predibase/lorax

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

47
/ 100
Emerging

This tool helps machine learning engineers and MLOps teams efficiently manage and deploy many specialized AI models (called 'adapters') that run on top of larger foundational models. It takes your fine-tuned LoRA adapters and a base Large Language Model, and provides a scalable inference server. The output is fast, cost-effective text generation from any of your specialized models.

3,735 stars. No commits in the last 6 months.

Use this if you need to serve hundreds or thousands of fine-tuned large language models without incurring massive GPU costs or compromising on response speed.

Not ideal if you only need to run a single large language model or don't have GPU infrastructure available.

LLM deployment model serving AI infrastructure MLOps scalable inference
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

3,735

Forks

309

Language

Python

License

Apache-2.0

Last pushed

May 21, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/predibase/lorax"

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