The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

A guidance language for controlling large language models.

llama3 implementation one matrix multiplication at a time

Official inference library for Mistral models

PyTorch code and models for the DINOv2 self-supervised learning method.

tiny vision language model

Time series Timeseries Deep Learning Machine Learning Python Pytorch fastai | State-of-the-art Deep Learning library for Time Series and Sequences in Pytorch / fastai

Code for the book Deep Learning with PyTorch by Eli Stevens, Luca Antiga, and Thomas Viehmann.

Material for gpu-mode lectures

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

Algorithms for outlier, adversarial and drift detection

Puzzles for learning Triton

Felafax is building AI infra for non-NVIDIA GPUs

Minimal implementation of scalable rectified flow transformers, based on SD3's approach

fMRI-to-image reconstruction on the NSD dataset.

Easy, fast and very cheap training and inference on AWS Trainium and Inferentia chips.

A benchmark for few-shot evaluation of foundation models for electronic health records (EHRs)

Example code for AWS Neuron SDK developers building inference and training applications

Hands-on workshop for distributed training and hosting on SageMaker

Air pollution prediction for Skopje