☆139May 29, 2025Updated last year
Alternatives and similar repositories for grouped-latent-attention
Users that are interested in grouped-latent-attention are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆22May 5, 2025Updated last year
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆280Jul 6, 2025Updated 11 months ago
- ☆52May 19, 2025Updated last year
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆133Jun 24, 2025Updated last year
- The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling☆43Dec 29, 2025Updated 6 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.
- Quantized Attention on GPU☆44Nov 22, 2024Updated last year
- ☆250Nov 19, 2025Updated 7 months ago
- ☆16Sep 22, 2024Updated last year
- The evaluation framework for training-free sparse attention in LLMs☆123Jan 27, 2026Updated 5 months ago
- Odysseus: Playground of LLM Sequence Parallelism☆82Jun 17, 2024Updated 2 years ago
- study of cutlass☆22Nov 10, 2024Updated last year
- ☆283Jun 6, 2025Updated last year
- Distributed Compiler based on Triton for Parallel Systems☆1,466Updated this week
- ☆27Feb 26, 2026Updated 4 months ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- Helpful tools and examples for working with flex-attention☆1,203May 28, 2026Updated last month
- ☆54May 20, 2024Updated 2 years ago
- [ICCV 2025] Dynamic-VLM☆28Dec 16, 2024Updated last year
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆1,006Feb 5, 2026Updated 4 months ago
- User-friendly implementation of the Mixture-of-Sparse-Attention (MoSA). MoSA selects distinct tokens for each head with expert choice rou…☆29May 3, 2025Updated last year
- PyTorch bindings for CUTLASS grouped GEMM.☆190Apr 8, 2026Updated 2 months ago
- Benchmark tests supporting the TiledCUDA library.☆19Nov 19, 2024Updated last year
- ☆67Nov 27, 2023Updated 2 years ago
- Code for the paper "Function-Space Learning Rates"☆23Jun 3, 2025Updated last year
- 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.
- ☆40Dec 14, 2025Updated 6 months ago
- ☆607Sep 23, 2025Updated 9 months ago
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆257Jun 15, 2025Updated last year
- A lightweight design for computation-communication overlap.☆241Jan 20, 2026Updated 5 months ago
- ☆14Mar 2, 2025Updated last year
- [NeurIPS 2025 Spotlight] TPA: Tensor ProducT ATTenTion Transformer (https://arxiv.org/abs/2501.06425)☆458Jun 15, 2026Updated 2 weeks ago
- ☆321Jul 10, 2025Updated 11 months ago
- A Quirky Assortment of CuTe Kernels☆1,027Jun 20, 2026Updated last week
- ☆39Feb 26, 2024Updated 2 years ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Linear Attention Sequence Parallelism (LASP)☆87Jun 4, 2024Updated 2 years ago
- [ICML 2025] LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models☆18Nov 4, 2025Updated 7 months ago
- ☆37Aug 7, 2025Updated 10 months ago
- ☆138Feb 4, 2026Updated 4 months ago
- VideoNSA: Native Sparse Attention Scales Video Understanding☆87Nov 16, 2025Updated 7 months ago
- Experiments Notebook of "Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism"☆16Apr 30, 2025Updated last year
- An experimental communicating attention kernel based on DeepEP.☆34Jul 29, 2025Updated 11 months ago