thu-pacman/chitu

High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.

79
/ 100
Verified

Chitu is a production-grade large language model (LLM) inference engine designed to efficiently deploy AI models in real-world business scenarios. It takes trained LLM models and enterprise data as input, then processes them to provide rapid, stable AI-powered responses. This is ideal for AI product managers, machine learning engineers, and MLOps teams looking to bring generative AI applications into production.

3,418 stars. Actively maintained with 111 commits in the last 30 days. Available on PyPI.

Use this if you need to run large language models reliably and efficiently across various hardware, from a single GPU to large-scale clusters, for enterprise-level AI applications.

Not ideal if you are looking for a simple tool for basic LLM experimentation or development and do not require high-performance, scalable, or diverse hardware support.

AI-deployment large-language-models AI-infrastructure enterprise-AI MLOps
Maintenance 22 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 22 / 25

How are scores calculated?

Stars

3,418

Forks

477

Language

Python

License

Apache-2.0

Last pushed

Mar 13, 2026

Commits (30d)

111

Dependencies

21

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/thu-pacman/chitu"

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