Stars
📊 Save matplotlib figures as TikZ/PGFplots for smooth integration into LaTeX.
Matplotlib styles for scientific plotting
Code for "Scaling Language-Free Visual Representation Learning" paper (Web-SSL).
A high-throughput and memory-efficient inference and serving engine for LLMs
An extremely fast Python package and project manager, written in Rust.
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
verl: Volcano Engine Reinforcement Learning for LLMs
Library for reading and processing ML training data.
[ICLR 2025 Spotlight] Official Implementation for ToST (Token Statistics Transformer)
Official repository for our work on micro-budget training of large-scale diffusion models.
⏩ Create, share, and use custom AI code assistants with our open-source IDE extensions and hub of models, rules, prompts, docs, and other building blocks
Entropy Based Sampling and Parallel CoT Decoding
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/
Nonlinear optimisation (root-finding, least squares, ...) in JAX+Equinox. https://docs.kidger.site/optimistix/
A JAX research toolkit for building, editing, and visualizing neural networks.
Simple and readable code for training and sampling from diffusion models
Accelerate, Optimize performance with streamlined training and serving options with JAX.
Resources for education in statistics and machine learning: from advanced undergraduate to research level
Official PyTorch Implementation of "SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers"
Type annotations and runtime checking for shape and dtype of JAX/NumPy/PyTorch/etc. arrays. https://docs.kidger.site/jaxtyping/
Interactively inspect module inputs, outputs, parameters, and gradients.
very good whiteboard SDK / infinite canvas SDK