Hiactor is a distributed C actor framework.

On-device Speech Recognition for Android

Optimized OpenAI's Whisper TFLite Port for Efficient Offline Inference on Edge Devices

High-efficiency floating-point neural network inference operators for mobile, server, and Web

General purpose Nix configuration for macOS / NixOS with starter templates step-by-step guides ✨

Official inference framework for 1-bit LLMs

Distribute and run LLMs with a single file.

Materials for the Learn PyTorch for Deep Learning: Zero to Mastery course.

ncnn is a high-performance neural network inference framework optimized for the mobile platform

simple msbuild based actions CI using hosted runners

The n-gram Language Model

llama.cpp fork with additional SOTA quants and improved performance

Burn is a new comprehensive dynamic Deep Learning Framework built using Rust with extreme flexibility, compute efficiency and portability as its primary goals.

On-device intelligence.

real time face swap and one-click video deepfake with only a single image

Extra notebooks for ECE-GY 6143

Comparison of Language Model Inference Engines

A 4-hour coding workshop to understand how LLMs are implemented and used

Dataframes powered by a multithreaded, vectorized query engine, written in Rust

Lightweight Error Augmentation Framework

Provides very lightweight outcome<T> and result<T> (non-Boost edition)

Backporting std::expected to C 17.

LLM inference in C/C

USB WiFi Adapter Information for Linux

NixOS/MacOS Nix Minimalist-Hardened-Privacy-oriented Configs

Curated list of project-based tutorials

Outline Server, developed by Jigsaw. The Outline Server is a proxy server that runs a Shadowsocks instance and provides a REST API for access key management.