GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.

Official inference framework for 1-bit LLMs

A modern replacement for Redis and Memcached

Open Source alternative to Algolia + Pinecone and an Easier-to-Use alternative to ElasticSearch ⚡ 🔍 ✨ Fast, typo tolerant, in-memory fuzzy Search Engine for building delightful search experiences

Filament is a real-time physically based rendering engine for Android, iOS, Windows, Linux, macOS, and WebGL2

A virtual machine for executing programs written in Hack.

Tensor library for machine learning

Amnezia VPN Client (Desktop+Mobile)

A fast, local neural text to speech system

CUDA Templates and Python DSLs for High-Performance Linear Algebra

Transformer related optimization, including BERT, GPT

Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https://discord.gg/5xXzkMu8Zk

A Tunnel which Improves your Network Quality on a High-latency Lossy Link by using Forward Error Correction, possible for All Traffics(TCP/UDP/ICMP)

fastllm是后端无依赖的高性能大模型推理库。同时支持张量并行推理稠密模型和混合模式推理MOE模型，任意10G以上显卡即可推理满血DeepSeek。双路9004/9005服务器+单显卡部署DeepSeek满血满精度原版模型，单并发20tps；INT4量化模型单并发30tps，多并发可达60+。

A machine learning compiler for GPUs, CPUs, and ML accelerators

HIP: C++ Heterogeneous-Compute Interface for Portability

Multi-GPU CUDA stress test

Apache Traffic Server™ is a fast, scalable and extensible HTTP/1.1 and HTTP/2 compliant caching proxy server.

The macOS kext for GPU bug fixes, QoL improvements, and extended hardware support.

INT4/INT5/INT8 and FP16 inference on CPU for RWKV language model

A local inference engine for Apple silicon, built around the model.

Build your own high performance LLM inference engine in C++ and CUDA - a smaller version of vLLM

A port of DOOM for a quantum computer

Fast Multi-dimensional Sparse Attention

Perplexity GPU Kernels

An open source advanced driver assistance system (ADAS) that uses Jetson Nano as the hardware. Features: Traffic sign detection, Forward collision warning, Lane departure warning.

Fast Matrix Multiplications for Lookup Table-Quantized LLMs

A small OpenCL benchmark program to measure peak GPU/CPU performance.

Source code for the TKET quantum compiler, Python bindings and utilities