Alternatives and similar repositories for power-attention

Users that are interested in power-attention are comparing it to the libraries listed below

• bloc97 / DeMo
  DeMo: Decoupled Momentum Optimization
  ☆190Updated 9 months ago
• main-horse / hnet
  H-Net Dynamic Hierarchical Architecture
  ☆80Updated last month
• LucasPrietoAl / grokking-at-the-edge-of-numerical-stability
  ☆102Updated last month
• MatX-inc / seqax
  seqax = sequence modeling + JAX
  ☆166Updated last month
• ethansmith2000 / fsdp_optimizers
  supporting pytorch FSDP for optimizers
  ☆84Updated 8 months ago
• athms / mad-lab
  A MAD laboratory to improve AI architecture designs 🧪
  ☆127Updated 8 months ago
• EleutherAI / nanoGPT-mup
  The simplest, fastest repository for training/finetuning medium-sized GPTs.
  ☆156Updated 2 months ago
• dvruette / barrel-rec-pytorch
  ☆53Updated last year
• cloneofsimo / min-max-gpt
  Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training
  ☆131Updated last year
• proger / accelerated-scan
  Accelerated First Order Parallel Associative Scan
  ☆187Updated last year
• NVIDIA / ngpt
  Normalized Transformer (nGPT)
  ☆187Updated 9 months ago
• Zyphra / tree_attention
  Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters
  ☆129Updated 9 months ago
• HazyResearch / zoology
  Understand and test language model architectures on synthetic tasks.
  ☆222Updated last month
• epfml / DenseFormer
  ☆82Updated last year
• berlino / seq_icl
  ☆53Updated last year
• modula-systems / modula
  🧱 Modula software package
  ☆231Updated 2 weeks ago
• google / tunix
  A JAX-native LLM Post-Training Library
  ☆128Updated last week
• JoeLi12345 / nGPT
  an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)
  ☆105Updated 5 months ago
• martin-marek / batch-size
  📄Small Batch Size Training for Language Models
  ☆57Updated last week
• VatsaDev / NanoPoor
  NanoGPT-speedrunning for the poor T4 enjoyers
  ☆70Updated 4 months ago
• srush / triton-autodiff
  Experiment of using Tangent to autodiff triton
  ☆80Updated last year
• shikaiqiu / compute-better-spent
  ☆57Updated 11 months ago
• cloneofsimo / min-fsdp
  ☆87Updated last year
• xrsrke / pipegoose
  Large scale 4D parallelism pre-training for 🤗 transformers in Mixture of Experts *(still work in progress)*
  ☆87Updated last year
• apple / ml-ademamix
  ☆65Updated 9 months ago
• test-time-training / ttt-tk
  ☆40Updated 4 months ago
• microsoft / dion
  Dion optimizer algorithm
  ☆334Updated this week
• Jaykef / Triton-nanoGPT
  Custom triton kernels for training Karpathy's nanoGPT.
  ☆19Updated 10 months ago
• lucidrains / PEER-pytorch
  Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind
  ☆127Updated last year
• apple / ml-planner
  ☆55Updated last year