KellerJordan / top-sgd

Related projects ⓘ

Alternatives and complementary repositories for top-sgd

• lixilinx / psgd_torch
  Pytorch implementation of preconditioned stochastic gradient descent (affine group preconditioner, low-rank approximation preconditioner …
  ☆128Updated last month
• shikaiqiu / compute-better-spent
  ☆46Updated last month
• google-deepmind / dks
  Multi-framework implementation of Deep Kernel Shaping and Tailored Activation Transformations, which are methods that modify neural netwo…
  ☆64Updated this week
• NVlabs / Forecasting-Model-Search
  A system for automating selection and optimization of pre-trained models from the TAO Model Zoo
  ☆22Updated 4 months ago
• stanislavfort / dissect-git-re-basin
  Replicating and dissecting the git-re-basin project in one-click-replication Colabs
  ☆36Updated 2 years ago
• dasayan05 / iclr24_blog_code
  Code repo for ICLR 24 BlogPost titled "Building Diffusion Model's theory from ground up"
  ☆13Updated 11 months ago
• lucidrains / frame-averaging-pytorch
  Pytorch implementation of a simple way to enable (Stochastic) Frame Averaging for any network
  ☆47Updated 3 months ago
• nikhilvyas / SOAP
  ☆128Updated this week
• facebookresearch / w2ot
  Euclidean Wasserstein-2 optimal transportation
  ☆44Updated last year
• AllanYangZhou / universal_neural_functional
  ☆48Updated 9 months ago
• facebookresearch / meta-ot
  Meta Optimal Transport
  ☆97Updated last year
• flukeskywalker / nanoDD
  Simple Scalable Discrete Diffusion for text in PyTorch
  ☆28Updated last month
• layer6ai-labs / calo-forest
  A scalable implementation of diffusion and flow-matching with XGBoost models, applied to calorimeter data.
  ☆17Updated 2 weeks ago
• kvfrans / jax-flow
  Flow-matching algorithms in JAX
  ☆77Updated 3 months ago
• radarFudan / mamba-minimal-jax
  ☆29Updated 2 months ago
• dylandoblar / noether-networks
  Meta-learning inductive biases in the form of useful conserved quantities.
  ☆37Updated 2 years 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.
  ☆35Updated 4 months ago
• Artur-Galstyan / statedict2pytree
  ☆40Updated 4 months ago
• google-deepmind / eigengame
  Open source code for EigenGame.
  ☆28Updated last year
• srush / triton-autodiff
  Experiment of using Tangent to autodiff triton
  ☆72Updated 9 months ago
• apple / ml-ademamix
  ☆48Updated last week
• jxbz / modula
  Scalable neural net training via automatic normalization in the modular norm.
  ☆121Updated 3 months ago
• advaitgosai / autocite
  simple bibtex generator for any text with \cite{}
  ☆31Updated 4 months ago
• aks2203 / easy-to-hard
  Official repository for the paper "Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks"
  ☆60Updated 2 years ago
• CLAIRE-Labo / flash_attention
  A basic pure pytorch implementation of flash attention
  ☆16Updated 3 weeks ago
• cloneofsimo / min-fsdp
  ☆73Updated 4 months ago
• vvvm23 / mamba-jax
  Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX
  ☆79Updated 9 months ago
• michaelsdr / sinkformers
  Transformers with doubly stochastic attention
  ☆40Updated 2 years ago
• matthias-wright / jax-fid
  FID computation in Jax/Flax.
  ☆24Updated 4 months ago