Pinned Repositories
cuda-mnist
Training MLP on MNIST in 2 seconds with pure CUDA
jax-diffusion
Implementation of Denoising Diffusion Probabilistic Models (DDPM) in JAX and Flax.
jax-logging
Imperative-like logging for JAX
jax-vqvae-gpt
Implementation of VQ-VAE with a GPT-style sampler in the JAX and Haiku ecosystem.
ml-weight-decay
Code for exploring effects of weight decay on neural network generalization
score-sde-inverse
Solving all kinds of (linear) inverse problems with diffusion models.
simpleGEMM
The simplest but fast implementation of matrix multiplication in CUDA.
sparse-dropout
SparseDrop is a simple, structured, and hardware-friendly variant of dropout that can benefit from sparsity on GPUs.
Text2Emoji
Text to emoji translation via DeepDreaming
YourMumBot
YourMumBot is a discord bot that makes your mum jokes based on content sent by users.
andylolu2's Repositories
andylolu2/cuda-mnist
Training MLP on MNIST in 2 seconds with pure CUDA
andylolu2/simpleGEMM
The simplest but fast implementation of matrix multiplication in CUDA.
andylolu2/jax-diffusion
Implementation of Denoising Diffusion Probabilistic Models (DDPM) in JAX and Flax.
andylolu2/jax-vqvae-gpt
Implementation of VQ-VAE with a GPT-style sampler in the JAX and Haiku ecosystem.
andylolu2/ml-weight-decay
Code for exploring effects of weight decay on neural network generalization
andylolu2/YourMumBot
YourMumBot is a discord bot that makes your mum jokes based on content sent by users.
andylolu2/score-sde-inverse
Solving all kinds of (linear) inverse problems with diffusion models.
andylolu2/jax-logging
Imperative-like logging for JAX
andylolu2/Learn-CUDA
Learning how to write CUDA
andylolu2/speedtoxify
Fast :speak_no_evil: Detoxify inference with ONNX runtime
andylolu2/adaptive-generation
Adaptive-compute generative modeling. Combining PonderNet and VAE/Diffusion models for better computation efficiency. Undergraduate dissertation @Cambridge.
andylolu2/ads-assignment
andylolu2/anthropic-hackathon
andylolu2/datasets
TFDS is a collection of datasets ready to use with TensorFlow, Jax, ...
andylolu2/dotfiles
My .dotfiles for Fish shell
andylolu2/sparse-dropout
SparseDrop is a simple, structured, and hardware-friendly variant of dropout that can benefit from sparsity on GPUs.
andylolu2/cutlass
CUDA Templates for Linear Algebra Subroutines
andylolu2/gpt-neox
An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.
andylolu2/gpu-stats
andylolu2/idiots
andylolu2/ivy
The Unified Machine Learning Framework
andylolu2/jax-flow-matching
andylolu2/jax-monads
Playing around with monads in JAX
andylolu2/llm-ol
Building a multilingual machine ontologist with language models
andylolu2/nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
andylolu2/nanotron
Minimalistic large language model 3D-parallelism training
andylolu2/simpleConv
andylolu2/tic-tac-gpt
Interpreting sequence models of Tic Tac Toe games.
andylolu2/transformer-lens-docker
Base docker image for Mech Intern research
andylolu2/vast-ai-setup