Implementation of the sparse attention pattern proposed by the Deepseek team in their "Native Sparse Attention" paper
☆800Aug 15, 2025Updated 8 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"☆984Feb 5, 2026Updated 2 months ago
- Implementation of the proposed DeepCrossAttention by Heddes et al at Google research, in Pytorch☆102Apr 3, 2026Updated 2 weeks ago
- MoBA: Mixture of Block Attention for Long-Context LLMs☆2,093Apr 3, 2025Updated last year
- Efficient triton implementation of Native Sparse Attention.☆275May 23, 2025Updated 10 months ago
- research impl of Native Sparse Attention (2502.11089)☆63Feb 19, 2025Updated last year
- Wordpress hosting with auto-scaling - Free Trial • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- DeepSeek Native Sparse Attention pytorch implementation☆116Dec 17, 2025Updated 4 months ago
- 🚀 Efficient implementations for emerging model architectures☆4,878Updated this week
- Explorations into adversarial losses on top of autoregressive loss for language modeling☆41Dec 21, 2025Updated 3 months ago
- Muon is Scalable for LLM Training☆1,458Aug 3, 2025Updated 8 months ago
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆781Apr 8, 2026Updated last week
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆133Jun 24, 2025Updated 9 months ago
- Helpful tools and examples for working with flex-attention☆1,174Updated this week
- Unofficial implementation of Titans, SOTA memory for transformers, in Pytorch☆1,948Feb 9, 2026Updated 2 months ago
- DeeperGEMM: crazy optimized version☆86May 5, 2025Updated 11 months ago
- 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.
- Design hardware-friendly model architectures and migrate existing LLMs with minimal performance loss☆457Apr 6, 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…☆47Sep 2, 2025Updated 7 months ago
- The Gaussian Histogram Loss (HL-Gauss) proposed by Imani et al. with a few convenient wrappers for regression, in Pytorch☆80Apr 3, 2026Updated 2 weeks ago
- Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch☆548May 16, 2025Updated 11 months ago
- SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs☆64Mar 25, 2025Updated last year
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆22Apr 9, 2026Updated last week
- [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.☆976Feb 25, 2026Updated last month
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆277Jul 6, 2025Updated 9 months ago
- Efficient LLM Inference over Long Sequences☆393Jun 25, 2025Updated 9 months ago
- Serverless GPU API endpoints on Runpod - Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- FlashMLA: Efficient Multi-head Latent Attention Kernels☆12,558Apr 7, 2026Updated last week
- ☆51May 19, 2025Updated 11 months ago
- [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-t…☆3,296Jan 17, 2026Updated 3 months ago
- A bidirectional pipeline parallelism algorithm for computation-communication overlap in DeepSeek V3/R1 training.☆2,943Jan 14, 2026Updated 3 months ago
- ☆119May 19, 2025Updated 11 months ago
- ☆48Dec 13, 2025Updated 4 months ago
- Fast and memory-efficient exact attention☆23,344Updated this week
- Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models☆343Feb 23, 2025Updated last year
- Quick implementation of nGPT, learning entirely on the hypersphere, from NvidiaAI☆293Jun 3, 2025Updated 10 months ago
- 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.
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆6,376Updated this week
- 🤖FFPA: Extend FlashAttention-2 with Split-D, ~O(1) SRAM complexity for large headdim, 1.8x~3x↑🎉 vs SDPA EA.☆260Feb 13, 2026Updated 2 months ago
- Exploring an idea where one forgets about efficiency and carries out attention across each edge of the nodes (tokens)☆55Mar 25, 2025Updated last year
- Distributed Compiler based on Triton for Parallel Systems☆1,403Apr 10, 2026Updated last week
- ☆67Apr 26, 2025Updated 11 months ago
- OctGPT: Octree-based Multiscale Autoregressive Models for 3D Shape Generation [SIGGRAPH 2025]☆201Sep 18, 2025Updated 7 months ago
- A PyTorch native platform for training generative AI models☆5,242Updated this week