mHC-lite: You Don’t Need 20 Sinkhorn-Knopp Iterations
☆96Jan 12, 2026Updated 9 months ago
Alternatives and similar repositories for mhc-lite
Users that are interested in mhc-lite are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICML 2026] Implementation for KromHC: Manifold-Constrained Hyper-Connections with Kronecker-Product Residual Matrices☆17Jul 13, 2026Updated 3 months ago
- ☆20Aug 9, 2026Updated 2 months ago
- Benchmark tests supporting the TiledCUDA library.☆19Nov 19, 2024Updated last year
- Implementation of "RaanA: A Fast, Flexible, and Data-Efficient Post-Training Quantization Algorithm"☆18Apr 11, 2025Updated last year
- implementations and experimentation on mHC by deepseek - https://arxiv.org/abs/2512.24880☆378Feb 17, 2026Updated 8 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.
- DeltaProduct is a new linear recurrent neural network architecture that uses products of generalized Householder matrices as state-transi…☆18Oct 13, 2025Updated last year
- mHC kernels implemented in CUDA☆267Mar 9, 2026Updated 7 months ago
- Official repository for "SSA: Sparse Sparse Attention by Aligning Full and Sparse Attention Outputs in Feature Space"☆32May 7, 2026Updated 5 months ago
- Spectral Sphere Optimizer☆135Mar 23, 2026Updated 7 months ago
- Efficient and unified implementations for TopK-based sparse attention☆41Jul 10, 2026Updated 3 months ago
- DeepSeek-V3.2-Exp DSA Warmup Lightning Indexer training operator based on tilelang☆52Nov 19, 2025Updated 11 months ago
- [Tech Report, NeurIPS 2026] Expanded Hyper-Connections☆77Oct 16, 2026Updated 2 weeks ago
- Code and results for "Revisiting RaBitQ and TurboQuant: a symmetric comparison of methods, theory, and experiments".☆13Aug 1, 2026Updated 3 months ago
- FA4-based Relative Attention Kernel developed by TML and Colfax☆18Sep 11, 2026Updated last month
- 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.
- Flash-Linear-Attention models beyond language☆21Aug 28, 2025Updated last year
- Distillation pipeline from pretrained Transformers to customized FLA models☆13Aug 4, 2025Updated last year
- Attempt to make multiple residual streams from Bytedance's Hyper-Connections paper accessible to the public☆189May 13, 2026Updated 5 months ago
- ☆11Aug 26, 2024Updated 2 years ago
- ☆32Jul 2, 2025Updated last year
- An experimental communicating attention kernel based on DeepEP.☆34Jul 29, 2025Updated last year
- ☆74Mar 24, 2026Updated 7 months ago
- The official code of "Mano: Restriking Manifold Optimization for LLM Training".☆26Jun 1, 2026Updated 5 months ago
- ☆38Dec 31, 2025Updated 10 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.
- The Newton-Muon optimizer☆35Jun 5, 2026Updated 4 months ago
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆135Jun 24, 2025Updated last year
- Compress and Attend Transformers (CATs) 😸☆24Aug 9, 2026Updated 2 months ago
- [ICML 2026] Spherical Steering: Geometry-Aware Activation Rotation for Language Models☆23May 19, 2026Updated 5 months ago
- Muon in Int8 Precision Made Possible☆20Jun 18, 2026Updated 4 months ago
- NVIDIA cuTile learn☆168Dec 9, 2025Updated 10 months ago
- ☆12May 8, 2026Updated 5 months ago
- ☆16Aug 26, 2026Updated 2 months ago
- A Triton-only attention backend for vLLM☆28Jul 14, 2026Updated 3 months ago
- 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.
- Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence☆72Nov 11, 2025Updated 11 months ago
- ☆29Oct 2, 2025Updated last year
- Stick-breaking attention☆64Jul 1, 2025Updated last year
- Joint Selection for Large-Scale Pre-Training Data via Policy Gradient-based Mask Learning☆22Jan 4, 2026Updated 9 months ago
- ☆125May 19, 2025Updated last year
- Overcoming Long-Context Limitations of State-Space Models via Context-Dependent Sparse Attention (NeurIPS 2025)☆23Sep 30, 2025Updated last year
- ☆40Dec 14, 2025Updated 10 months ago