Official repository of the xLSTM.
☆2,194May 28, 2026Updated 2 months ago
Alternatives and similar repositories for xlstm
Users that are interested in xlstm are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- xLSTM as Generic Vision Backbone☆490Oct 20, 2025Updated 9 months ago
- Efficient Python library for Extended LSTM with exponential gating, memory mixing, and matrix memory for superior sequence modeling.☆306Jun 28, 2024Updated 2 years ago
- Resources about xLSTM by Sepp Hochreiter☆319Nov 13, 2024Updated last year
- xLSTMTime for time series forecasting☆189Nov 25, 2024Updated last year
- Pytorch implementation of the xLSTM model by Beck et al. (2024)☆184Aug 12, 2024Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Cuda implementation of Extended Long Short Term Memory (xLSTM) with C++ and PyTorch ports☆92Jun 10, 2024Updated 2 years ago
- FlashRNN - Fast RNN Kernels with I/O Awareness☆188Jul 29, 2026Updated last week
- Implementation of xLSTM in Pytorch from the paper: "xLSTM: Extended Long Short-Term Memory"☆118Aug 3, 2026Updated last week
- ☆104Jun 12, 2025Updated last year
- Official JAX implementation of xLSTM including fast and efficient training and inference code. 7B model available at https://huggingface.…☆105Apr 8, 2026Updated 4 months ago
- TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning☆296Jul 18, 2026Updated 3 weeks ago
- Mamba SSM architecture☆18,723Jul 22, 2026Updated 2 weeks ago
- Tiled Flash Linear Attention library for fast and efficient mLSTM Kernels.☆93Jul 6, 2026Updated last month
- Time Series Forecasting with xLSTM☆50Aug 19, 2024Updated last year
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- A HuggingFace compatible Small Language Model trainer.☆77Feb 2, 2025Updated last year
- my attempts at implementing various bits of Sepp Hochreiter's new xLSTM architecture☆133May 8, 2024Updated 2 years ago
- Simple, minimal implementation of the Mamba SSM in one file of PyTorch.☆2,965Mar 8, 2024Updated 2 years ago
- Optimised Extended LSTM for time-series forecasting☆46May 2, 2026Updated 3 months ago
- Kolmogorov Arnold Networks☆16,332Jan 19, 2025Updated last year
- Official PyTorch implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States☆1,388Jul 14, 2024Updated 2 years ago
- Open weights language model from Google DeepMind, based on Griffin.☆684Feb 6, 2026Updated 6 months ago
- Schedule-Free Optimization in PyTorch☆2,323Jul 28, 2026Updated last week
- ☆60May 28, 2024Updated 2 years ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- [ICLR 2025] Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling☆971Nov 16, 2025Updated 8 months ago
- Implementation of the proposed minGRU in Pytorch☆325Dec 10, 2025Updated 8 months ago
- A simple and efficient Mamba implementation in pure PyTorch and MLX.☆1,473May 3, 2026Updated 3 months ago
- ☆16Oct 21, 2025Updated 9 months ago
- An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).☆4,654Aug 1, 2024Updated 2 years ago
- An implementation of mLSTM and sLSTM in PyTorch.☆28May 30, 2024Updated 2 years ago
- Replacing Mamba with xLSTM! It works better. We show that xLSTM-Unet can be an effective semantic segmentation backbone.☆202Jul 5, 2024Updated 2 years ago
- ☆23Nov 23, 2025Updated 8 months ago
- 🚀 Efficient implementations for emerging model architectures☆5,536Updated this week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable)…☆14,655Jul 23, 2026Updated 2 weeks ago
- [ICLR 2025 & COLM 2025] Official PyTorch implementation of the Forgetting Transformer and Adaptive Computation Pruning☆151Feb 25, 2026Updated 5 months ago
- Accelerated First Order Parallel Associative Scan☆198Jan 7, 2026Updated 7 months ago
- Structured state space sequence models☆2,916Jul 17, 2024Updated 2 years ago
- Hopfield Networks is All You Need☆1,961Apr 23, 2023Updated 3 years ago
- Annotated version of the Mamba paper☆502Feb 27, 2024Updated 2 years ago
- SDLG is an efficient method to accurately estimate aleatoric semantic uncertainty in LLMs☆28Jun 7, 2024Updated 2 years ago