Interactively inspect module inputs, outputs, parameters, and gradients.

The simplest, fastest repository for training/finetuning medium-sized GPTs.

A CLI tool to convert your codebase into a single LLM prompt with source tree, prompt templating, and token counting.

A tool for working with stacked PRs on github.

Helpful tools and examples for working with flex-attention

This repository contains the experimental PyTorch native float8 training UX

Deep inspection of Python objects

Master programming by recreating your favorite technologies from scratch.

🔍 A Hex Editor for Reverse Engineers, Programmers and people who value their retinas when working at 3 AM.

Collaborative Collection of C++ Best Practices. This online resource is part of Jason Turner's collection of C++ Best Practices resources. See README.md for more information.

Count your code, quickly.

Tile primitives for speedy kernels

Improved build system generator for CPython C, C++, Cython and Fortran extensions

Distribute and run LLMs with a single file.

This is the Rust course used by the Android team at Google. It provides you the material to quickly teach Rust.

Puzzles for learning Triton

Containers for machine learning

QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference

A native PyTorch Library for large model training

Ring attention implementation with flash attention

Annotated version of the Mamba paper

Marp for VS Code: Create slide deck written in Marp Markdown on VS Code

Official Code for Stable Cascade

Large World Model -- Modeling Text and Video with Millions Context

CUDA Templates for Linear Algebra Subroutines

Cuda extensions for PyTorch

FlashInfer: Kernel Library for LLM Serving

CUDA Kernel Benchmarking Library