dhcode-cpp / NSA-pytorchLinks
DeepSeek Native Sparse Attention pytorch implementation
☆97Updated 2 months ago
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☆75Updated 5 months ago
- TransMLA: Multi-Head Latent Attention Is All You Need (NeurIPS 2025 Spotlight)☆372Updated 2 weeks ago
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs☆155Updated 2 weeks ago
- Efficient Mixture of Experts for LLM Paper List☆131Updated last week
- ☆144Updated 3 months ago
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆234Updated 3 months ago
- Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"☆496Updated this week
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆117Updated 5 months ago
- Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models☆327Updated 7 months ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆241Updated last month
- ☆43Updated last year
- ☆55Updated last week
- ☆119Updated 4 months ago
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆192Updated 3 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆143Updated 4 months ago
- ☆429Updated last month
- Implementation of FlashAttention in PyTorch☆171Updated 8 months ago
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆249Updated last week
- A sparse attention kernel supporting mix sparse patterns☆311Updated 7 months ago
- The Official Implementation of Ada-KV [NeurIPS 2025]☆99Updated last week
- 16-fold memory access reduction with nearly no loss☆105Updated 6 months ago
- 青稞Talk☆148Updated 2 weeks ago
- Tiny-Megatron, a minimalistic re-implementation of the Megatron library☆17Updated last month
- [CoLM'25] The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>☆146Updated 2 months ago
- ☆147Updated 7 months ago
- Efficient triton implementation of Native Sparse Attention.☆226Updated 4 months ago
- Tiny-DeepSpeed, a minimalistic re-implementation of the DeepSpeed library☆46Updated last month
- D^2-MoE: Delta Decompression for MoE-based LLMs Compression☆67Updated 6 months ago
- analyse problems of AI with Math and Code☆25Updated 2 months ago
- Awesome list for LLM quantization☆312Updated last week