fla-org / native-sparse-attentionLinks
🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"
☆916Updated 7 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
Sorting:
- Implementation of the sparse attention pattern proposed by the Deepseek team in their "Native Sparse Attention" paper☆778Updated 2 months ago
- Ring attention implementation with flash attention☆903Updated last month
- Muon is Scalable for LLM Training☆1,348Updated 3 months ago
- Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"☆620Updated last week
- TransMLA: Multi-Head Latent Attention Is All You Need (NeurIPS 2025 Spotlight)☆396Updated last month
- VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo☆1,247Updated last week
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆586Updated 3 weeks ago
- 🔥 A minimal training framework for scaling FLA models☆273Updated last month
- Helpful tools and examples for working with flex-attention☆1,038Updated last week
- Efficient triton implementation of Native Sparse Attention.☆242Updated 5 months ago
- [ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Rule☆337Updated last month
- slime is an LLM post-training framework for RL Scaling.☆2,323Updated this week
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆545Updated this week
- Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling☆449Updated 5 months ago
- Efficient LLM Inference over Long Sequences☆390Updated 4 months ago
- LLM KV cache compression made easy☆674Updated this week
- ☆429Updated 2 months ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆451Updated this week
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆498Updated 8 months ago
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,143Updated last month
- ☆868Updated 3 weeks ago
- Muon is an optimizer for hidden layers in neural networks☆1,960Updated 3 months ago
- [NeurIPS 2025 Spotlight] TPA: Tensor ProducT ATTenTion Transformer (T6) (https://arxiv.org/abs/2501.06425)☆418Updated last week
- Large Context Attention☆746Updated 3 weeks ago
- 📰 Must-read papers on KV Cache Compression (constantly updating 🤗).☆584Updated last month
- Scalable toolkit for efficient model reinforcement☆977Updated this week
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆193Updated last month
- 🚀 Efficient implementations of state-of-the-art linear attention models☆3,661Updated this week
- MoBA: Mixture of Block Attention for Long-Context LLMs☆1,950Updated 7 months ago
- DeepSeek Native Sparse Attention pytorch implementation☆107Updated 3 weeks ago