Differentiable controlled differential equation solvers for PyTorch with GPU support and memory-efficient adjoint backpropagation.
APACHE-2.0 License
Interpolating natural cubic splines. Includes batching, GPU support, support for missing values, ...
PyTorch tutorials and best practices.
C++ library based on tensorrt integration
Differentiable computations of the signature and logsignature transforms, on both CPU and GPU. (I...
Code for "Neural Controlled Differential Equations for Irregular Time Series" (Neurips 2020 Spotl...
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (par...
Differentiable SDE solvers with GPU support and efficient sensitivity analysis.
Code for "'Hey, that's not an ODE:' Faster ODE Adjoints via Seminorms" (ICML 2021)
Software Architecture for ML engineers