lucidrains / native-sparse-attention-pytorch
Implementation of the sparse attention pattern proposed by the Deepseek team in their "Native Sparse Attention" paper
☆561Updated this week
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
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆590Updated last week
- [ICLR2025 Spotlight🔥] Official Implementation of TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters☆539Updated last month
- The official implementation of Tensor ProducT ATTenTion Transformer (T6)☆345Updated last month
- Muon optimizer: +>30% sample efficiency with <3% wallclock overhead☆521Updated 2 weeks ago
- ☆261Updated last month
- Muon is Scalable for LLM Training☆974Updated last month
- Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch☆506Updated 5 months ago
- Code for Adam-mini: Use Fewer Learning Rates To Gain More https://arxiv.org/abs/2406.16793☆399Updated 3 months ago
- Helpful tools and examples for working with flex-attention☆698Updated last week
- Efficient LLM Inference over Long Sequences☆365Updated last month
- TransMLA: Multi-Head Latent Attention Is All You Need☆220Updated 3 weeks ago
- ☆396Updated this week
- 🚀 Efficient implementations of state-of-the-art linear attention models in Torch and Triton☆2,144Updated this week
- Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models☆397Updated this week
- Ring attention implementation with flash attention☆714Updated last month
- PyTorch implementation of Infini-Transformer from "Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention…☆287Updated 10 months ago
- Quick implementation of nGPT, learning entirely on the hypersphere, from NvidiaAI☆276Updated last week
- Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models☆272Updated last month
- [ECCV 2024] Official PyTorch implementation of RoPE-ViT "Rotary Position Embedding for Vision Transformer"☆294Updated 3 months ago
- [ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Rule☆143Updated last week
- Official JAX implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States☆399Updated 7 months ago
- Normalized Transformer (nGPT)☆164Updated 4 months ago
- An Open-source RL System from ByteDance Seed and Tsinghua AIR☆767Updated last week
- Simple and Effective Masked Diffusion Language Model☆348Updated 3 weeks ago
- [ICML2024 (Oral)] Official PyTorch implementation of DoRA: Weight-Decomposed Low-Rank Adaptation☆748Updated 5 months ago
- Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, spars…☆310Updated 3 months ago
- Implementation of Autoregressive Diffusion in Pytorch☆364Updated 4 months ago
- Code release for DynamicTanh (DyT)☆710Updated last week
- Implementation of Rotary Embeddings, from the Roformer paper, in Pytorch☆651Updated 4 months ago
- Pytorch implementation of Transfusion, "Predict the Next Token and Diffuse Images with One Multi-Modal Model", from MetaAI☆985Updated last week