implementations and experimentation on mHC by deepseek - https://arxiv.org/abs/2512.24880
☆371Feb 17, 2026Updated 5 months ago
Alternatives and similar repositories for mHC-manifold-constrained-hyper-connections
Users that are interested in mHC-manifold-constrained-hyper-connections are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- mHC kernels implemented in CUDA☆265Mar 9, 2026Updated 4 months ago
- Attempt to make multiple residual streams from Bytedance's Hyper-Connections paper accessible to the public☆187May 13, 2026Updated 2 months ago
- mHC-lite: You Don’t Need 20 Sinkhorn-Knopp Iterations☆91Jan 12, 2026Updated 6 months ago
- Spectral Sphere Optimizer☆132Mar 23, 2026Updated 4 months ago
- Official repository for Parallax (Parameterized Local Linear Attention)☆68Jul 30, 2026Updated last week
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- Muon is an optimizer for hidden layers in neural networks☆2,762May 24, 2026Updated 2 months ago
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆259Jun 15, 2025Updated last year
- Code to generate figures of paper "When do spectral gradient updates help in deep learning?"☆16Dec 3, 2025Updated 8 months ago
- ☆38Dec 25, 2025Updated 7 months ago
- Official repository Flash Local Linear Attention☆38May 28, 2026Updated 2 months ago
- [ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Rule☆639Mar 13, 2026Updated 4 months ago
- Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models☆4,579Jan 14, 2026Updated 6 months ago
- ☆1,557Nov 17, 2025Updated 8 months ago
- Official PyTorch Implementation of Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention☆258May 25, 2026Updated 2 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.
- 🚀 Efficient implementations for emerging model architectures☆5,510Updated this week
- Physics of Language Models: Part 4.2, Canon Layers at Scale where Synthetic Pretraining Resonates in Reality☆357May 20, 2026Updated 2 months ago
- [ICLR 2025 & COLM 2025] Official PyTorch implementation of the Forgetting Transformer and Adaptive Computation Pruning☆151Feb 25, 2026Updated 5 months ago
- ☆68Mar 21, 2025Updated last year
- ☆252Nov 19, 2025Updated 8 months ago
- ☆253Updated this week
- Official Repo for Error-Free Linear Attention is a Free Lunch: Exact Solution from Continuous-Time Dynamics☆76Mar 26, 2026Updated 4 months ago
- Muon is Scalable for LLM Training☆1,524Aug 3, 2025Updated last year
- Official JAX implementation of End-to-End Test-Time Training for Long Context☆630Feb 15, 2026Updated 5 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.
- 🔥 A minimal training framework for scaling FLA models☆409Apr 22, 2026Updated 3 months ago
- ☆35Dec 31, 2025Updated 7 months ago
- Flash-Linear-Attention models beyond language☆21Aug 28, 2025Updated 11 months ago
- ☆285Jun 6, 2025Updated last year
- Combining SOAP and MUON☆25Feb 11, 2025Updated last year
- The Newton-Muon optimizer☆29Jun 5, 2026Updated 2 months ago
- Muon in Int8 Precision Made Possible☆20Jun 18, 2026Updated last month
- Code for the paper "Function-Space Learning Rates"☆23Jun 3, 2025Updated last year
- ☆136May 29, 2025Updated 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.
- My attempt to improve the speed of the newton schulz algorithm, starting from the dion implementation.☆41Apr 30, 2026Updated 3 months ago
- Minimal and highly hackable implementation of Looped Transformers with GPT☆25Mar 8, 2026Updated 4 months ago
- A single-line modification to any (dualizer-based) optimizer that allows the optimizer to adapt to the scale of the gradients as they cha…☆19Jan 11, 2025Updated last year
- ☆139Jun 6, 2025Updated last year
- ☆3,449Mar 17, 2026Updated 4 months ago
- Accelerating MoE with IO and Tile-aware Optimizations☆736Jul 4, 2026Updated last month
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆1,017Feb 5, 2026Updated 6 months ago