High-Speed Inference with llama.cpp and Vicuna on CPU

Author(s): Benjamin Marie

Originally published on Towards AI.

You don’t need a GPU for fast inference

A vicuna — Photo by Parsing Eye on Unsplash

For inference with large language models, we may think that we need a very big GPU or that it can’t run on consumer hardware. This is rarely the case.

Nowadays, we have many tricks and frameworks at our disposal, such as device mapping or QLoRa, that make inference possible at home, even for very large language models.

And now, thanks to Georgi Gerganov, we don’t even need a GPU. Georgi Gerganov is well-known for his work on implementing in plain C++ high-performance inference.

He has implemented, with the help of many contributors, the inference for… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI