Alternatives and similar repositories for dense-attention

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

• skolai / fewbit
  Compression schema for gradients of activations in backward pass
  ☆44Updated 2 years ago
• warner-benjamin / optimi
  Fast, Modern, and Low Precision PyTorch Optimizers
  ☆116Updated 2 months ago
• HomebrewML / Olmax
  HomebrewNLP in JAX flavour for maintable TPU-Training
  ☆51Updated last year
• alvarobartt / safejax
  Serialize JAX, Flax, Haiku, or Objax model params with 🤗`safetensors`
  ☆47Updated last year
• lixilinx / psgd_torch
  Pytorch implementation of preconditioned stochastic gradient descent (Kron and affine preconditioner, low-rank approximation precondition…
  ☆188Updated last month
• google-research / jestimator
  Amos optimizer with JEstimator lib.
  ☆82Updated last year
• 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.
  ☆45Updated last year
• graphcore-research / unit-scaling
  A library for unit scaling in PyTorch
  ☆132Updated 4 months ago
• ai-forever / LIBRA
  ☆18Updated 7 months ago
• LIONS-EPFL / scion
  ☆47Updated 3 weeks ago
• hal-314 / fastai-batch-size-finder
  Implementation of OpenAI paper with Simple Noise Scale on Fastai V2
  ☆20Updated 4 years ago
• meta-pytorch / torchfix
  TorchFix - a linter for PyTorch-using code with autofix support
  ☆148Updated 2 months ago
• HomebrewML / HomebrewNLP-torch
  A case study of efficient training of large language models using commodity hardware.
  ☆68Updated 3 years ago
• mgrankin / minGPT
  minGPT in JAX
  ☆48Updated 3 years ago
• srush / triton-autodiff
  Experiment of using Tangent to autodiff triton
  ☆79Updated last year
• FusionBrainLab / LLM-Microscope
  ☆70Updated last year
• drisspg / transformer_nuggets
  A place to store reusable transformer components of my own creation or found on the interwebs
  ☆59Updated last month
• edwardjhu / TP4
  Code accompanying our paper "Feature Learning in Infinite-Width Neural Networks" (https://arxiv.org/abs/2011.14522)
  ☆63Updated 4 years ago
• lucaslingle / mu_transformer
  Transformer with Mu-Parameterization, implemented in Jax/Flax. Supports FSDP on TPU pods.
  ☆32Updated 5 months ago
• mgmalek / efficient_cross_entropy
  ☆121Updated last year
• glassroom / heinsen_sequence
  Code implementing "Efficient Parallelization of a Ubiquitious Sequential Computation" (Heinsen, 2023)
  ☆96Updated 11 months ago
• davisyoshida / abnormal-floats
  Code for the note "NF4 Isn't Information Theoretically Optimal (and that's Good)
  ☆21Updated 2 years ago
• microsoft / mutransformers
  some common Huggingface transformers in maximal update parametrization (µP)
  ☆86Updated 3 years ago
• cloneofsimo / min-fsdp
  ☆91Updated last year
• ClashLuke / tpucare
  Automatically take good care of your preemptible TPUs
  ☆37Updated 2 years ago
• stat-ml / ncvis
  Noise-Contrastive Visualization
  ☆55Updated last year
• yandex-research / DeDLOC
  Official code for "Distributed Deep Learning in Open Collaborations" (NeurIPS 2021)
  ☆118Updated 3 years ago
• arogozhnikov / adamw_bfloat16
  AdamW optimizer for bfloat16 models in pytorch 🔥.
  ☆37Updated last year
• cat-state / tinypar
  ☆20Updated 2 years ago
• BlinkDL / SmallInitEmb
  LayerNorm(SmallInit(Embedding)) in a Transformer to improve convergence
  ☆60Updated 3 years ago