Train the smallest LM you can that fits in 16MB. Best model wins!

A lightweight inference engine supporting speculative speculative decoding (SSD).

KV Cache & LoRA for minGPT

Course on Flash-attention in Triton

From Minimal GEMM to Everything

Lists of company wise questions. Every csv file in the companies directory corresponds to a list of questions on leetcode for a specific company based on the leetcode company tags. Updated as of 20…

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…

Student version of Assignment 1 for Stanford CS336 - Language Modeling From Scratch

Official inference repo for FLUX.2 models

Flux 2 image generation model pure C inference

Claude Code skill that removes signs of AI-generated writing from text

The missing tiktoken training code

A curriculum for learning about gpu performance engineering, from scratch to what the frontier AI labs do

Shortest solutions for CS231n 2021-2026

~950 line, minimal, extensible LLM inference engine built from scratch.

Simple OSINT script to find Instagram profiles by name and e-mail/phone

Implementing scalable LLMs in pure JAX (no third-party libraries)

List of AI Residency Programs

Based on Nano-vLLM, a simple replication of vLLM with self-contained paged attention and flash attention implementation

Train your own speech AI model from scratch

Learn CUDA with PyTorch

Official code of Why Knowledge Distillation Works in Generative Models: A Minimal Working Explanation (NeurIPS 2025)

Big & Small LLMs working together

Agentic AI Infrastructure for magnifying HUMAN capabilities.

Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation

Examples demonstrating available options to program multiple GPUs in a single node or a cluster

Patterns and behaviors for GPU computing