🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"
☆1,019Feb 5, 2026Updated 6 months ago
Alternatives and similar repositories for native-sparse-attention
Users that are interested in native-sparse-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:
- Implementation of the sparse attention pattern proposed by the Deepseek team in their "Native Sparse Attention" paper☆811Aug 15, 2025Updated last year
- Efficient triton implementation of Native Sparse Attention.☆282May 23, 2025Updated last year
- 🚀 Efficient implementations for emerging model architectures☆5,671Updated this week
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆134Jun 24, 2025Updated last year
- MoBA: Mixture of Block Attention for Long-Context LLMs☆2,174Apr 3, 2025Updated last year
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Accelerating MoE with IO and Tile-aware Optimizations☆752Updated this week
- ☆253Nov 19, 2025Updated 9 months ago
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆929Updated this week
- qwen-nsa☆87Oct 14, 2025Updated 10 months ago
- 🔥 A minimal training framework for scaling FLA models☆413Apr 22, 2026Updated 4 months ago
- A sparse attention kernel supporting mix sparse patterns☆549Jan 18, 2026Updated 7 months ago
- Distributed Compiler and Optimized Parallel Kernels☆1,530Aug 12, 2026Updated 2 weeks ago
- Muon is Scalable for LLM Training☆1,541Aug 3, 2025Updated last year
- ☆138May 29, 2025Updated last year
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Helpful tools and examples for working with flex-attention☆1,230Updated this week
- Quantized Attention on GPU☆45Nov 22, 2024Updated last year
- [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.☆1,042Feb 25, 2026Updated 6 months ago
- A Quirky Assortment of CuTe Kernels☆1,135Updated this week
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆539Feb 10, 2025Updated last year
- DeeperGEMM: crazy optimized version☆85May 5, 2025Updated last year
- Ring attention implementation with flash attention☆1,049Sep 10, 2025Updated 11 months ago
- DeepSeek Native Sparse Attention pytorch implementation☆119Dec 17, 2025Updated 8 months ago
- FlashInfer: Kernel Library for LLM Serving☆6,298Updated this week
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- ☆285Jun 6, 2025Updated last year
- ☆37Aug 7, 2025Updated last year
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,226Apr 8, 2026Updated 4 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆404Jul 10, 2025Updated last year
- A Survey of Efficient Attention Methods: Hardware-efficient, Sparse, Compact, and Linear Attention☆309Dec 1, 2025Updated 9 months ago
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆7,310Updated this week
- Compact and Agent-Native MoE Training System☆345Aug 22, 2026Updated last week
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆854Mar 6, 2025Updated last year
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆266Aug 9, 2025Updated last year
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- ☆65Apr 26, 2025Updated last year
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,357Aug 28, 2025Updated last year
- Efficient Triton Kernels for LLM Training☆6,595Updated this week
- Tile primitives for speedy kernels☆3,661Updated this week
- ☆54May 19, 2025Updated last year
- ☆124May 19, 2025Updated last year
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆690May 21, 2026Updated 3 months ago