lucidrains / native-sparse-attention-pytorchLinks
Implementation of the sparse attention pattern proposed by the Deepseek team in their "Native Sparse Attention" paper
β772Updated 2 months ago
Alternatives and similar repositories for native-sparse-attention-pytorch
Users that are interested in native-sparse-attention-pytorch are comparing it to the libraries listed below
Sorting:
- π³ Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"β903Updated 7 months ago
- [ICLR2025 Spotlightπ₯] Official Implementation of TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parametersβ574Updated 8 months ago
- [NeurIPS 2025 Spotlight] TPA: Tensor ProducT ATTenTion Transformer (T6) (https://arxiv.org/abs/2501.06425)β400Updated 3 weeks ago
- Muon is an optimizer for hidden layers in neural networksβ1,888Updated 3 months ago
- H-Net: Hierarchical Network with Dynamic Chunkingβ760Updated 3 weeks ago
- [ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Ruleβ331Updated last month
- Helpful tools and examples for working with flex-attentionβ1,020Updated this week
- Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Modelsβ856Updated 3 months ago
- Muon is Scalable for LLM Trainingβ1,336Updated 2 months ago
- Official JAX implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden Statesβ423Updated last year
- TransMLA: Multi-Head Latent Attention Is All You Need (NeurIPS 2025 Spotlight)β389Updated last month
- Quick implementation of nGPT, learning entirely on the hypersphere, from NvidiaAIβ291Updated 4 months ago
- When it comes to optimizers, it's always better to be safe than sorryβ375Updated 3 weeks ago
- Code for Adam-mini: Use Fewer Learning Rates To Gain More https://arxiv.org/abs/2406.16793β439Updated 5 months ago
- β302Updated 6 months ago
- Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation (NeurIPS 2025)β484Updated 3 weeks ago
- β534Updated last month
- π₯ A minimal training framework for scaling FLA modelsβ266Updated last month
- Dream 7B, a large diffusion language modelβ1,018Updated 3 weeks ago
- Efficient LLM Inference over Long Sequencesβ390Updated 3 months ago
- Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"β581Updated last week
- Implementation of π Ring Attention, from Liu et al. at Berkeley AI, in Pytorchβ542Updated 5 months ago
- Efficient triton implementation of Native Sparse Attention.β238Updated 5 months ago
- Official PyTorch implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden Statesβ1,263Updated last year
- Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Modelsβ330Updated 8 months ago
- Ring attention implementation with flash attentionβ901Updated last month
- Official PyTorch implementation for ICLR2025 paper "Scaling up Masked Diffusion Models on Text"β326Updated 10 months ago
- π Efficient implementations of state-of-the-art linear attention modelsβ3,517Updated this week
- [NeurIPS 2024] Simple and Effective Masked Diffusion Language Modelβ537Updated 3 weeks ago
- β251Updated 4 months ago