MzeroMiko / mamba-mini
An efficient pytorch implementation of selective scan in one file, works with both cpu and gpu, with corresponding mathematical derivation. It is probably the code which is the most close to selective_scan_cuda in mamba.
☆85Updated last year
Alternatives and similar repositories for mamba-mini:
Users that are interested in mamba-mini are comparing it to the libraries listed below
- A Triton Kernel for incorporating Bi-Directionality in Mamba2☆65Updated 4 months ago
- This repository is the official implementation of our Autoregressive Pretraining with Mamba in Vision☆74Updated 10 months ago
- Open source implementation of "Vision Transformers Need Registers"☆175Updated 2 weeks ago
- Introduce Mamba2 to Vision.☆126Updated 8 months ago
- Code for paper LocalMamba: Visual State Space Model with Windowed Selective Scan☆244Updated 11 months ago
- Code Implementation of EfficientVMamba☆205Updated last year
- GroupMamba: Parameter-Efficient and Accurate Group Visual State Space Model [CVPR -2025]☆92Updated last month
- [ICLR 2025 Spotlight] Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures☆449Updated 2 months ago
- ☆65Updated last month
- [NeurIPS2024 Spotlight] The official implementation of MambaTree: Tree Topology is All You Need in State Space Model☆92Updated 10 months ago
- [BMVC 2024] PlainMamba: Improving Non-hierarchical Mamba in Visual Recognition☆76Updated 2 weeks ago
- Official PyTorch Implementation of "The Hidden Attention of Mamba Models"☆218Updated 10 months ago
- [CVPR'24] Multimodal Pathway: Improve Transformers with Irrelevant Data from Other Modalities☆99Updated last year
- Official repository of InLine attention (NeurIPS 2024)☆45Updated 4 months ago
- [ECCV 2024] Official PyTorch implementation of RoPE-ViT "Rotary Position Embedding for Vision Transformer"☆315Updated 4 months ago
- Official repository of MLLA (NeurIPS 2024)☆312Updated 5 months ago
- Awesome list of papers that extend Mamba to various applications.☆132Updated 3 weeks ago
- ☆86Updated 2 years ago
- A repository for DenseSSMs☆87Updated last year
- Ofiicial Implementation for Mamba-ND: Selective State Space Modeling for Multi-Dimensional Data☆59Updated 9 months ago
- The official repo for [TPAMI'23] "Vision Transformer with Quadrangle Attention"☆208Updated last year
- Causal depthwise conv1d in CUDA, with a PyTorch interface☆435Updated 4 months ago
- 1.5−3.0× lossless training or pre-training speedup. An off-the-shelf, easy-to-implement algorithm for the efficient training of foundatio…☆221Updated 8 months ago
- [ICLR2025] Spatial-Mamba: Effective Visual State Space Models via Structure-Aware State Fusion☆126Updated last month
- [NeurIPS 2024] The official code of "U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers"☆202Updated 6 months ago
- Official implementation of "Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers"☆128Updated 2 months ago
- [ICML 2024] Official PyTorch implementation of "SLAB: Efficient Transformers with Simplified Linear Attention and Progressive Re-paramete…☆104Updated 8 months ago
- ☆36Updated 9 months ago
- A PyTorch implementation of the paper "ZigMa: A DiT-Style Mamba-based Diffusion Model" (ECCV 2024)☆304Updated last month
- Minimal Mamba-2 implementation in PyTorch☆188Updated 10 months ago