expert loading + TurboQuant KV compression to run models that shouldn't fit on your hardware. Built from scratch, fully local, zero cloud.

🌿

Default Branch

main

🐞

Open Issues

0

👀

Watchers

23