CoderLSF/fast-llama

Runs LLaMA with Extremely HIGH speed

37
/ 100
Emerging

This project offers a powerful solution for developers looking to run large language models, specifically LLaMA2, on CPU hardware at extremely high speeds. It takes LLaMA2 models, including those from HuggingFace, and processes them to generate text outputs much faster than other existing engines. Developers building applications that need efficient, on-premise language model inference will find this tool valuable.

No commits in the last 6 months.

Use this if you are a developer deploying LLaMA2 models and need a C++ inference engine that prioritizes CPU performance and speed.

Not ideal if you are looking for a plug-and-play solution for non-developers or require extensive GPU support right now.

LLM deployment On-premise AI High-performance computing Natural Language Processing C++ development
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

95

Forks

10

Language

C++

License

MIT

Last pushed

Nov 21, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/CoderLSF/fast-llama"

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