🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"
☆1,004Feb 5, 2026Updated 4 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☆807Aug 15, 2025Updated 9 months ago
- Efficient triton implementation of Native Sparse Attention.☆279May 23, 2025Updated last year
- 🚀 Efficient implementations for emerging model architectures☆5,206Updated this week
- MoBA: Mixture of Block Attention for Long-Context LLMs☆2,123Apr 3, 2025Updated last year
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆134Jun 24, 2025Updated 11 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.
- A sparse attention kernel supporting mix sparse patterns☆518Jan 18, 2026Updated 4 months ago
- qwen-nsa☆87Oct 14, 2025Updated 7 months ago
- Muon is Scalable for LLM Training☆1,487Aug 3, 2025Updated 10 months ago
- Distributed Compiler based on Triton for Parallel Systems☆1,455Apr 22, 2026Updated last month
- Quantized Attention on GPU☆44Nov 22, 2024Updated last year
- Helpful tools and examples for working with flex-attention☆1,195May 28, 2026Updated 2 weeks ago
- FlashInfer: Kernel Library for LLM Serving☆5,760Updated this week
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆541Feb 10, 2025Updated last year
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆840Jun 5, 2026Updated last week
- 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.
- [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.☆1,002Feb 25, 2026Updated 3 months ago
- 🔥 A minimal training framework for scaling FLA models☆391Apr 22, 2026Updated last month
- Ring attention implementation with flash attention☆1,025Sep 10, 2025Updated 9 months ago
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,219Apr 8, 2026Updated 2 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆391Jul 10, 2025Updated 11 months ago
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆6,434Jun 5, 2026Updated last week
- ☆116Feb 25, 2025Updated last year
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆843Mar 6, 2025Updated last year
- 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.
- DeepSeek Native Sparse Attention pytorch implementation☆118Dec 17, 2025Updated 5 months ago
- ☆66Apr 26, 2025Updated last year
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆265Aug 9, 2025Updated 10 months ago
- Efficient Triton Kernels for LLM Training☆6,415Jun 5, 2026Updated last week
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆168Oct 13, 2025Updated 7 months ago
- ☆248Nov 19, 2025Updated 6 months ago
- ☆52May 19, 2025Updated last year
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,323Aug 28, 2025Updated 9 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆672May 21, 2026Updated 3 weeks ago
- 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.
- Tile primitives for speedy kernels☆3,420May 27, 2026Updated 2 weeks ago
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆765Aug 6, 2025Updated 10 months ago
- Efficient LLM Inference over Long Sequences☆394Jun 25, 2025Updated 11 months ago
- flash attention tutorial written in python, triton, cuda, cutlass☆523Jan 20, 2026Updated 4 months ago
- Fast low-bit matmul kernels in Triton☆470May 15, 2026Updated 3 weeks ago
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆7,342Jun 4, 2026Updated last week
- A bidirectional pipeline parallelism algorithm for computation-communication overlap in DeepSeek V3/R1 training.☆2,962Jan 14, 2026Updated 4 months ago