Rust-native MoE inference runtime with custom CUDA kernels for Blackwell GPUs. Includes DFlash speculative decoding, multi-tier Engram memory, and entropy-adaptive routing. Targets Qwen3.5-35B-A3B on a single RTX 5060 Ti 16GB.
Hybrid Mamba-2 + Transformer 2.94B LLM (Nemotron-H style) — Korean 3B model pretrained from scratch on ×ばつ NVIDIA B200 GPUs with SFT + DPO alignment
Hybrid SSM-Attention language model on Apple Silicon with MLX — interleaving Mamba-2 and Transformer for efficient inference
VerDee: Vertical Deep Network on Mamba-2 — staged LoRA (shallow/mid/deep), early-exit routing, and domain experts. Pilot on 370M; 16GB GPU friendly. Research/experiment repo.
A 390M-parameter Mamba2 + Differential Attention hybrid language model
GLACIER: Mamba with infinite memory. This project integrates the Mamba SSM with ICE-Lite, a virtual memory engine, to solve context rot. By adding persistent, time-aware memory, GLACIER gives Mamba the long-term recall of a Transformer while retaining its $O(N)$ speed. Apache 2.0 licensed, by Dopove.
Runs a Rust inference server for hybrid State-Space and MoE language models with fast GPU throughput on consumer hardware
Helix-v2 1B bilingual hybrid LLM - Nvidia
Unofficial PyTorch reproduction for Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality.
Build Your Own Mamba — From Math to Metal
llama.cpp fork with additional SOTA quants and improved performance
A simple, minimalistic, and explainable JAX implementation of Mamba 2 & Mamba 3
Jagged Mamba2 SSD kernel for TPU written in Pallas
Add a description, image, and links to the mamba2 topic page so that developers can more easily learn about it.
To associate your repository with the mamba2 topic, visit your repo's landing page and select "manage topics."