X-rayLaser/DistributedLLM

Run LLM inference by spliting models into parts and hosting each part on a separate machine. Project is no longer maintained.

20
/ 100
Experimental

This project helps you run large language models (LLMs) even if they are too big for a single computer's memory. You provide your LLM and a simple configuration, and the system splits the model across multiple machines and manages the connections. This is for users who want to run powerful LLMs without needing extremely high-end, single-machine hardware.

No commits in the last 6 months.

Use this if you need to run large LLaMA v1 or OpenLLaMA v1 models for basic text generation but your models don't fit on a single machine's RAM.

Not ideal if you need to work with LLaMA v2, OpenLLaMA v2, or chat-specific models, or if you require GPU support as these features are not yet implemented.

large-language-models distributed-computing natural-language-generation model-deployment AI-inference
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

8

Forks

Language

Python

License

MIT

Last pushed

Sep 29, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/X-rayLaser/DistributedLLM"

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