Alternatives and similar repositories for transformer_nuggets

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

• srush / triton-autodiff
  Experiment of using Tangent to autodiff triton
  ☆78Updated last year
• UmerHA / triton_util
  Make triton easier
  ☆47Updated 11 months ago
• cloneofsimo / min-fsdp
  ☆78Updated 10 months ago
• lianakoleva / no-libtorch-compile
  ☆21Updated 2 months ago
• amirzandieh / HyperAttention
  Triton Implementation of HyperAttention Algorithm
  ☆48Updated last year
• shreyansh26 / Attention-Mask-Patterns
  Using FlexAttention to compute attention with different masking patterns
  ☆43Updated 8 months ago
• graphcore-research / out-of-the-box-fp8-training
  Demo of the unit_scaling library, showing how a model can be easily adapted to train in FP8.
  ☆44Updated 10 months ago
• mgmalek / efficient_cross_entropy
  ☆108Updated last year
• GindaChen / FlexFlashAttention3
  FlexAttention w/ FlashAttention3 Support
  ☆26Updated 7 months ago
• lucidrains / autoregressive-linear-attention-cuda
  CUDA implementation of autoregressive linear attention, with all the latest research findings
  ☆43Updated 2 years ago
• joey00072 / ohara
  Collection of autoregressive model implementation
  ☆85Updated last month
• cat-state / tinypar
  ☆20Updated last year
• haileyschoelkopf / triton-index
  See https://github.com/cuda-mode/triton-index/ instead!
  ☆10Updated last year
• gau-nernst / learn-cuda
  Learn CUDA with PyTorch
  ☆21Updated this week
• ezyang / torchdbg
  PyTorch centric eager mode debugger
  ☆47Updated 5 months ago
• fal-ai-community / NativeSparseAttention
  research impl of Native Sparse Attention (2502.11089)
  ☆54Updated 3 months ago
• thecharlieblake / lovely-llama
  An implementation of the Llama architecture, to instruct and delight
  ☆21Updated this week
• cloneofsimo / zeroshampoo
  ☆33Updated 8 months ago
• rwightman / genalog
  Genalog is an open source, cross-platform python package allowing generation of synthetic document images with custom degradations and te…
  ☆41Updated last year
• lucaslingle / mu_transformer
  Transformer with Mu-Parameterization, implemented in Jax/Flax. Supports FSDP on TPU pods.
  ☆30Updated last week
• frankxwang / dpo-prefix-sharing
  DPO, but faster 🚀
  ☆42Updated 5 months ago
• srush / Tensor-Puzzles-Penzai
  ☆20Updated last year
• warner-benjamin / optimi
  Fast, Modern, Memory Efficient, and Low Precision PyTorch Optimizers
  ☆93Updated 10 months ago
• eth-easl / fmengine
  Utilities for Training Very Large Models
  ☆58Updated 8 months ago
• softmax1 / Flash-Attention-Softmax-N
  CUDA and Triton implementations of Flash Attention with SoftmaxN.
  ☆70Updated last year
• cloneofsimo / min-max-gpt
  Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training
  ☆127Updated last year
• Jokeren / triton-samples
  ☆28Updated 4 months ago
• lernapparat / torchhacks
  Hacks for PyTorch
  ☆19Updated 2 years ago
• lessw2020 / transformer_central
  Various transformers for FSDP research
  ☆37Updated 2 years ago
• sholtodouglas / scalingExperiments
  ☆59Updated 3 years ago