The “Quite OK Image Format” for fast, lossless image compression

Wrangling Untrusted File Formats Safely

[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

🚀 Fast and simple Node.js version manager, built in Rust

A Rust library for the Discord API.

Fast Multimodal LLM on Mobile Devices

Staging repo for development of native port of TypeScript

Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, DeepSeek, Mixtral, Gemma, Phi, MiniCPM, Qwen-VL, MiniCPM-V, etc.) on Intel XPU (e.g., local PC with iGPU and NPU, discr…

An implementation of Shazam's song recognition algorithm.

Truly independent web browser

Build your own 'AirTags' 🏷 today! Framework for tracking personal Bluetooth devices via Apple's massive Find My network.

Natural Number Game

DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

Forward RSS feeds to your email address, community maintained

A collection of guides and examples for the Gemma open models from Google.

The fast.ai course notebooks

Transcription, forced alignment, and audio indexing with OpenAI's Whisper

Port of OpenAI's Whisper model in C/C++

Creusot helps you prove your code is correct in an automated fashion.

Yet Another Random Program Generator

A better and stronger spiritual successor to BZip2.

CUDA on non-NVIDIA GPUs

Virtual Machine for the Web

MiniCPM-o 2.6: A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming on Your Phone

Development repository for the Triton language and compiler

Automatic verification of LLVM optimizations

C++ wrapper around libcURL