Mamba Python Packages

mojolearn

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

mojolearn-nvidia

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

py-rattler-build

rattler-build is a universal Conda package builder for Windows, macOS and Linux (like conda-build but faster)

mojolearn-amd

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

synapse-sr

SYNAPSE-SR: Sentinel-2 super-resolution from 10 m to 2 m resolution. Physics-consistent deep learning with per-pixel trust maps and calibrated uncertainty. Flash (any CPU) and Pro (Mamba). pip install synapse-sr

nepenthe

Forget your environment sorrows

torchmamba

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

mambavision

[CVPR 2025] Official PyTorch Implementation of MambaVision: A Hybrid Mamba-Transformer Vision Backbone

spectomate

spectomate to narzędzie do konwersji projektów z pakietów pip do różnych środowisk opartych na conda (conda, miniconda, mamba, micromamba).

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.

mamba-safe

Generating Molecules with the Mamba architecture

trifusion-fp-kernel

TriFusion-FP inference kernels and CUDA Graph runtime for NVIDIA L4 (Triton/PTX, BF16, Python API)

gleamlm

GleamLM大语言模型全栈训练平台——核心代码用 PyTorch 从零实现，最低仅需 12GB 消费级显卡即可完整训练，另有一套工业代码与手写实现消费同一份数据逐层对照。模型训练支持CLI和可视化训练。

pydeps2env

Creates a conda environment.yml file from python package dependencies (e.g. from pyproject.toml or setup.cfg files).

vision-mamba

Implementation of Vision Mamba from the paper: "Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model" It's 2.8x faster than DeiT and saves 86.8% GPU memory when performing batch inference to extract features on high-res images

mmm-zeta

A novel implementation of fusing ViT with Mamba into a fast, agile, and high performance Multi-Modal Model. Powered by Zeta, the simplest AI framework ever.

tracedistill

Distill teacher chains-of-thought into a LoRA adapter via a strict boxed-answer format contract + two-phase Train→Nudge (silver-medal NVIDIA Nemotron reasoning recipe, as a tested library).

gpkg

GPU package manager — find prebuilt CUDA wheels, build missing ones

lmxlab

Transformer language models on Apple Silicon with MLX

mamba-former

Implementation of MambaFormer in Pytorch ++ Zeta from the paper: "Can Mamba Learn How to Learn? A Comparative Study on In-Context Learning Tasks"

xontrib-pm

Persistent aliases for package managers.

statecraft

Statecraft - Load, store and remix states for SSMs, Mamba and Stateful models

mambabyte

Implementation of MambaByte in "MambaByte: Token-free Selective State Space Model" in Pytorch and Zeta