Official PyTorch Implementation of Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention
☆361Oct 11, 2026Updated last month
Alternatives and similar repositories for GatedDeltaNet-2
Users that are interested in GatedDeltaNet-2 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Rule☆693Mar 13, 2026Updated 7 months ago
- Official repository for Parallax (Parameterized Local Linear Attention)☆71Jul 30, 2026Updated 3 months ago
- Linear Attention Architectures: Mechanisms, Trade-offs, and Cross-Layer Routing (Technical Report)☆40Jul 10, 2026Updated 4 months ago
- 🚀 Efficient implementations for emerging model architectures☆6,040Updated this week
- Delta Attention Residuals - supplementary code and pretrained models☆45Sep 26, 2026Updated last month
- 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.
- high-performance linear attention kernel library built on TileLang☆753Oct 30, 2026Updated last week
- FlashKDA: high-performance Kimi Delta Attention kernels☆1,297Oct 26, 2026Updated 2 weeks ago
- ☆1,633Nov 17, 2025Updated 11 months ago
- ☆93Aug 19, 2026Updated 2 months ago
- Code for Fast-weight Product Key Memory (FwPKM)☆27Mar 18, 2026Updated 7 months ago
- Attention variant with per-channel multiplicative decay☆50Jun 3, 2026Updated 5 months ago
- The Newton-Muon optimizer☆35Jun 5, 2026Updated 5 months ago
- CUDA kernels for linear attention variants, written in CuTe DSL and CUTLASS C++.☆560Updated this week
- ☆289Jun 6, 2025Updated last year
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Official PyTorch implementation of Cyclic Flow Attention (CyFA)☆17Oct 17, 2026Updated 3 weeks ago
- Gecko Architecture☆19Jan 13, 2026Updated 9 months ago
- ☆34Aug 18, 2026Updated 2 months ago
- [ICLR 2025 & COLM 2025] Official PyTorch implementation of the Forgetting Transformer and Adaptive Computation Pruning☆155Feb 25, 2026Updated 8 months ago
- MoonEP: A Perfectly Balanced Expert Parallelism Library via Dynamic Redundant Experts☆1,210Oct 12, 2026Updated last month
- mKernel: fast multi-node, multi-GPU fused kernels☆309Oct 17, 2026Updated 3 weeks ago
- implementations and experimentation on mHC by deepseek - https://arxiv.org/abs/2512.24880☆381Feb 17, 2026Updated 8 months ago
- FLAT: Flash Linear Attention on TPUs☆24Oct 13, 2026Updated 3 weeks ago
- ☆437Oct 31, 2026Updated last 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.
- 🔥 A minimal training framework for scaling FLA models☆426Apr 22, 2026Updated 6 months ago
- ☆16Feb 5, 2026Updated 9 months ago
- Experiments Notebook of "Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism"☆18Apr 30, 2025Updated last year
- This repositories contains the reference implementation for the Sparse Delta Memory paper.More precisely, it contains the model definitio…☆43Oct 24, 2026Updated 2 weeks ago
- DeltaProduct is a new linear recurrent neural network architecture that uses products of generalized Householder matrices as state-transi…☆19Oct 13, 2025Updated last year
- An hardware-aware Efficient Implementation for "Mixture-of-Depths Attention".☆279May 6, 2026Updated 6 months ago
- Official code for HiLS-Attention☆153Aug 13, 2026Updated 2 months ago
- Official Codebase: LT2: Linear-Time Looped Transformers.☆69Jul 27, 2026Updated 3 months ago
- [Tech Report, NeurIPS 2026] Expanded Hyper-Connections☆77Updated this week
- 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.
- ☆291Updated this week
- [ACL 2026] Official repo for "Native Hybrid Attention for Efficient Sequence Modeling"☆36Sep 17, 2026Updated last month
- Quasar Attention Continuous-Time Memory Dynamics for Scaling Models Context to Millions of Tokens☆30Mar 26, 2026Updated 7 months ago
- ☆23Jul 10, 2026Updated 4 months ago
- Code for the paper ReplaySSM: Cache SSM Inputs, Not State☆74Oct 13, 2026Updated 3 weeks ago
- LM engine is a library for pretraining/finetuning LLMs☆197Sep 25, 2026Updated last month
- The official implementation for [NeurIPS2025 Oral] Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink…☆992Dec 20, 2025Updated 10 months ago
Are these results useful?