Libraries

A symbolic framework for numeric optimization that implements forward- and reverse-mode automatic differentiation on sparse matrix-valued computational graphs, usable from C++, Python, MATLAB/Octave, Julia or JavaScript.

• Libraries

A collection of TypeScript libraries for working with the Hugging Face API and Hub: managing repositories, calling more than 100,000 hosted inference models, an MCP client, parsers for the GGUF, DDUF and LeRobot formats, and a small library for building tool-using AI agents.

• Inference
• Libraries

A Rust interface for hardware-accelerated inference and training on ONNX-format machine learning models, built mainly as a wrapper around Microsoft's ONNX Runtime with support for other pure-Rust runtimes.

• Inference
• Libraries

A Fody add-in for .NET that embeds a project's dependency assemblies as resources so an application or library ships as a single file.

• Libraries

A universal wireless-communication library for embedded devices that supports many radio modules and digital modes such as LoRa, RTTY, AX.25, and SSTV through one consistent interface.

• Libraries

A cross-platform engine that renders video as real-time ASCII or colored-block text, streamed to a browser canvas over a low-overhead binary protocol at 30 frames per second.

• Libraries

A PyTorch-native library for quantizing and optimizing models across the training-to-serving lifecycle, covering low-bit formats, sparsity, and hardware-aware kernels.

• Inference
• Libraries

A Go library for generating x86 assembly, letting Go control structures describe assembly programs that avo compiles into an assembly file and a Go stub.

• Libraries

A C++ template library that provides STL-like fixed-size containers and utilities for embedded systems, with no dynamic memory allocation.

• Libraries

A lightweight, fast Python library for generating text, sparse and image embeddings using the ONNX runtime instead of PyTorch, with no GPU required.

• RAG
• Libraries

An easy-to-use, embeddable C and C++ web server with optional CGI, SSL, and Lua support, usable as a library or as a standalone executable.

• Libraries
• Backend

A cross-platform Python framework for real-time voice AI, vision-language tasks and IoT device control, evolved from the xiaozhi-esp32 firmware project.

• Speech
• Libraries

A Hugging Face library that optimizes and accelerates Transformers, Diffusers, TIMM and Sentence Transformers models for training and inference on specific hardware.

• Inference
• Libraries

A Python library that integrates large language models such as ChatGPT into scikit-learn for text analysis tasks like zero-shot classification.

• Libraries

A small, SMP-aware embedded operating system kernel ported to many CPU architectures, used as the bootloader in numerous Android phones.

• Libraries

A C++ and Python library implementing fast rigid body dynamics algorithms and their analytical derivatives, used in robotics, biomechanics, and physics simulation.

• Libraries

A Python computer vision framework for self-supervised learning, offering modular loss functions and model heads with PyTorch and PyTorch Lightning-based examples for many published methods.

• Libraries

A JAX and Flax codebase for research on attention-based computer vision models, providing shared libraries for training large-scale, multi-device vision models plus complete example projects.

• Libraries

A library for quantizing and compressing large language models for deployment with vLLM, covering weight, activation, KV-cache and attention quantization with Hugging Face integration.

• Inference
• Libraries

A library for mechanistic interpretability of GPT-style language models that exposes a model's internal activations so they can be cached, edited, removed or replaced while the model runs.

• Libraries

A PyTorch library of vector and scalar quantization techniques, transcribed from DeepMind's TensorFlow implementation, used for models such as VQ-VAE-2 and Jukebox.

• Libraries

A real-time operating system for embedded systems, scaling from 8-bit to 64-bit microcontrollers with POSIX and ANSI standards compliance.

• Libraries

A fast tokenizer for language models, written in Rust, that aims to match HuggingFace Tokenizers output while running at multi-gigabyte-per-second throughput.

• Libraries

A fast Python library for serializing and validating data as JSON, MessagePack, YAML, and TOML using standard type annotations.

• Libraries