sdpmas

triton

Development repository for the Triton language and compiler

LAVIS

LAVIS - A One-stop Library for Language-Vision Intelligence

Megatron-LM

Ongoing research training transformer models at scale

einops

Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)

torchdiffeq

Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.

bolt

10x faster matrix and vector operations

hivemind

Decentralized deep learning in PyTorch. Built to train models on thousands of volunteers across the world.

dreamerv3

Mastering Diverse Domains through World Models

iris

Transformers are Sample-Efficient World Models. ICLR 2023, notable top 5%.

torchsort

Fast, differentiable sorting and ranking in PyTorch

cuda_programming

Code from the "CUDA Crash Course" YouTube series by CoffeeBeforeArch

ml-compiler-opt

Infrastructure for Machine Learning Guided Optimization (MLGO) in LLVM.

category-theory-resources

Resources for learning Category Theory for an enthusiast

gflownet

Generative Flow Networks

clrs

Awesome-GFlowNets

A curated list of resources about generative flow networks (GFlowNets).

G.pt

Official PyTorch Implementation of "Learning to Learn with Generative Models of Neural Network Checkpoints"

HEPML-LivingReview

Living Review of Machine Learning for Particle Physics

walk_in_the_park

raspy

An interactive exploration of Transformer programming.

in-context-learning

gfn-lm-tuning

lvt

The PyTorch implementation of Latent Video Transformer.

minimal-flask-api

A template for 'production ready' Flask APIs with Flask & Gunicorn. Includes template test and error-handling files.

TNP-pytorch

Official implementation of Transformer Neural Processes

neural-network-cuda

A neural network from scratch in CUDA/C++

GNCA

Code for "Learning Graph Cellular Automata" (NeurIPS 2021).

information-bottleneck

Deep Learning & Information Bottleneck

lila

Code for "Invariance Learning in Deep Neural Networks with Differentiable Laplace Approximations"

CatGNN

Prototype for a Category Theory-based GNN Library