Stars
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
You like pytorch? You like micrograd? You love tinygrad! ❤️
A community-maintained Python framework for creating mathematical animations.
Open source platform for the machine learning lifecycle
A Django content management system focused on flexibility and user experience
Python Implementation of Reinforcement Learning: An Introduction
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference,…
Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)
Open Source Platform for developing, scaling and deploying serious ML, AI, and data science systems
Numenta Platform for Intelligent Computing is an implementation of Hierarchical Temporal Memory (HTM), a theory of intelligence based strictly on the neuroscience of the neocortex.
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
SGLang is a fast serving framework for large language models and vision language models.
A concise but complete full-attention transformer with a set of promising experimental features from various papers
Find your trading edge, using the fastest engine for backtesting, algorithmic trading, and research.
Simple, elegant, Pythonic functional programming.
An unnecessarily tiny implementation of GPT-2 in NumPy.
Scalable and user friendly neural 🧠 forecasting algorithms.
ManimML is a project focused on providing animations and visualizations of common machine learning concepts with the Manim Community Library.
A fast serialization and validation library, with builtin support for JSON, MessagePack, YAML, and TOML
Probabilistic programming with NumPy powered by JAX for autograd and JIT compilation to GPU/TPU/CPU.
Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/
A statistical library designed to fill the void in Python's time series analysis capabilities, including the equivalent of R's auto.arima function.