🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

A game where players compete to draw differing prompts on a shared canvas, as scored by a computer vision model

A high-throughput and memory-efficient inference and serving engine for LLMs

A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM

Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM

Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation

A safetensors extension to efficiently store sparse quantized tensors on disk

A high-throughput and memory-efficient inference and serving engine for LLMs

Sparsity-aware deep learning inference runtime for CPUs

C++ with rizz

Neatly written data structures in Python! With Tests! Feel feel to use this as-is, or as a base for your own implementation

Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models

Automatically generate ctypes Python bindings from C sources and shared objects, using ctypeslib2 with libclang. Plus a CMake wrapper.

Virtual DOM for C++ Web Assembly projects using asm-dom and gccx, wrapped in CMake

Which Bollywood star are you?

Implementation related to the Deep Complex Networks

A quick monty-hall problem simulator

COVID-Net Open Source Initiative