implementations and experimentation on mHC by deepseek - https://arxiv.org/abs/2512.24880
☆381Feb 17, 2026Updated 8 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☆267Mar 9, 2026Updated 8 months ago
- Attempt to make multiple residual streams from Bytedance's Hyper-Connections paper accessible to the public☆189May 13, 2026Updated 6 months ago
- mHC-lite: You Don’t Need 20 Sinkhorn-Knopp Iterations☆96Jan 12, 2026Updated 10 months ago
- Spectral Sphere Optimizer☆136Mar 23, 2026Updated 7 months ago
- Official repository for Parallax (Parameterized Local Linear Attention)☆71Jul 30, 2026Updated 3 months 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.
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆265Jun 15, 2025Updated last year
- Muon is an optimizer for hidden layers in neural networks☆2,940May 24, 2026Updated 5 months ago
- Interactive visualization of Manifold-Constrained Hyper-Connections (mHC) for stable deep network training☆28Jul 4, 2026Updated 4 months ago
- ☆38Dec 25, 2025Updated 10 months ago
- Official repository Flash Local Linear Attention☆40May 28, 2026Updated 5 months ago
- ☆1,634Nov 17, 2025Updated 11 months ago
- Muon in Int8 Precision Made Possible☆21Nov 7, 2026Updated last week
- [ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Rule☆694Mar 13, 2026Updated 8 months ago
- Code to generate figures of paper "When do spectral gradient updates help in deep learning?"☆19Dec 3, 2025Updated 11 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Combining SOAP and MUON☆24Feb 11, 2025Updated last year
- Official Repo for Error-Free Linear Attention is a Free Lunch: Exact Solution from Continuous-Time Dynamics☆80Sep 25, 2026Updated last month
- Official PyTorch Implementation of Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention☆363Oct 11, 2026Updated last month
- Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models☆4,827Jan 14, 2026Updated 10 months ago
- ☆38Dec 31, 2025Updated 10 months ago
- Muon is Scalable for LLM Training☆1,560Aug 3, 2025Updated last year
- 🚀 Efficient implementations for emerging model architectures☆6,049Updated this week
- [Tech Report, NeurIPS 2026] Expanded Hyper-Connections☆78Nov 8, 2026Updated last week
- Physics of Language Models: Part 4.2, Canon Layers at Scale where Synthetic Pretraining Resonates in Reality☆364Aug 21, 2026Updated 2 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- 🔥 A minimal training framework for scaling FLA models☆427Apr 22, 2026Updated 6 months ago
- The Newton-Muon optimizer☆35Jun 5, 2026Updated 5 months ago
- Triton kernels and PyTorch ops for Block Attention Residuals (AttnRes)☆90May 29, 2026Updated 5 months ago
- ☆255Nov 19, 2025Updated 11 months ago
- Minimal and highly hackable implementation of Looped Transformers with GPT☆27Mar 8, 2026Updated 8 months ago
- Stick-breaking attention☆64Jul 1, 2025Updated last year
- Accelerating MoE with IO and Tile-aware Optimizations☆791Aug 29, 2026Updated 2 months ago
- ☆294Updated this week
- Open implementation of Attention Residuals (Kimi Team, arXiv:2603.15031)☆86Apr 30, 2026Updated 6 months 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.
- ☆3,576Mar 17, 2026Updated 7 months ago
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆1,029Feb 5, 2026Updated 9 months ago
- ☆125Feb 19, 2026Updated 8 months ago
- ☆289Jun 6, 2025Updated last year
- [ICLR 2025 & COLM 2025] Official PyTorch implementation of the Forgetting Transformer and Adaptive Computation Pruning☆155Feb 25, 2026Updated 8 months ago
- ☆16Aug 26, 2026Updated 2 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
Are these results useful?