Alternatives and similar repositories for NativeSparseAttention

Users that are interested in NativeSparseAttention are comparing it to the libraries listed below

• fal-ai / diffusion-speedrun
  Focused on fast experimentation and simplicity
  ☆75Updated 8 months ago
• ethansmith2000 / fsdp_optimizers
  supporting pytorch FSDP for optimizers
  ☆84Updated 9 months ago
• fal-ai-community / nano-mdm
  Tiny re-implementation of MDM in style of LLaDA and nano-gpt speedrun
  ☆56Updated 6 months ago
• bloc97 / DeMo
  DeMo: Decoupled Momentum Optimization
  ☆190Updated 9 months ago
• cloneofsimo / min-fsdp
  ☆87Updated last year
• lucidrains / PEER-pytorch
  Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind
  ☆128Updated last year
• main-horse / hnet
  H-Net Dynamic Hierarchical Architecture
  ☆79Updated last month
• lucidrains / taylor-series-linear-attention
  Explorations into the recently proposed Taylor Series Linear Attention
  ☆100Updated last year
• kyleliang919 / Super_Muon
  ☆63Updated 5 months ago
• cloneofsimo / scaling-guide
  WIP
  ☆94Updated last year
• cloneofsimo / minSAE
  ☆30Updated 9 months ago
• ethansmith2000 / TransformerExperiments
  ☆19Updated 3 months ago
• NX-AI / mlstm_kernels
  Tiled Flash Linear Attention library for fast and efficient mLSTM Kernels.
  ☆68Updated last month
• BlinkDL / LinearAttentionArena
  Here we will test various linear attention designs.
  ☆62Updated last year
• lucidrains / simplicial-attention
  Implementation of 2-simplicial attention proposed by Clift et al. (2019) and the recent attempt to make practical in Fast and Simplex, Ro…
  ☆46Updated last week
• cloneofsimo / zeroshampoo
  ☆34Updated last year
• ClashLuke / SOAP
  ☆21Updated 10 months ago
• apple / ml-ademamix
  ☆65Updated 10 months ago
• NVIDIA / ngpt
  Normalized Transformer (nGPT)
  ☆188Updated 9 months ago
• cloneofsimo / ezmup
  Simple implementation of muP, based on Spectral Condition for Feature Learning. The implementation is SGD only, dont use it for Adam
  ☆85Updated last year
• RWKV / ZeroCoT
  https://x.com/BlinkDL_AI/status/1884768989743882276
  ☆28Updated 4 months ago
• mgmalek / efficient_cross_entropy
  ☆118Updated last year
• nil0x9 / flash-muon
  Flash-Muon: An Efficient Implementation of Muon Optimizer
  ☆181Updated 3 months ago
• Zyphra / tree_attention
  Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters
  ☆129Updated 9 months ago
• martin-marek / batch-size
  📄Small Batch Size Training for Language Models
  ☆60Updated 2 weeks ago
• proger / hippogriff
  Griffin MQA + Hawk Linear RNN Hybrid
  ☆89Updated last year
• cloneofsimo / min-max-gpt
  Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training
  ☆132Updated last year
• proger / accelerated-scan
  Accelerated First Order Parallel Associative Scan
  ☆188Updated last year
• frankxwang / dpo-prefix-sharing
  DPO, but faster 🚀
  ☆44Updated 9 months ago
• warner-benjamin / optimi
  Fast, Modern, and Low Precision PyTorch Optimizers
  ☆109Updated last week