An efficient implementation of the NSA (Native Sparse Attention) kernel
☆135Jun 24, 2025Updated last year
Alternatives and similar repositories for nsa-release
Users that are interested in nsa-release are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆37Aug 7, 2025Updated last year
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆1,021Feb 5, 2026Updated 7 months ago
- Some funny cute/cuteDSL code snippets☆35Mar 2, 2026Updated 6 months ago
- FA4-based Relative Attention Kernel developed by TML and Colfax☆18Sep 11, 2026Updated last week
- Efficient triton implementation of Native Sparse Attention.☆283May 23, 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.
- ☆48Dec 13, 2025Updated 9 months ago
- DeepSeek-V3.2-Exp DSA Warmup Lightning Indexer training operator based on tilelang☆52Nov 19, 2025Updated 9 months ago
- Benchmark tests supporting the TiledCUDA library.☆19Nov 19, 2024Updated last year
- High performance RMSNorm Implement by using SM Core Storage(Registers and Shared Memory)☆31Jan 22, 2026Updated 7 months ago
- Minimal PyTorch implementation of TP, SP, FSDP and sharded-EMA☆32Nov 27, 2025Updated 9 months ago
- ☆46Oct 15, 2025Updated 11 months ago
- DeeperGEMM: crazy optimized version☆85May 5, 2025Updated last year
- ☆254Nov 19, 2025Updated 9 months ago
- ☆32Jul 2, 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.
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆262Jun 15, 2025Updated last year
- ☆287Jun 6, 2025Updated last year
- ☆39Dec 14, 2025Updated 9 months ago
- Code repository for the SOSP'25 paper DCP: Addressing Input Dynamism In Long-Context Training via Dynamic Context Parallelism.☆22Nov 28, 2025Updated 9 months ago
- [ICLR 2025 & COLM 2025] Official PyTorch implementation of the Forgetting Transformer and Adaptive Computation Pruning☆154Feb 25, 2026Updated 6 months ago
- Memory optimized Mixture of Experts☆84Jul 25, 2025Updated last year
- ☆138May 29, 2025Updated last year
- ☆54May 19, 2025Updated last year
- Accelerating MoE with IO and Tile-aware Optimizations☆767Aug 29, 2026Updated 2 weeks ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆942Updated this week
- NVIDIA cuTile learn☆168Dec 9, 2025Updated 9 months ago
- ☆14Mar 2, 2025Updated last year
- High-performance LLM operator library built on TileLang.☆187Updated this week
- ☆104Feb 11, 2026Updated 7 months ago
- ☆73Mar 24, 2026Updated 5 months ago
- Official repository for Parallax (Parameterized Local Linear Attention)☆69Jul 30, 2026Updated last month
- The Newton-Muon optimizer☆32Jun 5, 2026Updated 3 months ago
- The evaluation framework for training-free sparse attention in LLMs☆132Jan 27, 2026Updated 7 months ago
- 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.
- Stick-breaking attention☆64Jul 1, 2025Updated last year
- qwen-nsa☆87Oct 14, 2025Updated 11 months ago
- ☆22May 5, 2025Updated last year
- ☆37Dec 31, 2025Updated 8 months ago
- Quantized Attention on GPU☆45Nov 22, 2024Updated last year
- Tilus is a tile-level kernel programming language with explicit control over shared memory and registers.☆492Sep 7, 2026Updated last week
- A Quirky Assortment of CuTe Kernels☆1,146Updated this week