Scalable and Stable Parallelization of Nonlinear RNNS
☆33Jun 28, 2026Updated 2 months ago
Alternatives and similar repositories for elk
Users that are interested in elk are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Parallelizing non-linear sequential models over the sequence length☆56Jun 23, 2025Updated last year
- HGRN2: Gated Linear RNNs with State Expansion☆59Aug 20, 2024Updated 2 years ago
- ☆209Sep 11, 2026Updated last week
- Flax Implementation of DreamerV3 on Crafter☆19Nov 29, 2025Updated 9 months ago
- speed-running solving robot manipulation tasks☆24Oct 31, 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.
- ☆21Jan 4, 2023Updated 3 years ago
- ☆12May 16, 2024Updated 2 years ago
- Code for "Structured Linear CDEs: Maximally Expressive and Parallel-in-Time Sequence Models" (NeurIPS 2025, Spotlight)☆19Feb 17, 2026Updated 7 months ago
- A high-performance reinforcement learning library in jax specialized for robotic learning☆22Sep 4, 2023Updated 3 years ago
- Non official implementation of the Linear Recurrent Unit (LRU, Orvieto et al. 2023)☆64Sep 3, 2025Updated last year
- Reference implementation of "Softmax Attention with Constant Cost per Token" (Heinsen, 2024)☆25Jun 6, 2024Updated 2 years ago
- ☆325Jan 8, 2025Updated last year
- ☆15Aug 21, 2026Updated 3 weeks ago
- Attention Kernels for Symmetric Power Transformers☆131Sep 25, 2025Updated 11 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆33Oct 22, 2024Updated last year
- Code for "Learning Unitary Operators with Help From u(n)", AAAI-17. (https://arxiv.org/abs/1607.04903)☆17Jan 10, 2017Updated 9 years ago
- Comparison between GFlowNets & Maximum Entropy RL☆19Feb 19, 2024Updated 2 years ago
- ☆14Oct 11, 2022Updated 3 years ago
- GP Sinkhorn Implementation, paper: https://www.mdpi.com/1099-4300/23/9/1134☆23May 1, 2022Updated 4 years ago
- Implementation of Hyena Hierarchy in JAX☆10Apr 30, 2023Updated 3 years ago
- ☆15Mar 20, 2025Updated last year
- Hrrformer: A Neuro-symbolic Self-attention Model (ICML23)☆66Oct 8, 2025Updated 11 months ago
- Experiments on the impact of depth in transformers and SSMs.☆47Oct 23, 2025Updated 10 months ago
- 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 State-Space Model with Rational Transfer Function Representation.☆85May 17, 2024Updated 2 years ago
- [ICML 2024]: Official implementation for the paper: "Consistent Diffusion Meets Tweedie"☆52Apr 26, 2024Updated 2 years ago
- FlashRNN - Fast RNN Kernels with I/O Awareness☆188Updated this week
- nanoGPT using Equinox☆15Mar 3, 2023Updated 3 years ago
- DeltaProduct is a new linear recurrent neural network architecture that uses products of generalized Householder matrices as state-transi…☆17Oct 13, 2025Updated 11 months ago
- Sequence Modeling with Multiresolution Convolutional Memory (ICML 2023)☆127Oct 11, 2023Updated 2 years ago
- Subset-Norm and Subset-Momentum. This repo is built on top of https://github.com/jiaweizzhao/GaLore.☆19Jul 9, 2025Updated last year
- ☆36Apr 12, 2024Updated 2 years ago
- AGaLiTe: Approximate Gated Linear Transformers for Online Reinforcement Learning (Published in TMLR)☆24Oct 15, 2024Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- MonarchAttention: Zero-Shot Conversion to Fast, Hardware-Aware Structured Attention (NeurIPS'25 Spotlight)☆27Feb 22, 2026Updated 6 months ago
- nanoGPT-like codebase for LLM training☆119Nov 7, 2025Updated 10 months ago
- Code for lin-RFM used for sparse recovery tasks☆17Mar 13, 2025Updated last year
- ☆21Mar 7, 2024Updated 2 years ago
- NanoGPT speedrun in JAX. Originally at https://nor-git.pages.dev/modded-nanogpt-jax/☆17Aug 28, 2025Updated last year
- Accelerated First Order Parallel Associative Scan☆199Jan 7, 2026Updated 8 months ago
- Efficient PScan implementation in PyTorch☆17Jan 2, 2024Updated 2 years ago