gotzmann/booster

Booster - open accelerator for LLM models. Better inference and debugging for AI hackers

36
/ 100
Emerging

This project helps AI developers and engineers deploy large language models (LLMs) like LLaMA and Mistral more efficiently. It takes your pre-trained LLM and configuration settings, then serves it up for faster text generation and inference, even on less powerful hardware. You would use this if you're building applications that rely on LLMs and need to optimize their performance and scalability in production.

167 stars. No commits in the last 6 months.

Use this if you need to run large language models reliably and with high performance, whether on powerful GPUs or more modest CPU-only machines, without the complexities of Python dependencies.

Not ideal if you are looking for a platform to train new LLMs from scratch or a no-code solution for integrating AI into your applications.

LLM deployment AI inference MLOps language model optimization production AI
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

167

Forks

11

Language

C++

License

Last pushed

Aug 15, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/gotzmann/booster"

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