fla-org / native-sparse-attentionLinks
🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"
☆925Updated 8 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:
- Ring attention implementation with flash attention☆921Updated 2 months ago
- Implementation of the sparse attention pattern proposed by the Deepseek team in their "Native Sparse Attention" paper☆782Updated 3 months ago
- Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"☆696Updated last month
- Muon is Scalable for LLM Training☆1,365Updated 3 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆602Updated last month
- 🔥 A minimal training framework for scaling FLA models☆311Updated last week
- Efficient triton implementation of Native Sparse Attention.☆250Updated 6 months ago
- VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo☆1,338Updated this week
- TransMLA: Multi-Head Latent Attention Is All You Need (NeurIPS 2025 Spotlight)☆412Updated 2 months ago
- Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling☆451Updated 6 months ago
- [ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Rule☆379Updated 2 months ago
- Helpful tools and examples for working with flex-attention☆1,059Updated last week
- Efficient LLM Inference over Long Sequences☆391Updated 5 months ago
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆562Updated this week
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆505Updated 9 months ago
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆195Updated last month
- slime is an LLM post-training framework for RL Scaling.☆2,543Updated this week
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆483Updated last week
- LLM KV cache compression made easy☆694Updated this week
- ☆438Updated 3 months ago
- Scalable toolkit for efficient model reinforcement☆1,036Updated last week
- ☆550Updated 2 months ago
- ☆912Updated 3 weeks ago
- Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch☆545Updated 6 months ago
- [NeurIPS 2025 Spotlight] TPA: Tensor ProducT ATTenTion Transformer (T6) (https://arxiv.org/abs/2501.06425)☆426Updated last month
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs☆173Updated 2 months ago
- MoBA: Mixture of Block Attention for Long-Context LLMs☆2,006Updated 7 months ago
- Large Context Attention☆752Updated last month
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆275Updated 2 weeks ago
- 📰 Must-read papers on KV Cache Compression (constantly updating 🤗).☆608Updated last month