LLM.swift is a simple and readable library that allows you to interact with large language models locally with ease for macOS, iOS, watchOS, tvOS, and visionOS.

CUDA/Metal accelerated language model inference

DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including CUDA, x86 and ARMv9.

REST: Retrieval-Based Speculative Decoding, NAACL 2024

电子鹦鹉 / Toy Language Model

V-lang api wrapper for llm-inference chatllm.cpp

Nim api-wrapper for llm-inference chatllm.cpp

kotlin api wrapper for llm-inference chatllm.cpp

Implementing LLM from scratch. (Developing...)

Python bindings for the Transformer models implemented in C/C++ using GGML library.

<img align="left" width="100" height="100" src="logo.png" alt="logo" style="float: left;"/><h3 align="left">Aquila. <br>iOS 6 untethered jailbreak for all devices<div align="right" style="float: top;"></br></h3> Aquila offers a straightforward solution for jailbreaking iOS 6 on various devices. Check out the installation guide at [ios.cfw.guid