Make PyTorch models up to 40% faster! Thunder is a source to source compiler for PyTorch. It enables using different hardware executors at once; across one or thousands of GPUs.

LLM101n: Let's build a Storyteller

PyTorch native finetuning library

A fast, easy-to-use, production-ready inference server for computer vision supporting deployment of many popular model architectures and fine-tuned models.

You like pytorch? You like micrograd? You love tinygrad! ❤️

Benchmark of detection methods for anomalies and obstacles in traffic images.

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga…

A modular, easy to extend GFlowNet library

Neural Point-Based Graphics

[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation

Understanding Deep Learning - Simon J.D. Prince

Generating Local Point Signature for "A Robust Local Spectral Descriptor for Matching Non-Rigid Shapes with Incompatible Shape Structures"

FreeFEM user documentation

Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".

Code for T-Few from "Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning"

Council is an open-source platform for the rapid development and robust deployment of customized generative AI applications

Code for visualizing the loss landscape of neural nets

Make huge neural nets fit in memory

Python code for "Probabilistic Machine learning" book by Kevin Murphy

jax library for E3 Equivariant Neural Networks

DPPIN: A Biological Repository of Dynamic Protein-Protein Interaction Network Data, IEEE BigData 2022

Llemmings is a game being written by LLMs. Only. Humans copy and paste code.

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

TAO best practices. How to adapt for a new domain, new classes, and generalize the model with a small dataset using Nvidia's TAO toolkit

Compilers Principles, Techniques, & Tools (a.k.a purple dragon book) second edition exercise answers.

Diffusers Stable Diffusion as a Cog model