Implementation of the sparse attention pattern proposed by the Deepseek team in their "Native Sparse Attention" paper
☆807Aug 15, 2025Updated 10 months ago
Alternatives and similar repositories for native-sparse-attention-pytorch
Users that are interested in native-sparse-attention-pytorch are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆1,006Feb 5, 2026Updated 4 months ago
- Implementation of the proposed DeepCrossAttention by Heddes et al at Google research, in Pytorch☆105Apr 3, 2026Updated 2 months ago
- Efficient triton implementation of Native Sparse Attention.☆279May 23, 2025Updated last year
- MoBA: Mixture of Block Attention for Long-Context LLMs☆2,128Apr 3, 2025Updated last year
- research impl of Native Sparse Attention (2502.11089)☆63Feb 19, 2025Updated last year
- 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.
- DeepSeek Native Sparse Attention pytorch implementation☆118Dec 17, 2025Updated 6 months ago
- 🚀 Efficient implementations for emerging model architectures☆5,227Jun 11, 2026Updated last week
- Explorations into adversarial losses on top of autoregressive loss for language modeling☆41Dec 21, 2025Updated 5 months ago
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆135Jun 24, 2025Updated 11 months ago
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆852Updated this week
- Muon is Scalable for LLM Training☆1,492Aug 3, 2025Updated 10 months ago
- Helpful tools and examples for working with flex-attention☆1,197May 28, 2026Updated 3 weeks ago
- Unofficial implementation of Titans, SOTA memory for transformers, in Pytorch☆1,961Jun 6, 2026Updated last week
- DeeperGEMM: crazy optimized version☆86May 5, 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.
- Design hardware-friendly model architectures and migrate existing LLMs with minimal performance loss☆484Jun 9, 2026Updated last week
- Implementation of 2-simplicial attention proposed by Clift et al. (2019) and the recent attempt to make practical in Fast and Simplex, Ro…☆49Sep 2, 2025Updated 9 months ago
- The Gaussian Histogram Loss (HL-Gauss) proposed by Imani et al. with a few convenient wrappers for regression, in Pytorch☆78Apr 3, 2026Updated 2 months ago
- Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch☆547May 16, 2025Updated last year
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆27Updated this week
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆281Jul 6, 2025Updated 11 months ago
- [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.☆1,003Feb 25, 2026Updated 3 months ago
- SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs☆67Mar 25, 2025Updated last year
- FlashMLA: Efficient Multi-head Latent Attention Kernels☆12,704Apr 30, 2026Updated last month
- 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.
- Efficient LLM Inference over Long Sequences☆395Jun 25, 2025Updated 11 months ago
- ☆52May 19, 2025Updated last year
- [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-t…☆3,425Jan 17, 2026Updated 5 months ago
- A bidirectional pipeline parallelism algorithm for computation-communication overlap in DeepSeek V3/R1 training.☆2,966Jan 14, 2026Updated 5 months ago
- Fast and memory-efficient exact attention☆24,170Updated this week
- ☆121May 19, 2025Updated last year
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆7,370Jun 4, 2026Updated 2 weeks ago
- ☆47Dec 13, 2025Updated 6 months ago
- Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models☆345Feb 23, 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.
- Quick implementation of nGPT, learning entirely on the hypersphere, from NvidiaAI☆298Jun 3, 2025Updated last year
- Exploring an idea where one forgets about efficiency and carries out attention across each edge of the nodes (tokens)☆56Mar 25, 2025Updated last year
- ☆66Apr 26, 2025Updated last year
- Distributed Compiler based on Triton for Parallel Systems☆1,459Apr 22, 2026Updated last month
- OctGPT: Octree-based Multiscale Autoregressive Models for 3D Shape Generation [SIGGRAPH 2025]☆204Sep 18, 2025Updated 9 months ago
- A PyTorch native platform for training generative AI models☆5,435Updated this week
- 🤖FFPA: Extends FlashAttention-2 via Split-D for large headdims, 1.5x~3×↑🎉 vs SDPA, up to 430T🎉 on H200.☆310Updated this week