Get up and running with Llama 3.3, Mistral, Gemma 2, and other large language models.

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Tensor library for machine learning

Generative AI extensions for onnxruntime

LLM inference in C/C++

SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime

Make it real

Official JAX implementation of MAGVIT: Masked Generative Video Transformer

C# Stable Diffusion using ONNX Runtime

Olive: Simplify ML Model Finetuning, Conversion, Quantization, and Optimization for CPUs, GPUs and NPUs.

Inference code for Llama models

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.

StableLM: Stability AI Language Models

Run macOS on QEMU/KVM. With OpenCore + Monterey + Ventura + Sonoma support now! Only commercial (paid) support is available now to avoid spammy issues. No Mac system is required.

C++ implementation of the Ethereum protocol

A C++ client for Ethereum's KZG Ceremony

Resources and documentation related to the ongoing Ethereum KZG Ceremony.

Specs for Ethereum's KZG Powers of Tau Ceremony

Ethereum end-to-end test harness

Point cloud diffusion for 3D model synthesis

A fast, secure, and portable multichain light client for Ethereum

Project Management: Meeting notes and agenda items

aztec connect repository

Go implementation of Ethereum proof of stake

Repository for the third EPF cohort

Decentralised Ethereum Liquid Staking Protocol.

The CLI package for Rocket Pool smart nodes.

A module to find available network ports for testing.