Alternatives and similar repositories for Bi-Mamba2

Users that are interested in Bi-Mamba2 are comparing it to the libraries listed below

• goombalab / hydra
  Official implementation of "Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers"
  ☆166Updated 10 months ago
• AmeenAli / HiddenMambaAttn
  Official PyTorch Implementation of "The Hidden Attention of Mamba Models"
  ☆231Updated last month
• Adamdad / rational_kat_cu
  ☆76Updated 10 months ago
• pengzhangzhi / Awesome-Mamba
  Awesome list of papers that extend Mamba to various applications.
  ☆139Updated 5 months ago
• tommyip / mamba2-minimal
  Minimal Mamba-2 implementation in PyTorch
  ☆236Updated last year
• kyegomez / Griffin
  Implementation of Griffin from the paper: "Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models"
  ☆56Updated last month
• assafbk / DeciMamba
  DeciMamba: Exploring the Length Extrapolation Potential of Mamba (ICLR 2025)
  ☆31Updated 7 months ago
• MzeroMiko / mamba-mini
  An efficient pytorch implementation of selective scan in one file, works with both cpu and gpu, with corresponding mathematical derivatio…
  ☆98Updated last month
• Itamarzimm / UnifiedImplicitAttnRepr
  [ICLR 2025] Official Code Release for Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation
  ☆47Updated 9 months ago
• ethanbar11 / ssm_2d
  More dimensions = More fun
  ☆26Updated last year
• badripatro / mamba360
  State Space Models
  ☆71Updated last year
• kyegomez / MambaTransformer
  Integrating Mamba/SSMs with Transformer for Enhanced Long Context and High-Quality Sequence Modeling
  ☆211Updated last month
• AvivBick / awesome-ssm-ml
  Reading list for research topics in state-space models
  ☆335Updated 5 months ago
• goombalab / phi-mamba
  Official implementation of Phi-Mamba. A MOHAWK-distilled model (Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Mode…
  ☆116Updated last year
• WailordHe / DenseSSM
  A repository for DenseSSMs
  ☆89Updated last year
• zhixuan-lin / forgetting-transformer
  [ICLR 2025 & COLM 2025] Official PyTorch implementation of the Forgetting Transformer and Adaptive Computation Pruning
  ☆134Updated last month
• NVlabs / ConvSSM
  ☆69Updated last year
• OpenNLPLab / HGRN2
  HGRN2: Gated Linear RNNs with State Expansion
  ☆55Updated last year
• Weixin-Liang / Mixture-of-Mamba
  ☆50Updated 10 months ago
• qiuzh20 / gated_attention
  The official implementation for [NeurIPS2025 Oral] Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink…
  ☆273Updated 2 months ago
• apple / ml-sigmoid-attention
  ☆303Updated 7 months ago
• badripatro / simba
  Simba
  ☆214Updated last year
• BICLab / MetaLA
  Offical implementation of "MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map" (NeurIPS2024 Oral)
  ☆32Updated 10 months ago
• MambaMixer / M2
  ☆48Updated last year
• fkodom / yet-another-retnet
  A simple but robust PyTorch implementation of RetNet from "Retentive Network: A Successor to Transformer for Large Language Models" (http…
  ☆106Updated 2 years ago
• lucidrains / multimodal-dit-pytorch
  Implementation of a multimodal diffusion transformer in Pytorch
  ☆106Updated last year
• RobinWu218 / ToST
  [ICLR 2025 Spotlight] Official Implementation for ToST (Token Statistics Transformer)
  ☆127Updated 9 months ago
• test-time-training / ttt-lm-kernels
  Inference Speed Benchmark for Learning to (Learn at Test Time): RNNs with Expressive Hidden States
  ☆75Updated last year
• jacklishufan / Mamba-ND
  Ofiicial Implementation for Mamba-ND: Selective State Space Modeling for Multi-Dimensional Data
  ☆64Updated last year
• kyleliang919 / C-Optim
  When it comes to optimizers, it's always better to be safe than sorry
  ☆381Updated 2 months ago