Stars
Tongyi Deep Research, the Leading Open-source Deep Research Agent
DSPy: The framework for programming—not prompting—language models
The main chat app for the Public AI Inference Utility, based on OpenWebUI
Discrete Exterior Calculus on Polygonal Meshes
Rust bindings for the C++ api of PyTorch.
A python library for studying Calabi-Yau metrics
[ICLR 2025 Spotlight] Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures
A RWKV management and startup tool, full automation, only 8MB. And provides an interface compatible with the OpenAI API. RWKV is a large language model that is fully open source and available for c…
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…
INT4/INT5/INT8 and FP16 inference on CPU for RWKV language model
ndarray: an N-dimensional array with array views, multidimensional slicing, and efficient operations
Understanding the paper "Principles of Riemannian Geometry in Neural Networks" by Michael Hauser and Asok Ray
Minimal code example of the publication "On the accuracy, stability and computational efficiency of explicit last-stage diagonally implicit Runge-Kutta methods (ELDIRK) for the adaptive solution of…
Neuromorphic Intermediate Representation reference implementation
A deep learning library for spiking neural networks which is based on PyTorch, focuses on fast training and supports inference on neuromorphic hardware.
Implementation of 'Inverse-design of nonlinear mechanical metamaterials via video denoising diffusion models' (Nature Machine Intelligence)
Implementation of 'Physics-Informed Neural Networks for Shell Structures' (European Journal of Mechanics A)
Deep learning with spiking neural networks (SNNs) in PyTorch.
Deep and online learning with spiking neural networks in Python
Computations and statistics on manifolds with geometric structures.
Fast and Easy Infinite Neural Networks in Python
Physics-Informed Neural Networks (PINN) Solvers of (Partial) Differential Equations for Scientific Machine Learning (SciML) accelerated simulation