ML Frameworks

It teaches how LLMs work by implementing tokenization, attention, pretraining, and finetuning in pure PyTorch, one notebook at a time.

It exists to handle the tedious wiring—annotations, dataset formats, tracking—that sits between a trained model and a useful application.

Google's attempt to own the full machine-learning stack, from research lab to Raspberry Pi.

DeepFace wraps a zoo of pre-trained face models into a single Python API so you can verify identities, search databases, and analyze attributes without hand-rolling a Keras pipeline.

It exists because keeping up with the training loops, quantization tricks, and inference stacks of 100+ models is a full-time job most developers would rather delegate.

A volunteer-maintained Python machine learning module built on SciPy since 2007.

Ultralytics wants to stop you from stitching together separate repos for every computer vision task by bundling detection, segmentation, tracking, and pose estimation into one YOLO-backed package.

A PyTorch toolkit that treats robot learning like Hugging Face treats NLP: standardized datasets, pretrained policies, and one interface for many arms.

TimesFM is a pretrained decoder-only transformer that turns historical sequences into point and quantile forecasts without training from scratch.

YOLOv5 made real-time object detection as easy as `torch.hub.load`, then exported to everything from iOS to edge chips.

PyTorch exists to give researchers and engineers GPU-accelerated tensor math and automatic differentiation without forcing them to leave Python’s debugger and stack traces behind.

Ray treats distributed computing as a Python primitive, then layers on libraries for training, tuning, serving, and reinforcement learning.

Because training a transformer shouldn't require 245MB of PyTorch just to multiply matrices.

A curated library of 60+ deep learning papers with side-by-side code and annotations, because reading arXiv shouldn't require a PhD in suffering.

A readable reference for how classic machine learning actually works under the hood, from backprop to genetic algorithms.

DeepSpeed is the optimization library that let the BLOOM and MT-530B teams train models too large to fit in any single GPU.

It centralizes model definitions so the same architecture works across PyTorch, JAX, vLLM, and llama.cpp without rewrites.

exo auto-discovers Apple devices on your network and shards frontier models across them, turning a pile of Macs into a single inference engine.

For when you outgrow micrograd but still want a deep learning compiler small enough to read and hack.

An inference runtime that strips away third-party dependencies to run neural networks on everything from smartphones to smartwatches.