mHC-lite: You Don’t Need 20 Sinkhorn-Knopp Iterations
☆94Jan 12, 2026Updated 7 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☆16Jul 13, 2026Updated last month
- Implementation of "RaanA: A Fast, Flexible, and Data-Efficient Post-Training Quantization Algorithm"☆18Apr 11, 2025Updated last year
- Benchmark tests supporting the TiledCUDA library.☆19Nov 19, 2024Updated last year
- implementations and experimentation on mHC by deepseek - https://arxiv.org/abs/2512.24880☆376Feb 17, 2026Updated 6 months ago
- DeltaProduct is a new linear recurrent neural network architecture that uses products of generalized Householder matrices as state-transi…☆17Oct 13, 2025Updated 10 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.
- Official repository for "SSA: Sparse Sparse Attention by Aligning Full and Sparse Attention Outputs in Feature Space"☆29May 7, 2026Updated 3 months ago
- Spectral Sphere Optimizer☆133Mar 23, 2026Updated 5 months ago
- mHC kernels implemented in CUDA☆266Mar 9, 2026Updated 5 months ago
- DeepSeek-V3.2-Exp DSA Warmup Lightning Indexer training operator based on tilelang☆52Nov 19, 2025Updated 9 months ago
- Flash-Linear-Attention models beyond language☆21Aug 28, 2025Updated last year
- [Tech Report] Expanded Hyper-Connections☆62Jul 21, 2026Updated last month
- FA4-based Relative Attention Kernel developed by TML and Colfax☆18Jul 17, 2026Updated last month
- Attempt to make multiple residual streams from Bytedance's Hyper-Connections paper accessible to the public☆189May 13, 2026Updated 3 months ago
- ☆32Jul 2, 2025Updated last year
- 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.
- ☆72Mar 24, 2026Updated 5 months ago
- An experimental communicating attention kernel based on DeepEP.☆34Jul 29, 2025Updated last year
- Compress and Attend Transformers (CATs) 😸☆23Aug 9, 2026Updated 3 weeks ago
- The Newton-Muon optimizer☆31Jun 5, 2026Updated 2 months ago
- The official code of "Mano: Restriking Manifold Optimization for LLM Training".☆25Jun 1, 2026Updated 3 months ago
- ☆37Dec 31, 2025Updated 8 months ago
- This repositories contains the reference implementation for the Sparse Delta Memory paper.More precisely, it contains the model definitio…☆38Jul 9, 2026Updated last month
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆135Jun 24, 2025Updated last year
- A Triton-only attention backend for vLLM☆28Jul 14, 2026Updated last month
- 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.
- NVIDIA cuTile learn☆168Dec 9, 2025Updated 8 months ago
- Muon in Int8 Precision Made Possible☆20Jun 18, 2026Updated 2 months ago
- Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence☆69Nov 11, 2025Updated 9 months ago
- ☆28Oct 2, 2025Updated 11 months ago
- Joint Selection for Large-Scale Pre-Training Data via Policy Gradient-based Mask Learning☆22Jan 4, 2026Updated 7 months ago
- Transformers components but in Triton☆34May 9, 2025Updated last year
- Agent-friendly GPU profile-query CLI☆119Aug 21, 2026Updated last week
- ☆125May 19, 2025Updated last year
- STABILIZING GRADIENTS FOR DEEP NEURAL NETWORKS VIA EFFICIENT SVD PARAMETERIZATION☆16Jun 5, 2018Updated 8 years ago
- 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.
- Learning TileLang with 10 puzzles!☆373Aug 11, 2026Updated 3 weeks ago
- Official repository for Parallax (Parameterized Local Linear Attention)☆68Jul 30, 2026Updated last month
- Overcoming Long-Context Limitations of State-Space Models via Context-Dependent Sparse Attention (NeurIPS 2025)☆23Sep 30, 2025Updated 11 months ago
- Triton kernels and PyTorch ops for Block Attention Residuals (AttnRes)☆88May 29, 2026Updated 3 months ago
- ☆39Dec 14, 2025Updated 8 months ago
- high-performance linear attention kernel library built on TileLang☆682Aug 26, 2026Updated last week
- ☆23Jun 12, 2025Updated last year