assafbk / DeciMambaLinks
DeciMamba: Exploring the Length Extrapolation Potential of Mamba (ICLR 2025)
☆31Updated 6 months ago
Alternatives and similar repositories for DeciMamba
Users that are interested in DeciMamba are comparing it to the libraries listed below
Sorting:
- [ICLR 2025 & COLM 2025] Official PyTorch implementation of the Forgetting Transformer and Adaptive Computation Pruning☆131Updated last month
- The this is the official implementation of "DAPE: Data-Adaptive Positional Encoding for Length Extrapolation"☆39Updated last year
- HGRN2: Gated Linear RNNs with State Expansion☆55Updated last year
- ☆34Updated 7 months ago
- [NeurIPS 2023 spotlight] Official implementation of HGRN in our NeurIPS 2023 paper - Hierarchically Gated Recurrent Neural Network for Se…☆65Updated last year
- Official implementation of Phi-Mamba. A MOHAWK-distilled model (Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Mode…☆116Updated last year
- Stick-breaking attention☆61Updated 3 months ago
- ☆86Updated last year
- The official implementation for [NeurIPS2025 Oral] Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink…☆95Updated last month
- A repository for DenseSSMs☆89Updated last year
- ☆104Updated last month
- Some preliminary explorations of Mamba's context scaling.☆216Updated last year
- ☆61Updated 3 months ago
- ☆33Updated last year
- Remasking Discrete Diffusion Models with Inference-Time Scaling☆49Updated 7 months ago
- Here we will test various linear attention designs.☆61Updated last year
- [ICML 2024] When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models☆36Updated last year
- [ICML 2025] Fourier Position Embedding: Enhancing Attention’s Periodic Extension for Length Generalization☆100Updated 4 months ago
- [NeurIPS 2024] Official Repository of The Mamba in the Llama: Distilling and Accelerating Hybrid Models☆231Updated last week
- ☆56Updated last year
- ☆105Updated last year
- ☆25Updated 2 months ago
- Flash-Linear-Attention models beyond language☆19Updated last month
- [ICLR2025] Codebase for "ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing", built on Megatron-LM.☆97Updated 10 months ago
- Inference Speed Benchmark for Learning to (Learn at Test Time): RNNs with Expressive Hidden States☆73Updated last year
- [NeurIPS '25] Multi-Token Prediction Needs Registers☆22Updated last month
- The official github repo for "Diffusion Language Models are Super Data Learners".☆135Updated 3 weeks ago
- Implementation of Griffin from the paper: "Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models"☆56Updated this week
- User-friendly implementation of the Mixture-of-Sparse-Attention (MoSA). MoSA selects distinct tokens for each head with expert choice rou…☆27Updated 5 months ago
- M1: Towards Scalable Test-Time Compute with Mamba Reasoning Models☆44Updated 3 months ago