State Space Models Python Packages

mojolearn

GPU machine learning in Mojo that supports bitwise identical inference and training on Apple Metal, NVIDIA CUDA and AMD HIP.

dynamax

A Python package for probabilistic state space modeling with JAX

mojolearn-nvidia

GPU machine learning in Mojo that supports bitwise identical inference and training on Apple Metal, NVIDIA CUDA and AMD HIP.

mojolearn-amd

GPU machine learning in Mojo that supports bitwise identical inference and training on Apple Metal, NVIDIA CUDA and AMD HIP.

smcx

Sequential inference for state-space models in JAX: Kalman-family filters and smoothers, and SMC methods including particle filters, tempered SMC, and SMC².

torchmamba

Clean PyTorch reference kernels for Mamba-1/2/3 (S6, SSD, SISO, MIMO) — parity with paper math

deeptab

DeepTab is a Python package that simplifies tabular deep learning by providing a suite of models for regression, classification, and distributional regression tasks. It includes models such as Mambular, TabM, FT-Transformer, TabulaRNN, TabTransformer, and tabular ResNets.

mambular

DeepTab is a Python package that simplifies tabular deep learning by providing a suite of models for regression, classification, and distributional regression tasks. It includes models such as Mambular, TabM, FT-Transformer, TabulaRNN, TabTransformer, and tabular ResNets.

baysil

Bayesian Sequential Inference Library for State-Space Models

rts-smoother

High-performance Rauch–Tung–Striebel Kalman smoother for the local level model

bayesnewton

Bayes-Newton—A Gaussian process library in JAX, with a unifying view of approximate Bayesian inference as variants of Newton's method.

linoss-dynamics

NumPy runtime helpers for LinOSS-style oscillator dynamics — sequence stepping, closed-form damped oscillator, Bayesian filtering, MLE fit. See Roadmap issue for vision.

discretax

Discretax is a light weight collection of state space models implemented in JAX ⚡️

identifiability-diagnostic

An O(T) pre-training geometric diagnostic system that detects latent regime unidentifiability via singular value subspace collapse in Switching State-Space Models (S-SSMs) before model training begins.

smcjax

Sequential inference for state-space models in JAX: Kalman-family filters and smoothers, and SMC methods including particle filters, tempered SMC, and SMC².

metamer

Stochastic noise-model fitting and selection for time series, for correctly calibrated trend uncertainties at up to 10^7 series.

mlx-recurrence

Fused Metal training kernels for linear recurrence on Apple Silicon — SSD (Mamba-2), GLA, RG-LRU, rotational LRU. Flash-linear-attention for MLX: 12-18x less training memory, production-validated.

parallelwatch

🧠 Real-time multivariate temporal correlation and anomaly detection primitive. Leverages structured state-space sequence modeling (SSMs) to map system failures across massive telemetry streams without O(M^2) cross-attention overhead.

linax

Discretax is a light weight collection of state space models implemented in JAX ⚡️

lrnnx

A unified PyTorch library for Linear RNNs