dhcode-cpp / NSA-pytorchLinks
DeepSeek Native Sparse Attention pytorch implementation
☆111Updated last month
Alternatives and similar repositories for NSA-pytorch
Users that are interested in NSA-pytorch are comparing it to the libraries listed below
Sorting:
- qwen-nsa☆87Updated 3 months ago
- Efficient Mixture of Experts for LLM Paper List☆156Updated 3 months ago
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs☆187Updated 3 months ago
- ☆152Updated 6 months ago
- TransMLA: Multi-Head Latent Attention Is All You Need (NeurIPS 2025 Spotlight)☆426Updated 3 months ago
- Tiny-Megatron, a minimalistic re-implementation of the Megatron library☆21Updated 4 months ago
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆147Updated 3 weeks ago
- Tiny-DeepSpeed, a minimalistic re-implementation of the DeepSpeed library☆49Updated 5 months ago
- ☆127Updated 7 months ago
- A Survey of Efficient Attention Methods: Hardware-efficient, Sparse, Compact, and Linear Attention☆271Updated last month
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆265Updated 6 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆160Updated 3 months ago
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆200Updated last month
- [CoLM'25] The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>☆153Updated last week
- Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models☆339Updated 10 months ago
- Implementation of FlashAttention in PyTorch☆180Updated last year
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆283Updated 2 months ago
- The Official Implementation of Ada-KV [NeurIPS 2025]☆125Updated last month
- 16-fold memory access reduction with nearly no loss☆109Updated 9 months ago
- This repository is the official implementation of "Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE"☆36Updated 3 months ago
- analyse problems of AI with Math and Code☆27Updated 5 months ago
- ☆153Updated 10 months ago
- ☆81Updated last month
- ☆132Updated 7 months ago
- 青稞Talk☆186Updated last week
- Triton Documentation in Chinese Simplified / Triton 中文文档☆99Updated last month
- ☆444Updated 5 months ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆257Updated 5 months ago
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter☆126Updated last month
- A lightweight reinforcement learning framework that integrates seamlessly into your codebase, empowering developers to focus on algorithm…☆98Updated 4 months ago