A method designed to enhance the efficiency of Transformer models

Building applications with LLMs through composability

Lightweight alternative to LangChain for composing LLMs

WebAssembly binding for llama.cpp - Enabling in-browser LLM inference

SGLang is a fast serving framework for large language models and vision language models.

a chat interface crafted with llama.cpp for running Alpaca models. No API keys, entirely self-hosted!