Simple, fast primitives for building pdf viewers. maintained by @anaralabs

The codebase for the book "AI-Powered Search" (Manning Publications, 2025)

Build custom inference engines for models, agents, multi-modal systems, RAG, pipelines and more.

Optimus is a flexible and scalable framework built to train language models efficiently across diverse hardware configurations, including CPU, AMD, and NVIDIA GPUs.

Argilla is a collaboration tool for AI engineers and domain experts to build high-quality datasets

Puzzles for learning Triton

A markup-based typesetting system that is powerful and easy to learn.

A framework for Reinforcement Learning research.

A simple, performant and scalable Jax LLM!

Machine Learning Engineering Open Book

High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC, LB-SAC, SPOT, Cal-QL, ReBRAC

Inference code for Llama models

Open Lakehouse Format for Multimodal AI. Convert from Parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, DuckDB, Polars, Pyarrow, a…

There can be more than Notion and Miro. AFFiNE(pronounced [ə‘fain]) is a next-gen knowledge base that brings planning, sorting and creating all together. Privacy first, open-source, customizable an…

Official PyTorch implementation of Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion (CVPR 2020)

This repository aims at providing efficient CNNs for Audio Tagging. We provide AudioSet pre-trained models ready for downstream training and extraction of audio embeddings.

Reinforcement Learning environments for Traffic Signal Control with SUMO. Compatible with Gymnasium, PettingZoo, and popular RL libraries.

C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.

Scaled-YOLOv4: Scaling Cross Stage Partial Network

Fast and procedurally generated side-scroller-game-like graphical environments (formerly Procgen)

JAX - A curated list of resources https://github.com/google/jax

An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

An educational resource to help anyone learn deep reinforcement learning.

Type annotations and runtime checking for shape and dtype of JAX/NumPy/PyTorch/etc. arrays. https://docs.kidger.site/jaxtyping/

Multi-Joint dynamics with Contact. A general purpose physics simulator.

JAX-based neural network library

An elegant PyTorch deep reinforcement learning library.

😎 Curated list of awesome things around WebGPU ecosystem.