patrick-kidger

bagua

Bagua Speeds up PyTorch

cockpit

Cockpit: A Practical Debugging Tool for Training Deep Neural Networks

restic

Fast, secure, efficient backup program

github-cards

The unofficial GitHub Cards. Card for your GitHub profile, card for your GitHub repositories.

py-spy

Sampling profiler for Python programs

plum

Multiple dispatch in Python

x-transformers

A simple but complete full-attention transformer with a set of promising experimental features from various papers

modern-unix

A collection of modern/faster/saner alternatives to common unix commands.

monkeytype

The most customizable typing website with a minimalistic design and a ton of features. Test yourself in various modes, track your progress and improve your speed.

cifar10-fast

DimensionalData.jl

Named dimensions and indexing for julia arrays and other data

adaptdl

Resource-adaptive cluster scheduler for deep learning training.

WeightWatcher

The WeightWatcher tool for predicting the accuracy of Deep Neural Networks

beartype

Unbearably fast near-real-time hybrid runtime-static type-checking in pure Python.

AxisKeys.jl

🎹

diff-zoo

Differentiation for Hackers

SymbolicRegression.jl

Distributed High-Performance Symbolic Regression in Julia

ManualDispatch.jl

Avoid method dispatch at runtime

RuntimeGeneratedFunctions.jl

Functions generated at runtime without world-age issues or overhead

ThreadPools.jl

Improved thread management for background and nonuniform tasks in Julia. Docs at https://tro3.github.io/ThreadPools.jl

SciMLBook

Parallel Computing and Scientific Machine Learning (SciML): Methods and Applications (MIT 18.337J/6.338J)

FromFile.jl

Julia enhancement proposal (Julep) for implicit per file module in Julia

alive-progress

A new kind of Progress Bar, with real-time throughput, ETA, and very cool animations!

pytorch-optimizer

torch-optimizer -- collection of optimizers for Pytorch

ssqueezepy

Synchrosqueezing, wavelet transforms, and time-frequency analysis in Python

probabilitydistributiontoolbox

Folklore facts on probability distribution learning, testing, and whatever-ing

glow

Code for reproducing results in "Glow: Generative Flow with Invertible 1x1 Convolutions"

FasterNeuralDiffEq

Code for "'Hey, that's not an ODE:' Faster ODE Adjoints via Seminorms" (ICML 2021)

neuralRDEs

Code for: "Neural Rough Differential Equations for Long Time Series", (ICML 2021)

torchcde

Differentiable controlled differential equation solvers for PyTorch with GPU support and memory-efficient adjoint backpropagation.