fla-org / native-sparse-attentionLinks
🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"
☆964Updated this week
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☆797Updated 5 months ago
- Ring attention implementation with flash attention☆979Updated 4 months ago
- Muon is Scalable for LLM Training☆1,426Updated 6 months ago
- TransMLA: Multi-Head Latent Attention Is All You Need (NeurIPS 2025 Spotlight)☆429Updated 4 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆641Updated 3 weeks ago
- Helpful tools and examples for working with flex-attention☆1,118Updated 3 weeks ago
- Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"☆825Updated last week
- 🔥 A minimal training framework for scaling FLA models☆343Updated 2 months ago
- [ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Rule☆452Updated 4 months ago
- Efficient triton implementation of Native Sparse Attention.☆262Updated 8 months ago
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆631Updated this week
- VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo☆1,620Updated this week
- ☆579Updated 4 months ago
- Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling☆468Updated 8 months ago
- Accelerating MoE with IO and Tile-aware Optimizations☆569Updated 3 weeks ago
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆524Updated 11 months ago
- Efficient LLM Inference over Long Sequences☆394Updated 7 months ago
- Training library for Megatron-based models with bidirectional Hugging Face conversion capability☆419Updated this week
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆204Updated 2 months ago
- Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.☆830Updated this week
- LLM KV cache compression made easy☆876Updated last week
- Scalable toolkit for efficient model reinforcement☆1,293Updated this week
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆676Updated this week
- Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models☆340Updated 11 months ago
- 📰 Must-read papers on KV Cache Compression (constantly updating 🤗).☆658Updated 4 months ago
- Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch☆549Updated 8 months ago
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,180Updated 4 months ago
- ☆449Updated 5 months ago
- A sparse attention kernel supporting mix sparse patterns☆453Updated 3 weeks ago
- [NeurIPS 2025 Spotlight] TPA: Tensor ProducT ATTenTion Transformer (T6) (https://arxiv.org/abs/2501.06425)☆445Updated 2 weeks ago