sustcsonglin / flash-linear-rnnLinks
Implementations of various linear RNN layers using pytorch and triton
☆52Updated 2 years ago
Alternatives and similar repositories for flash-linear-rnn
Users that are interested in flash-linear-rnn are comparing it to the libraries listed below
Sorting:
- Parallelizing non-linear sequential models over the sequence length☆54Updated 3 months ago
- Non official implementation of the Linear Recurrent Unit (LRU, Orvieto et al. 2023)☆57Updated last month
- Sequence Modeling with Structured State Spaces☆66Updated 3 years ago
- Sequence Modeling with Multiresolution Convolutional Memory (ICML 2023)☆127Updated last year
- Code for "Theoretical Foundations of Deep Selective State-Space Models" (NeurIPS 2024)☆15Updated 8 months ago
- [NeurIPS 2023 spotlight] Official implementation of HGRN in our NeurIPS 2023 paper - Hierarchically Gated Recurrent Neural Network for Se…☆66Updated last year
- Unofficial implementation of Linear Recurrent Units, by Deepmind, in Pytorch☆71Updated 5 months ago
- Pytorch implementation of Simplified Structured State-Spaces for Sequence Modeling (S5)☆79Updated last year
- Implementation of GateLoop Transformer in Pytorch and Jax☆91Updated last year
- The accompanying code for "Simplifying and Understanding State Space Models with Diagonal Linear RNNs" (Ankit Gupta, Harsh Mehta, Jonatha…☆23Updated 2 years ago
- ☆49Updated last year
- Accelerated First Order Parallel Associative Scan☆190Updated last year
- ☆164Updated 2 years ago
- A State-Space Model with Rational Transfer Function Representation.☆81Updated last year
- Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX☆89Updated last year
- ☆39Updated last year
- ☆44Updated 7 years ago
- ☆58Updated last year
- Implementation of Gated State Spaces, from the paper "Long Range Language Modeling via Gated State Spaces", in Pytorch☆101Updated 2 years ago
- ☆28Updated last year
- ☆185Updated last year
- ☆33Updated last year
- Explorations into the recently proposed Taylor Series Linear Attention☆100Updated last year
- ☆302Updated 8 months ago
- A PyTorch wrapper of parallel exclusive scan in CUDA☆12Updated 2 years ago
- ☆38Updated last year
- ☆23Updated last year
- Efficient PScan implementation in PyTorch☆16Updated last year
- ☆34Updated last year
- PyTorch implementation of Structured State Space for Sequence Modeling (S4), based on Annotated S4.☆87Updated last year